[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-synthesize-research":3,"mdc-7h7g6l-key":34,"related-repo-anthropic-synthesize-research":1587,"related-org-anthropic-synthesize-research":1704},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":32,"mdContent":33},"synthesize-research","synthesize user research into insights","Synthesize user research from interviews, surveys, and feedback into structured insights. Use when you have a pile of interview notes, survey responses, or support tickets to make sense of, need to extract themes and rank findings by frequency and impact, or want to turn raw feedback into roadmap recommendations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"anthropic","Anthropic","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fanthropic.png","anthropics",[13,17,20],{"name":14,"slug":15,"type":16},"Research","research","tag",{"name":18,"slug":19,"type":16},"User Research","user-research",{"name":21,"slug":22,"type":16},"Product Management","product-management",22885,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins","2026-04-06T17:59:08.941625",null,2736,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Ftree\u002FHEAD\u002Fproduct-management\u002Fskills\u002Fsynthesize-research","---\nname: synthesize-research\ndescription: Synthesize user research from interviews, surveys, and feedback into structured insights. Use when you have a pile of interview notes, survey responses, or support tickets to make sense of, need to extract themes and rank findings by frequency and impact, or want to turn raw feedback into roadmap recommendations.\nargument-hint: \"\u003Cresearch topic or question>\"\n---\n\n# Synthesize Research\n\n> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](..\u002F..\u002FCONNECTORS.md).\n\nSynthesize user research from multiple sources into structured insights and recommendations.\n\n## Usage\n\n```\n\u002Fsynthesize-research $ARGUMENTS\n```\n\n## Workflow\n\n### 1. Gather Research Inputs\n\nAccept research from any combination of:\n- **Pasted text**: Interview notes, transcripts, survey responses, feedback\n- **Uploaded files**: Research documents, spreadsheets, recordings summaries\n- **~~knowledge base** (if connected): Search for research documents, interview notes, survey results\n- **~~user feedback** (if connected): Pull recent support tickets, feature requests, bug reports\n- **~~product analytics** (if connected): Pull usage data, funnel metrics, behavioral data\n- **~~meeting transcription** (if connected): Pull interview recordings, meeting summaries, and discussion notes\n\nAsk the user what they have:\n- What type of research? (interviews, surveys, usability tests, analytics, support tickets, sales call notes)\n- How many sources \u002F participants?\n- Is there a specific question or hypothesis they are investigating?\n- What decisions will this research inform?\n\n### 2. Process the Research\n\nFor each source, extract:\n- **Key observations**: What did users say, do, or experience?\n- **Quotes**: Verbatim quotes that illustrate important points\n- **Behaviors**: What users actually did (vs what they said they do)\n- **Pain points**: Frustrations, workarounds, and unmet needs\n- **Positive signals**: What works well, moments of delight\n- **Context**: User segment, use case, experience level\n\n### 3. Identify Themes and Patterns\n\nApply thematic analysis — see **Research Synthesis Methodology** below for detailed guidance on thematic analysis, affinity mapping, and triangulation techniques.\n\nGroup observations into themes, count frequency across participants, and assess impact severity. Note contradictions and surprises.\n\nCreate a priority matrix:\n- **High frequency + High impact**: Top priority findings\n- **Low frequency + High impact**: Important for specific segments\n- **High frequency + Low impact**: Quality-of-life improvements\n- **Low frequency + Low impact**: Note but deprioritize\n\n### 4. Generate the Synthesis\n\nProduce a structured research synthesis:\n\n#### Research Overview\n- Methodology: what types of research, how many participants\u002Fsources\n- Research question(s): what we set out to learn\n- Timeframe: when the research was conducted\n\n#### Key Findings\nFor each major finding (aim for 5-8):\n- **Finding statement**: One clear sentence describing the insight\n- **Evidence**: Supporting quotes, data points, or observations (with source attribution)\n- **Frequency**: How many participants\u002Fsources support this finding\n- **Impact**: How significantly this affects the user experience or business\n- **Confidence level**: High (strong evidence), Medium (suggestive), Low (early signal)\n\nOrder findings by priority (frequency x impact).\n\n#### User Segments \u002F Personas\nIf the research reveals distinct user segments:\n- Segment name and description\n- Key characteristics and behaviors\n- Unique needs and pain points\n- Size estimate if data is available\n\n#### Opportunity Areas\nBased on the findings, identify opportunity areas:\n- What user needs are unmet or underserved\n- Where do current solutions fall short\n- What new capabilities would unlock value\n- Prioritized by potential impact\n\n#### Recommendations\nSpecific, actionable recommendations:\n- What to build, change, or investigate further\n- Tied back to specific findings\n- Prioritized by impact and feasibility\n\n#### Open Questions\nWhat the research did not answer:\n- Gaps in understanding\n- Areas needing further investigation\n- Suggested follow-up research methods\n\n### 5. Review and Extend\n\nAfter generating the synthesis:\n- Ask if any findings need more detail or different framing\n- Offer to generate specific artifacts: persona documents, opportunity maps, research presentations\n- Offer to create follow-up research plans for open questions\n- Offer to draft product implications (how findings should influence the roadmap)\n\n## Research Synthesis Methodology\n\n### Thematic Analysis\nThe core method for synthesizing qualitative research:\n\n1. **Familiarization**: Read through all the data. Get a feel for the overall landscape before coding anything.\n2. **Initial coding**: Go through the data systematically. Tag each observation, quote, or data point with descriptive codes. Be generous with codes — it is easier to merge than to split later.\n3. **Theme development**: Group related codes into candidate themes. A theme captures something important about the data in relation to the research question.\n4. **Theme review**: Check themes against the data. Does each theme have sufficient evidence? Are themes distinct from each other? Do they tell a coherent story?\n5. **Theme refinement**: Define and name each theme clearly. Write a 1-2 sentence description of what each theme captures.\n6. **Report**: Write up the themes as findings with supporting evidence.\n\n### Affinity Mapping\nA collaborative method for grouping observations:\n\n1. **Capture observations**: Write each distinct observation, quote, or data point as a separate note\n2. **Cluster**: Group related notes together based on similarity. Do not pre-define categories — let them emerge from the data.\n3. **Label clusters**: Give each cluster a descriptive name that captures the common thread\n4. **Organize clusters**: Arrange clusters into higher-level groups if patterns emerge\n5. **Identify themes**: The clusters and their relationships reveal the key themes\n\n**Tips for affinity mapping**:\n- One observation per note. Do not combine multiple insights.\n- Move notes between clusters freely. The first grouping is rarely the best.\n- If a cluster gets too large, it probably contains multiple themes. Split it.\n- Outliers are interesting. Do not force every observation into a cluster.\n- The process of grouping is as valuable as the output. It builds shared understanding.\n\n### Triangulation\nStrengthen findings by combining multiple data sources:\n\n- **Methodological triangulation**: Same question, different methods (interviews + survey + analytics)\n- **Source triangulation**: Same method, different participants or segments\n- **Temporal triangulation**: Same observation at different points in time\n\nA finding supported by multiple sources and methods is much stronger than one supported by a single source. When sources disagree, that is interesting — it may reveal different user segments or contexts.\n\n## Interview Note Analysis\n\n### Extracting Insights from Interview Notes\nFor each interview, identify:\n\n**Observations**: What did the participant describe doing, experiencing, or feeling?\n- Distinguish between behaviors (what they do) and attitudes (what they think\u002Ffeel)\n- Note context: when, where, with whom, how often\n- Flag workarounds — these are unmet needs in disguise\n\n**Direct quotes**: Verbatim statements that powerfully illustrate a point\n- Good quotes are specific and vivid, not generic\n- Attribute to participant type, not name: \"Enterprise admin, 200-person team\" not \"Sarah\"\n- A quote is evidence, not a finding. The finding is your interpretation of what the quote means.\n\n**Behaviors vs stated preferences**: What people DO often differs from what they SAY they want\n- Behavioral observations are stronger evidence than stated preferences\n- If a participant says \"I want feature X\" but their workflow shows they never use similar features, note the contradiction\n- Look for revealed preferences through actual behavior\n\n**Signals of intensity**: How much does this matter to the participant?\n- Emotional language: frustration, excitement, resignation\n- Frequency: how often do they encounter this issue\n- Workarounds: how much effort do they expend working around the problem\n- Impact: what is the consequence when things go wrong\n\n### Cross-Interview Analysis\nAfter processing individual interviews:\n- Look for patterns: which observations appear across multiple participants?\n- Note frequency: how many participants mentioned each theme?\n- Identify segments: do different types of users have different patterns?\n- Surface contradictions: where do participants disagree? This often reveals meaningful segments.\n- Find surprises: what challenged your prior assumptions?\n\n## Survey Data Interpretation\n\n### Quantitative Survey Analysis\n- **Response rate**: How representative is the sample? Low response rates may introduce bias.\n- **Distribution**: Look at the shape of responses, not just averages. A bimodal distribution (lots of 1s and 5s) tells a different story than a normal distribution (lots of 3s).\n- **Segmentation**: Break down responses by user segment. Aggregates can mask important differences.\n- **Statistical significance**: For small samples, be cautious about drawing conclusions from small differences.\n- **Benchmark comparison**: How do scores compare to industry benchmarks or previous surveys?\n\n### Open-Ended Survey Response Analysis\n- Treat open-ended responses like mini interview notes\n- Code each response with themes\n- Count frequency of themes across responses\n- Pull representative quotes for each theme\n- Look for themes that appear in open-ended responses but not in structured questions — these are things you did not think to ask about\n\n### Common Survey Analysis Mistakes\n- Reporting averages without distributions. A 3.5 average could mean everyone is lukewarm or half love it and half hate it.\n- Ignoring non-response bias. The people who did not respond may be systematically different.\n- Over-interpreting small differences. A 0.1 point change in NPS is noise, not signal.\n- Treating Likert scales as interval data. The difference between \"Strongly Agree\" and \"Agree\" is not necessarily the same as between \"Agree\" and \"Neutral.\"\n- Confusing correlation with causation in cross-tabulations.\n\n## Combining Qualitative and Quantitative Insights\n\n### The Qual-Quant Feedback Loop\n- **Qualitative first**: Interviews and observation reveal WHAT is happening and WHY. They generate hypotheses.\n- **Quantitative validation**: Surveys and analytics reveal HOW MUCH and HOW MANY. They test hypotheses at scale.\n- **Qualitative deep-dive**: Return to qualitative methods to understand unexpected quantitative findings.\n\n### Integration Strategies\n- Use quantitative data to prioritize qualitative findings. A theme from interviews is more important if usage data shows it affects many users.\n- Use qualitative data to explain quantitative anomalies. A drop in retention is a number; interviews reveal it is because of a confusing onboarding change.\n- Present combined evidence: \"47% of surveyed users report difficulty with X (survey), and interviews reveal this is because Y (qualitative finding).\"\n\n### When Sources Disagree\n- Quantitative and qualitative sources may tell different stories. This is signal, not error.\n- Check if the disagreement is due to different populations being measured\n- Check if stated preferences (survey) differ from actual behavior (analytics)\n- Check if the quantitative question captured what you think it captured\n- Report the disagreement honestly and investigate further rather than choosing one source\n\n## Persona Development from Research\n\n### Building Evidence-Based Personas\nPersonas should emerge from research data, not imagination:\n\n1. **Identify behavioral patterns**: Look for clusters of similar behaviors, goals, and contexts across participants\n2. **Define distinguishing variables**: What dimensions differentiate one cluster from another? (e.g., company size, technical skill, usage frequency, primary use case)\n3. **Create persona profiles**: For each behavioral cluster:\n   - Name and brief description\n   - Key behaviors and goals\n   - Pain points and needs\n   - Context (role, company, tools used)\n   - Representative quotes\n4. **Validate with data**: Can you size each persona segment using quantitative data?\n\n### Persona Template\n```\n[Persona Name] — [One-line description]\n\nWho they are:\n- Role, company type\u002Fsize, experience level\n- How they found\u002Fstarted using the product\n\nWhat they are trying to accomplish:\n- Primary goals and jobs to be done\n- How they measure success\n\nHow they use the product:\n- Frequency and depth of usage\n- Key workflows and features used\n- Tools they use alongside this product\n\nKey pain points:\n- Top 3 frustrations or unmet needs\n- Workarounds they have developed\n\nWhat they value:\n- What matters most in a solution\n- What would make them switch or churn\n\nRepresentative quotes:\n- 2-3 verbatim quotes that capture this persona's perspective\n```\n\n### Common Persona Mistakes\n- Demographic personas: defining by age\u002Fgender\u002Flocation instead of behavior. Behavior predicts product needs better than demographics.\n- Too many personas: 3-5 is the sweet spot. More than that and they are not actionable.\n- Fictional personas: made up based on assumptions rather than research data.\n- Static personas: never updated as the product and market evolve.\n- Personas without implications: a persona that does not change any product decisions is not useful.\n\n## Opportunity Sizing\n\n### Estimating Opportunity Size\nFor each research finding or opportunity area, estimate:\n\n- **Addressable users**: How many users could benefit from addressing this? Use product analytics, survey data, or market data to estimate.\n- **Frequency**: How often do affected users encounter this issue? (Daily, weekly, monthly, one-time)\n- **Severity**: How much does this issue impact users when it occurs? (Blocker, significant friction, minor annoyance)\n- **Willingness to pay**: Would addressing this drive upgrades, retention, or new customer acquisition?\n\n### Opportunity Scoring\nScore opportunities on a simple matrix:\n\n- **Impact**: (Users affected) x (Frequency) x (Severity) = impact score\n- **Evidence strength**: How confident are we in the finding? (Multiple sources > single source, behavioral data > stated preferences)\n- **Strategic alignment**: Does this opportunity align with company strategy and product vision?\n- **Feasibility**: Can we realistically address this? (Technical feasibility, resource availability, time to impact)\n\n### Presenting Opportunity Sizing\n- Be transparent about assumptions and confidence levels\n- Show the math: \"Based on support ticket volume, approximately 2,000 users per month encounter this issue. Interview data suggests 60% of them consider it a significant blocker.\"\n- Use ranges rather than false precision: \"This affects 1,500-2,500 users monthly\" not \"This affects 2,137 users monthly\"\n- Compare opportunities against each other to create a relative ranking, not just absolute scores\n\n## Output Format\n\nUse clear headers and structured formatting. Each finding should stand on its own — a reader should be able to read any single finding and understand it without reading the rest.\n\n## Tips\n\n- Let the data speak. Do not force findings into a predetermined narrative.\n- Distinguish between what users say and what they do. Behavioral data is stronger than stated preferences.\n- Quotes are powerful evidence. Include them generously, with attribution to participant type (not name).\n- Be explicit about confidence levels. A finding from 2 interviews is a hypothesis, not a conclusion.\n- Contradictions in the data are interesting, not inconvenient. They often reveal distinct user segments.\n- Recommendations should be specific enough to act on. \"Improve onboarding\" is not actionable. \"Add a progress indicator to the setup flow\" is.\n- Resist the temptation to synthesize too many themes. 5-8 strong findings are better than 20 weak ones.\n",{"data":35,"body":37},{"name":4,"description":6,"argument-hint":36},"\u003Cresearch topic or question>",{"type":38,"children":39},"root",[40,48,67,72,79,92,98,105,110,176,181,204,210,215,278,284,296,301,306,349,355,360,367,385,391,396,449,454,460,465,488,494,499,522,528,533,551,557,562,580,586,591,614,619,625,630,694,700,705,758,768,796,802,807,840,845,851,857,862,872,890,900,918,928,946,956,979,985,990,1018,1024,1030,1083,1089,1117,1123,1151,1157,1163,1196,1202,1220,1226,1254,1260,1266,1271,1342,1348,1357,1363,1391,1397,1403,1408,1450,1456,1461,1503,1509,1532,1538,1543,1549],{"type":41,"tag":42,"props":43,"children":44},"element","h1",{"id":4},[45],{"type":46,"value":47},"text","Synthesize Research",{"type":41,"tag":49,"props":50,"children":51},"blockquote",{},[52],{"type":41,"tag":53,"props":54,"children":55},"p",{},[56,58,65],{"type":46,"value":57},"If you see unfamiliar placeholders or need to check which tools are connected, see ",{"type":41,"tag":59,"props":60,"children":62},"a",{"href":61},"..\u002F..\u002FCONNECTORS.md",[63],{"type":46,"value":64},"CONNECTORS.md",{"type":46,"value":66},".",{"type":41,"tag":53,"props":68,"children":69},{},[70],{"type":46,"value":71},"Synthesize user research from multiple sources into structured insights and recommendations.",{"type":41,"tag":73,"props":74,"children":76},"h2",{"id":75},"usage",[77],{"type":46,"value":78},"Usage",{"type":41,"tag":80,"props":81,"children":85},"pre",{"className":82,"code":84,"language":46},[83],"language-text","\u002Fsynthesize-research $ARGUMENTS\n",[86],{"type":41,"tag":87,"props":88,"children":90},"code",{"__ignoreMap":89},"",[91],{"type":46,"value":84},{"type":41,"tag":73,"props":93,"children":95},{"id":94},"workflow",[96],{"type":46,"value":97},"Workflow",{"type":41,"tag":99,"props":100,"children":102},"h3",{"id":101},"_1-gather-research-inputs",[103],{"type":46,"value":104},"1. Gather Research Inputs",{"type":41,"tag":53,"props":106,"children":107},{},[108],{"type":46,"value":109},"Accept research from any combination of:",{"type":41,"tag":111,"props":112,"children":113},"ul",{},[114,126,136,146,156,166],{"type":41,"tag":115,"props":116,"children":117},"li",{},[118,124],{"type":41,"tag":119,"props":120,"children":121},"strong",{},[122],{"type":46,"value":123},"Pasted text",{"type":46,"value":125},": Interview notes, transcripts, survey responses, feedback",{"type":41,"tag":115,"props":127,"children":128},{},[129,134],{"type":41,"tag":119,"props":130,"children":131},{},[132],{"type":46,"value":133},"Uploaded files",{"type":46,"value":135},": Research documents, spreadsheets, recordings summaries",{"type":41,"tag":115,"props":137,"children":138},{},[139,144],{"type":41,"tag":119,"props":140,"children":141},{},[142],{"type":46,"value":143},"~~knowledge base",{"type":46,"value":145}," (if connected): Search for research documents, interview notes, survey results",{"type":41,"tag":115,"props":147,"children":148},{},[149,154],{"type":41,"tag":119,"props":150,"children":151},{},[152],{"type":46,"value":153},"~~user feedback",{"type":46,"value":155}," (if connected): Pull recent support tickets, feature requests, bug reports",{"type":41,"tag":115,"props":157,"children":158},{},[159,164],{"type":41,"tag":119,"props":160,"children":161},{},[162],{"type":46,"value":163},"~~product analytics",{"type":46,"value":165}," (if connected): Pull usage data, funnel metrics, behavioral data",{"type":41,"tag":115,"props":167,"children":168},{},[169,174],{"type":41,"tag":119,"props":170,"children":171},{},[172],{"type":46,"value":173},"~~meeting transcription",{"type":46,"value":175}," (if connected): Pull interview recordings, meeting summaries, and discussion notes",{"type":41,"tag":53,"props":177,"children":178},{},[179],{"type":46,"value":180},"Ask the user what they have:",{"type":41,"tag":111,"props":182,"children":183},{},[184,189,194,199],{"type":41,"tag":115,"props":185,"children":186},{},[187],{"type":46,"value":188},"What type of research? (interviews, surveys, usability tests, analytics, support tickets, sales call notes)",{"type":41,"tag":115,"props":190,"children":191},{},[192],{"type":46,"value":193},"How many sources \u002F participants?",{"type":41,"tag":115,"props":195,"children":196},{},[197],{"type":46,"value":198},"Is there a specific question or hypothesis they are investigating?",{"type":41,"tag":115,"props":200,"children":201},{},[202],{"type":46,"value":203},"What decisions will this research inform?",{"type":41,"tag":99,"props":205,"children":207},{"id":206},"_2-process-the-research",[208],{"type":46,"value":209},"2. Process the Research",{"type":41,"tag":53,"props":211,"children":212},{},[213],{"type":46,"value":214},"For each source, extract:",{"type":41,"tag":111,"props":216,"children":217},{},[218,228,238,248,258,268],{"type":41,"tag":115,"props":219,"children":220},{},[221,226],{"type":41,"tag":119,"props":222,"children":223},{},[224],{"type":46,"value":225},"Key observations",{"type":46,"value":227},": What did users say, do, or experience?",{"type":41,"tag":115,"props":229,"children":230},{},[231,236],{"type":41,"tag":119,"props":232,"children":233},{},[234],{"type":46,"value":235},"Quotes",{"type":46,"value":237},": Verbatim quotes that illustrate important points",{"type":41,"tag":115,"props":239,"children":240},{},[241,246],{"type":41,"tag":119,"props":242,"children":243},{},[244],{"type":46,"value":245},"Behaviors",{"type":46,"value":247},": What users actually did (vs what they said they do)",{"type":41,"tag":115,"props":249,"children":250},{},[251,256],{"type":41,"tag":119,"props":252,"children":253},{},[254],{"type":46,"value":255},"Pain points",{"type":46,"value":257},": Frustrations, workarounds, and unmet needs",{"type":41,"tag":115,"props":259,"children":260},{},[261,266],{"type":41,"tag":119,"props":262,"children":263},{},[264],{"type":46,"value":265},"Positive signals",{"type":46,"value":267},": What works well, moments of delight",{"type":41,"tag":115,"props":269,"children":270},{},[271,276],{"type":41,"tag":119,"props":272,"children":273},{},[274],{"type":46,"value":275},"Context",{"type":46,"value":277},": User segment, use case, experience level",{"type":41,"tag":99,"props":279,"children":281},{"id":280},"_3-identify-themes-and-patterns",[282],{"type":46,"value":283},"3. Identify Themes and Patterns",{"type":41,"tag":53,"props":285,"children":286},{},[287,289,294],{"type":46,"value":288},"Apply thematic analysis — see ",{"type":41,"tag":119,"props":290,"children":291},{},[292],{"type":46,"value":293},"Research Synthesis Methodology",{"type":46,"value":295}," below for detailed guidance on thematic analysis, affinity mapping, and triangulation techniques.",{"type":41,"tag":53,"props":297,"children":298},{},[299],{"type":46,"value":300},"Group observations into themes, count frequency across participants, and assess impact severity. Note contradictions and surprises.",{"type":41,"tag":53,"props":302,"children":303},{},[304],{"type":46,"value":305},"Create a priority matrix:",{"type":41,"tag":111,"props":307,"children":308},{},[309,319,329,339],{"type":41,"tag":115,"props":310,"children":311},{},[312,317],{"type":41,"tag":119,"props":313,"children":314},{},[315],{"type":46,"value":316},"High frequency + High impact",{"type":46,"value":318},": Top priority findings",{"type":41,"tag":115,"props":320,"children":321},{},[322,327],{"type":41,"tag":119,"props":323,"children":324},{},[325],{"type":46,"value":326},"Low frequency + High impact",{"type":46,"value":328},": Important for specific segments",{"type":41,"tag":115,"props":330,"children":331},{},[332,337],{"type":41,"tag":119,"props":333,"children":334},{},[335],{"type":46,"value":336},"High frequency + Low impact",{"type":46,"value":338},": Quality-of-life improvements",{"type":41,"tag":115,"props":340,"children":341},{},[342,347],{"type":41,"tag":119,"props":343,"children":344},{},[345],{"type":46,"value":346},"Low frequency + Low impact",{"type":46,"value":348},": Note but deprioritize",{"type":41,"tag":99,"props":350,"children":352},{"id":351},"_4-generate-the-synthesis",[353],{"type":46,"value":354},"4. Generate the Synthesis",{"type":41,"tag":53,"props":356,"children":357},{},[358],{"type":46,"value":359},"Produce a structured research synthesis:",{"type":41,"tag":361,"props":362,"children":364},"h4",{"id":363},"research-overview",[365],{"type":46,"value":366},"Research Overview",{"type":41,"tag":111,"props":368,"children":369},{},[370,375,380],{"type":41,"tag":115,"props":371,"children":372},{},[373],{"type":46,"value":374},"Methodology: what types of research, how many participants\u002Fsources",{"type":41,"tag":115,"props":376,"children":377},{},[378],{"type":46,"value":379},"Research question(s): what we set out to learn",{"type":41,"tag":115,"props":381,"children":382},{},[383],{"type":46,"value":384},"Timeframe: when the research was conducted",{"type":41,"tag":361,"props":386,"children":388},{"id":387},"key-findings",[389],{"type":46,"value":390},"Key Findings",{"type":41,"tag":53,"props":392,"children":393},{},[394],{"type":46,"value":395},"For each major finding (aim for 5-8):",{"type":41,"tag":111,"props":397,"children":398},{},[399,409,419,429,439],{"type":41,"tag":115,"props":400,"children":401},{},[402,407],{"type":41,"tag":119,"props":403,"children":404},{},[405],{"type":46,"value":406},"Finding statement",{"type":46,"value":408},": One clear sentence describing the insight",{"type":41,"tag":115,"props":410,"children":411},{},[412,417],{"type":41,"tag":119,"props":413,"children":414},{},[415],{"type":46,"value":416},"Evidence",{"type":46,"value":418},": Supporting quotes, data points, or observations (with source attribution)",{"type":41,"tag":115,"props":420,"children":421},{},[422,427],{"type":41,"tag":119,"props":423,"children":424},{},[425],{"type":46,"value":426},"Frequency",{"type":46,"value":428},": How many participants\u002Fsources support this finding",{"type":41,"tag":115,"props":430,"children":431},{},[432,437],{"type":41,"tag":119,"props":433,"children":434},{},[435],{"type":46,"value":436},"Impact",{"type":46,"value":438},": How significantly this affects the user experience or business",{"type":41,"tag":115,"props":440,"children":441},{},[442,447],{"type":41,"tag":119,"props":443,"children":444},{},[445],{"type":46,"value":446},"Confidence level",{"type":46,"value":448},": High (strong evidence), Medium (suggestive), Low (early signal)",{"type":41,"tag":53,"props":450,"children":451},{},[452],{"type":46,"value":453},"Order findings by priority (frequency x impact).",{"type":41,"tag":361,"props":455,"children":457},{"id":456},"user-segments-personas",[458],{"type":46,"value":459},"User Segments \u002F Personas",{"type":41,"tag":53,"props":461,"children":462},{},[463],{"type":46,"value":464},"If the research reveals distinct user segments:",{"type":41,"tag":111,"props":466,"children":467},{},[468,473,478,483],{"type":41,"tag":115,"props":469,"children":470},{},[471],{"type":46,"value":472},"Segment name and description",{"type":41,"tag":115,"props":474,"children":475},{},[476],{"type":46,"value":477},"Key characteristics and behaviors",{"type":41,"tag":115,"props":479,"children":480},{},[481],{"type":46,"value":482},"Unique needs and pain points",{"type":41,"tag":115,"props":484,"children":485},{},[486],{"type":46,"value":487},"Size estimate if data is available",{"type":41,"tag":361,"props":489,"children":491},{"id":490},"opportunity-areas",[492],{"type":46,"value":493},"Opportunity Areas",{"type":41,"tag":53,"props":495,"children":496},{},[497],{"type":46,"value":498},"Based on the findings, identify opportunity areas:",{"type":41,"tag":111,"props":500,"children":501},{},[502,507,512,517],{"type":41,"tag":115,"props":503,"children":504},{},[505],{"type":46,"value":506},"What user needs are unmet or underserved",{"type":41,"tag":115,"props":508,"children":509},{},[510],{"type":46,"value":511},"Where do current solutions fall short",{"type":41,"tag":115,"props":513,"children":514},{},[515],{"type":46,"value":516},"What new capabilities would unlock value",{"type":41,"tag":115,"props":518,"children":519},{},[520],{"type":46,"value":521},"Prioritized by potential impact",{"type":41,"tag":361,"props":523,"children":525},{"id":524},"recommendations",[526],{"type":46,"value":527},"Recommendations",{"type":41,"tag":53,"props":529,"children":530},{},[531],{"type":46,"value":532},"Specific, actionable recommendations:",{"type":41,"tag":111,"props":534,"children":535},{},[536,541,546],{"type":41,"tag":115,"props":537,"children":538},{},[539],{"type":46,"value":540},"What to build, change, or investigate further",{"type":41,"tag":115,"props":542,"children":543},{},[544],{"type":46,"value":545},"Tied back to specific findings",{"type":41,"tag":115,"props":547,"children":548},{},[549],{"type":46,"value":550},"Prioritized by impact and feasibility",{"type":41,"tag":361,"props":552,"children":554},{"id":553},"open-questions",[555],{"type":46,"value":556},"Open Questions",{"type":41,"tag":53,"props":558,"children":559},{},[560],{"type":46,"value":561},"What the research did not answer:",{"type":41,"tag":111,"props":563,"children":564},{},[565,570,575],{"type":41,"tag":115,"props":566,"children":567},{},[568],{"type":46,"value":569},"Gaps in understanding",{"type":41,"tag":115,"props":571,"children":572},{},[573],{"type":46,"value":574},"Areas needing further investigation",{"type":41,"tag":115,"props":576,"children":577},{},[578],{"type":46,"value":579},"Suggested follow-up research methods",{"type":41,"tag":99,"props":581,"children":583},{"id":582},"_5-review-and-extend",[584],{"type":46,"value":585},"5. Review and Extend",{"type":41,"tag":53,"props":587,"children":588},{},[589],{"type":46,"value":590},"After generating the synthesis:",{"type":41,"tag":111,"props":592,"children":593},{},[594,599,604,609],{"type":41,"tag":115,"props":595,"children":596},{},[597],{"type":46,"value":598},"Ask if any findings need more detail or different framing",{"type":41,"tag":115,"props":600,"children":601},{},[602],{"type":46,"value":603},"Offer to generate specific artifacts: persona documents, opportunity maps, research presentations",{"type":41,"tag":115,"props":605,"children":606},{},[607],{"type":46,"value":608},"Offer to create follow-up research plans for open questions",{"type":41,"tag":115,"props":610,"children":611},{},[612],{"type":46,"value":613},"Offer to draft product implications (how findings should influence the roadmap)",{"type":41,"tag":73,"props":615,"children":617},{"id":616},"research-synthesis-methodology",[618],{"type":46,"value":293},{"type":41,"tag":99,"props":620,"children":622},{"id":621},"thematic-analysis",[623],{"type":46,"value":624},"Thematic Analysis",{"type":41,"tag":53,"props":626,"children":627},{},[628],{"type":46,"value":629},"The core method for synthesizing qualitative research:",{"type":41,"tag":631,"props":632,"children":633},"ol",{},[634,644,654,664,674,684],{"type":41,"tag":115,"props":635,"children":636},{},[637,642],{"type":41,"tag":119,"props":638,"children":639},{},[640],{"type":46,"value":641},"Familiarization",{"type":46,"value":643},": Read through all the data. Get a feel for the overall landscape before coding anything.",{"type":41,"tag":115,"props":645,"children":646},{},[647,652],{"type":41,"tag":119,"props":648,"children":649},{},[650],{"type":46,"value":651},"Initial coding",{"type":46,"value":653},": Go through the data systematically. Tag each observation, quote, or data point with descriptive codes. Be generous with codes — it is easier to merge than to split later.",{"type":41,"tag":115,"props":655,"children":656},{},[657,662],{"type":41,"tag":119,"props":658,"children":659},{},[660],{"type":46,"value":661},"Theme development",{"type":46,"value":663},": Group related codes into candidate themes. A theme captures something important about the data in relation to the research question.",{"type":41,"tag":115,"props":665,"children":666},{},[667,672],{"type":41,"tag":119,"props":668,"children":669},{},[670],{"type":46,"value":671},"Theme review",{"type":46,"value":673},": Check themes against the data. Does each theme have sufficient evidence? Are themes distinct from each other? Do they tell a coherent story?",{"type":41,"tag":115,"props":675,"children":676},{},[677,682],{"type":41,"tag":119,"props":678,"children":679},{},[680],{"type":46,"value":681},"Theme refinement",{"type":46,"value":683},": Define and name each theme clearly. Write a 1-2 sentence description of what each theme captures.",{"type":41,"tag":115,"props":685,"children":686},{},[687,692],{"type":41,"tag":119,"props":688,"children":689},{},[690],{"type":46,"value":691},"Report",{"type":46,"value":693},": Write up the themes as findings with supporting evidence.",{"type":41,"tag":99,"props":695,"children":697},{"id":696},"affinity-mapping",[698],{"type":46,"value":699},"Affinity Mapping",{"type":41,"tag":53,"props":701,"children":702},{},[703],{"type":46,"value":704},"A collaborative method for grouping observations:",{"type":41,"tag":631,"props":706,"children":707},{},[708,718,728,738,748],{"type":41,"tag":115,"props":709,"children":710},{},[711,716],{"type":41,"tag":119,"props":712,"children":713},{},[714],{"type":46,"value":715},"Capture observations",{"type":46,"value":717},": Write each distinct observation, quote, or data point as a separate note",{"type":41,"tag":115,"props":719,"children":720},{},[721,726],{"type":41,"tag":119,"props":722,"children":723},{},[724],{"type":46,"value":725},"Cluster",{"type":46,"value":727},": Group related notes together based on similarity. Do not pre-define categories — let them emerge from the data.",{"type":41,"tag":115,"props":729,"children":730},{},[731,736],{"type":41,"tag":119,"props":732,"children":733},{},[734],{"type":46,"value":735},"Label clusters",{"type":46,"value":737},": Give each cluster a descriptive name that captures the common thread",{"type":41,"tag":115,"props":739,"children":740},{},[741,746],{"type":41,"tag":119,"props":742,"children":743},{},[744],{"type":46,"value":745},"Organize clusters",{"type":46,"value":747},": Arrange clusters into higher-level groups if patterns emerge",{"type":41,"tag":115,"props":749,"children":750},{},[751,756],{"type":41,"tag":119,"props":752,"children":753},{},[754],{"type":46,"value":755},"Identify themes",{"type":46,"value":757},": The clusters and their relationships reveal the key themes",{"type":41,"tag":53,"props":759,"children":760},{},[761,766],{"type":41,"tag":119,"props":762,"children":763},{},[764],{"type":46,"value":765},"Tips for affinity mapping",{"type":46,"value":767},":",{"type":41,"tag":111,"props":769,"children":770},{},[771,776,781,786,791],{"type":41,"tag":115,"props":772,"children":773},{},[774],{"type":46,"value":775},"One observation per note. Do not combine multiple insights.",{"type":41,"tag":115,"props":777,"children":778},{},[779],{"type":46,"value":780},"Move notes between clusters freely. The first grouping is rarely the best.",{"type":41,"tag":115,"props":782,"children":783},{},[784],{"type":46,"value":785},"If a cluster gets too large, it probably contains multiple themes. Split it.",{"type":41,"tag":115,"props":787,"children":788},{},[789],{"type":46,"value":790},"Outliers are interesting. Do not force every observation into a cluster.",{"type":41,"tag":115,"props":792,"children":793},{},[794],{"type":46,"value":795},"The process of grouping is as valuable as the output. It builds shared understanding.",{"type":41,"tag":99,"props":797,"children":799},{"id":798},"triangulation",[800],{"type":46,"value":801},"Triangulation",{"type":41,"tag":53,"props":803,"children":804},{},[805],{"type":46,"value":806},"Strengthen findings by combining multiple data sources:",{"type":41,"tag":111,"props":808,"children":809},{},[810,820,830],{"type":41,"tag":115,"props":811,"children":812},{},[813,818],{"type":41,"tag":119,"props":814,"children":815},{},[816],{"type":46,"value":817},"Methodological triangulation",{"type":46,"value":819},": Same question, different methods (interviews + survey + analytics)",{"type":41,"tag":115,"props":821,"children":822},{},[823,828],{"type":41,"tag":119,"props":824,"children":825},{},[826],{"type":46,"value":827},"Source triangulation",{"type":46,"value":829},": Same method, different participants or segments",{"type":41,"tag":115,"props":831,"children":832},{},[833,838],{"type":41,"tag":119,"props":834,"children":835},{},[836],{"type":46,"value":837},"Temporal triangulation",{"type":46,"value":839},": Same observation at different points in time",{"type":41,"tag":53,"props":841,"children":842},{},[843],{"type":46,"value":844},"A finding supported by multiple sources and methods is much stronger than one supported by a single source. When sources disagree, that is interesting — it may reveal different user segments or contexts.",{"type":41,"tag":73,"props":846,"children":848},{"id":847},"interview-note-analysis",[849],{"type":46,"value":850},"Interview Note Analysis",{"type":41,"tag":99,"props":852,"children":854},{"id":853},"extracting-insights-from-interview-notes",[855],{"type":46,"value":856},"Extracting Insights from Interview Notes",{"type":41,"tag":53,"props":858,"children":859},{},[860],{"type":46,"value":861},"For each interview, identify:",{"type":41,"tag":53,"props":863,"children":864},{},[865,870],{"type":41,"tag":119,"props":866,"children":867},{},[868],{"type":46,"value":869},"Observations",{"type":46,"value":871},": What did the participant describe doing, experiencing, or feeling?",{"type":41,"tag":111,"props":873,"children":874},{},[875,880,885],{"type":41,"tag":115,"props":876,"children":877},{},[878],{"type":46,"value":879},"Distinguish between behaviors (what they do) and attitudes (what they think\u002Ffeel)",{"type":41,"tag":115,"props":881,"children":882},{},[883],{"type":46,"value":884},"Note context: when, where, with whom, how often",{"type":41,"tag":115,"props":886,"children":887},{},[888],{"type":46,"value":889},"Flag workarounds — these are unmet needs in disguise",{"type":41,"tag":53,"props":891,"children":892},{},[893,898],{"type":41,"tag":119,"props":894,"children":895},{},[896],{"type":46,"value":897},"Direct quotes",{"type":46,"value":899},": Verbatim statements that powerfully illustrate a point",{"type":41,"tag":111,"props":901,"children":902},{},[903,908,913],{"type":41,"tag":115,"props":904,"children":905},{},[906],{"type":46,"value":907},"Good quotes are specific and vivid, not generic",{"type":41,"tag":115,"props":909,"children":910},{},[911],{"type":46,"value":912},"Attribute to participant type, not name: \"Enterprise admin, 200-person team\" not \"Sarah\"",{"type":41,"tag":115,"props":914,"children":915},{},[916],{"type":46,"value":917},"A quote is evidence, not a finding. The finding is your interpretation of what the quote means.",{"type":41,"tag":53,"props":919,"children":920},{},[921,926],{"type":41,"tag":119,"props":922,"children":923},{},[924],{"type":46,"value":925},"Behaviors vs stated preferences",{"type":46,"value":927},": What people DO often differs from what they SAY they want",{"type":41,"tag":111,"props":929,"children":930},{},[931,936,941],{"type":41,"tag":115,"props":932,"children":933},{},[934],{"type":46,"value":935},"Behavioral observations are stronger evidence than stated preferences",{"type":41,"tag":115,"props":937,"children":938},{},[939],{"type":46,"value":940},"If a participant says \"I want feature X\" but their workflow shows they never use similar features, note the contradiction",{"type":41,"tag":115,"props":942,"children":943},{},[944],{"type":46,"value":945},"Look for revealed preferences through actual behavior",{"type":41,"tag":53,"props":947,"children":948},{},[949,954],{"type":41,"tag":119,"props":950,"children":951},{},[952],{"type":46,"value":953},"Signals of intensity",{"type":46,"value":955},": How much does this matter to the participant?",{"type":41,"tag":111,"props":957,"children":958},{},[959,964,969,974],{"type":41,"tag":115,"props":960,"children":961},{},[962],{"type":46,"value":963},"Emotional language: frustration, excitement, resignation",{"type":41,"tag":115,"props":965,"children":966},{},[967],{"type":46,"value":968},"Frequency: how often do they encounter this issue",{"type":41,"tag":115,"props":970,"children":971},{},[972],{"type":46,"value":973},"Workarounds: how much effort do they expend working around the problem",{"type":41,"tag":115,"props":975,"children":976},{},[977],{"type":46,"value":978},"Impact: what is the consequence when things go wrong",{"type":41,"tag":99,"props":980,"children":982},{"id":981},"cross-interview-analysis",[983],{"type":46,"value":984},"Cross-Interview Analysis",{"type":41,"tag":53,"props":986,"children":987},{},[988],{"type":46,"value":989},"After processing individual interviews:",{"type":41,"tag":111,"props":991,"children":992},{},[993,998,1003,1008,1013],{"type":41,"tag":115,"props":994,"children":995},{},[996],{"type":46,"value":997},"Look for patterns: which observations appear across multiple participants?",{"type":41,"tag":115,"props":999,"children":1000},{},[1001],{"type":46,"value":1002},"Note frequency: how many participants mentioned each theme?",{"type":41,"tag":115,"props":1004,"children":1005},{},[1006],{"type":46,"value":1007},"Identify segments: do different types of users have different patterns?",{"type":41,"tag":115,"props":1009,"children":1010},{},[1011],{"type":46,"value":1012},"Surface contradictions: where do participants disagree? This often reveals meaningful segments.",{"type":41,"tag":115,"props":1014,"children":1015},{},[1016],{"type":46,"value":1017},"Find surprises: what challenged your prior assumptions?",{"type":41,"tag":73,"props":1019,"children":1021},{"id":1020},"survey-data-interpretation",[1022],{"type":46,"value":1023},"Survey Data Interpretation",{"type":41,"tag":99,"props":1025,"children":1027},{"id":1026},"quantitative-survey-analysis",[1028],{"type":46,"value":1029},"Quantitative Survey Analysis",{"type":41,"tag":111,"props":1031,"children":1032},{},[1033,1043,1053,1063,1073],{"type":41,"tag":115,"props":1034,"children":1035},{},[1036,1041],{"type":41,"tag":119,"props":1037,"children":1038},{},[1039],{"type":46,"value":1040},"Response rate",{"type":46,"value":1042},": How representative is the sample? Low response rates may introduce bias.",{"type":41,"tag":115,"props":1044,"children":1045},{},[1046,1051],{"type":41,"tag":119,"props":1047,"children":1048},{},[1049],{"type":46,"value":1050},"Distribution",{"type":46,"value":1052},": Look at the shape of responses, not just averages. A bimodal distribution (lots of 1s and 5s) tells a different story than a normal distribution (lots of 3s).",{"type":41,"tag":115,"props":1054,"children":1055},{},[1056,1061],{"type":41,"tag":119,"props":1057,"children":1058},{},[1059],{"type":46,"value":1060},"Segmentation",{"type":46,"value":1062},": Break down responses by user segment. Aggregates can mask important differences.",{"type":41,"tag":115,"props":1064,"children":1065},{},[1066,1071],{"type":41,"tag":119,"props":1067,"children":1068},{},[1069],{"type":46,"value":1070},"Statistical significance",{"type":46,"value":1072},": For small samples, be cautious about drawing conclusions from small differences.",{"type":41,"tag":115,"props":1074,"children":1075},{},[1076,1081],{"type":41,"tag":119,"props":1077,"children":1078},{},[1079],{"type":46,"value":1080},"Benchmark comparison",{"type":46,"value":1082},": How do scores compare to industry benchmarks or previous surveys?",{"type":41,"tag":99,"props":1084,"children":1086},{"id":1085},"open-ended-survey-response-analysis",[1087],{"type":46,"value":1088},"Open-Ended Survey Response Analysis",{"type":41,"tag":111,"props":1090,"children":1091},{},[1092,1097,1102,1107,1112],{"type":41,"tag":115,"props":1093,"children":1094},{},[1095],{"type":46,"value":1096},"Treat open-ended responses like mini interview notes",{"type":41,"tag":115,"props":1098,"children":1099},{},[1100],{"type":46,"value":1101},"Code each response with themes",{"type":41,"tag":115,"props":1103,"children":1104},{},[1105],{"type":46,"value":1106},"Count frequency of themes across responses",{"type":41,"tag":115,"props":1108,"children":1109},{},[1110],{"type":46,"value":1111},"Pull representative quotes for each theme",{"type":41,"tag":115,"props":1113,"children":1114},{},[1115],{"type":46,"value":1116},"Look for themes that appear in open-ended responses but not in structured questions — these are things you did not think to ask about",{"type":41,"tag":99,"props":1118,"children":1120},{"id":1119},"common-survey-analysis-mistakes",[1121],{"type":46,"value":1122},"Common Survey Analysis Mistakes",{"type":41,"tag":111,"props":1124,"children":1125},{},[1126,1131,1136,1141,1146],{"type":41,"tag":115,"props":1127,"children":1128},{},[1129],{"type":46,"value":1130},"Reporting averages without distributions. A 3.5 average could mean everyone is lukewarm or half love it and half hate it.",{"type":41,"tag":115,"props":1132,"children":1133},{},[1134],{"type":46,"value":1135},"Ignoring non-response bias. The people who did not respond may be systematically different.",{"type":41,"tag":115,"props":1137,"children":1138},{},[1139],{"type":46,"value":1140},"Over-interpreting small differences. A 0.1 point change in NPS is noise, not signal.",{"type":41,"tag":115,"props":1142,"children":1143},{},[1144],{"type":46,"value":1145},"Treating Likert scales as interval data. The difference between \"Strongly Agree\" and \"Agree\" is not necessarily the same as between \"Agree\" and \"Neutral.\"",{"type":41,"tag":115,"props":1147,"children":1148},{},[1149],{"type":46,"value":1150},"Confusing correlation with causation in cross-tabulations.",{"type":41,"tag":73,"props":1152,"children":1154},{"id":1153},"combining-qualitative-and-quantitative-insights",[1155],{"type":46,"value":1156},"Combining Qualitative and Quantitative Insights",{"type":41,"tag":99,"props":1158,"children":1160},{"id":1159},"the-qual-quant-feedback-loop",[1161],{"type":46,"value":1162},"The Qual-Quant Feedback Loop",{"type":41,"tag":111,"props":1164,"children":1165},{},[1166,1176,1186],{"type":41,"tag":115,"props":1167,"children":1168},{},[1169,1174],{"type":41,"tag":119,"props":1170,"children":1171},{},[1172],{"type":46,"value":1173},"Qualitative first",{"type":46,"value":1175},": Interviews and observation reveal WHAT is happening and WHY. They generate hypotheses.",{"type":41,"tag":115,"props":1177,"children":1178},{},[1179,1184],{"type":41,"tag":119,"props":1180,"children":1181},{},[1182],{"type":46,"value":1183},"Quantitative validation",{"type":46,"value":1185},": Surveys and analytics reveal HOW MUCH and HOW MANY. They test hypotheses at scale.",{"type":41,"tag":115,"props":1187,"children":1188},{},[1189,1194],{"type":41,"tag":119,"props":1190,"children":1191},{},[1192],{"type":46,"value":1193},"Qualitative deep-dive",{"type":46,"value":1195},": Return to qualitative methods to understand unexpected quantitative findings.",{"type":41,"tag":99,"props":1197,"children":1199},{"id":1198},"integration-strategies",[1200],{"type":46,"value":1201},"Integration Strategies",{"type":41,"tag":111,"props":1203,"children":1204},{},[1205,1210,1215],{"type":41,"tag":115,"props":1206,"children":1207},{},[1208],{"type":46,"value":1209},"Use quantitative data to prioritize qualitative findings. A theme from interviews is more important if usage data shows it affects many users.",{"type":41,"tag":115,"props":1211,"children":1212},{},[1213],{"type":46,"value":1214},"Use qualitative data to explain quantitative anomalies. A drop in retention is a number; interviews reveal it is because of a confusing onboarding change.",{"type":41,"tag":115,"props":1216,"children":1217},{},[1218],{"type":46,"value":1219},"Present combined evidence: \"47% of surveyed users report difficulty with X (survey), and interviews reveal this is because Y (qualitative finding).\"",{"type":41,"tag":99,"props":1221,"children":1223},{"id":1222},"when-sources-disagree",[1224],{"type":46,"value":1225},"When Sources Disagree",{"type":41,"tag":111,"props":1227,"children":1228},{},[1229,1234,1239,1244,1249],{"type":41,"tag":115,"props":1230,"children":1231},{},[1232],{"type":46,"value":1233},"Quantitative and qualitative sources may tell different stories. This is signal, not error.",{"type":41,"tag":115,"props":1235,"children":1236},{},[1237],{"type":46,"value":1238},"Check if the disagreement is due to different populations being measured",{"type":41,"tag":115,"props":1240,"children":1241},{},[1242],{"type":46,"value":1243},"Check if stated preferences (survey) differ from actual behavior (analytics)",{"type":41,"tag":115,"props":1245,"children":1246},{},[1247],{"type":46,"value":1248},"Check if the quantitative question captured what you think it captured",{"type":41,"tag":115,"props":1250,"children":1251},{},[1252],{"type":46,"value":1253},"Report the disagreement honestly and investigate further rather than choosing one source",{"type":41,"tag":73,"props":1255,"children":1257},{"id":1256},"persona-development-from-research",[1258],{"type":46,"value":1259},"Persona Development from Research",{"type":41,"tag":99,"props":1261,"children":1263},{"id":1262},"building-evidence-based-personas",[1264],{"type":46,"value":1265},"Building Evidence-Based Personas",{"type":41,"tag":53,"props":1267,"children":1268},{},[1269],{"type":46,"value":1270},"Personas should emerge from research data, not imagination:",{"type":41,"tag":631,"props":1272,"children":1273},{},[1274,1284,1294,1332],{"type":41,"tag":115,"props":1275,"children":1276},{},[1277,1282],{"type":41,"tag":119,"props":1278,"children":1279},{},[1280],{"type":46,"value":1281},"Identify behavioral patterns",{"type":46,"value":1283},": Look for clusters of similar behaviors, goals, and contexts across participants",{"type":41,"tag":115,"props":1285,"children":1286},{},[1287,1292],{"type":41,"tag":119,"props":1288,"children":1289},{},[1290],{"type":46,"value":1291},"Define distinguishing variables",{"type":46,"value":1293},": What dimensions differentiate one cluster from another? (e.g., company size, technical skill, usage frequency, primary use case)",{"type":41,"tag":115,"props":1295,"children":1296},{},[1297,1302,1304],{"type":41,"tag":119,"props":1298,"children":1299},{},[1300],{"type":46,"value":1301},"Create persona profiles",{"type":46,"value":1303},": For each behavioral cluster:\n",{"type":41,"tag":111,"props":1305,"children":1306},{},[1307,1312,1317,1322,1327],{"type":41,"tag":115,"props":1308,"children":1309},{},[1310],{"type":46,"value":1311},"Name and brief description",{"type":41,"tag":115,"props":1313,"children":1314},{},[1315],{"type":46,"value":1316},"Key behaviors and goals",{"type":41,"tag":115,"props":1318,"children":1319},{},[1320],{"type":46,"value":1321},"Pain points and needs",{"type":41,"tag":115,"props":1323,"children":1324},{},[1325],{"type":46,"value":1326},"Context (role, company, tools used)",{"type":41,"tag":115,"props":1328,"children":1329},{},[1330],{"type":46,"value":1331},"Representative quotes",{"type":41,"tag":115,"props":1333,"children":1334},{},[1335,1340],{"type":41,"tag":119,"props":1336,"children":1337},{},[1338],{"type":46,"value":1339},"Validate with data",{"type":46,"value":1341},": Can you size each persona segment using quantitative data?",{"type":41,"tag":99,"props":1343,"children":1345},{"id":1344},"persona-template",[1346],{"type":46,"value":1347},"Persona Template",{"type":41,"tag":80,"props":1349,"children":1352},{"className":1350,"code":1351,"language":46},[83],"[Persona Name] — [One-line description]\n\nWho they are:\n- Role, company type\u002Fsize, experience level\n- How they found\u002Fstarted using the product\n\nWhat they are trying to accomplish:\n- Primary goals and jobs to be done\n- How they measure success\n\nHow they use the product:\n- Frequency and depth of usage\n- Key workflows and features used\n- Tools they use alongside this product\n\nKey pain points:\n- Top 3 frustrations or unmet needs\n- Workarounds they have developed\n\nWhat they value:\n- What matters most in a solution\n- What would make them switch or churn\n\nRepresentative quotes:\n- 2-3 verbatim quotes that capture this persona's perspective\n",[1353],{"type":41,"tag":87,"props":1354,"children":1355},{"__ignoreMap":89},[1356],{"type":46,"value":1351},{"type":41,"tag":99,"props":1358,"children":1360},{"id":1359},"common-persona-mistakes",[1361],{"type":46,"value":1362},"Common Persona Mistakes",{"type":41,"tag":111,"props":1364,"children":1365},{},[1366,1371,1376,1381,1386],{"type":41,"tag":115,"props":1367,"children":1368},{},[1369],{"type":46,"value":1370},"Demographic personas: defining by age\u002Fgender\u002Flocation instead of behavior. Behavior predicts product needs better than demographics.",{"type":41,"tag":115,"props":1372,"children":1373},{},[1374],{"type":46,"value":1375},"Too many personas: 3-5 is the sweet spot. More than that and they are not actionable.",{"type":41,"tag":115,"props":1377,"children":1378},{},[1379],{"type":46,"value":1380},"Fictional personas: made up based on assumptions rather than research data.",{"type":41,"tag":115,"props":1382,"children":1383},{},[1384],{"type":46,"value":1385},"Static personas: never updated as the product and market evolve.",{"type":41,"tag":115,"props":1387,"children":1388},{},[1389],{"type":46,"value":1390},"Personas without implications: a persona that does not change any product decisions is not useful.",{"type":41,"tag":73,"props":1392,"children":1394},{"id":1393},"opportunity-sizing",[1395],{"type":46,"value":1396},"Opportunity Sizing",{"type":41,"tag":99,"props":1398,"children":1400},{"id":1399},"estimating-opportunity-size",[1401],{"type":46,"value":1402},"Estimating Opportunity Size",{"type":41,"tag":53,"props":1404,"children":1405},{},[1406],{"type":46,"value":1407},"For each research finding or opportunity area, estimate:",{"type":41,"tag":111,"props":1409,"children":1410},{},[1411,1421,1430,1440],{"type":41,"tag":115,"props":1412,"children":1413},{},[1414,1419],{"type":41,"tag":119,"props":1415,"children":1416},{},[1417],{"type":46,"value":1418},"Addressable users",{"type":46,"value":1420},": How many users could benefit from addressing this? Use product analytics, survey data, or market data to estimate.",{"type":41,"tag":115,"props":1422,"children":1423},{},[1424,1428],{"type":41,"tag":119,"props":1425,"children":1426},{},[1427],{"type":46,"value":426},{"type":46,"value":1429},": How often do affected users encounter this issue? (Daily, weekly, monthly, one-time)",{"type":41,"tag":115,"props":1431,"children":1432},{},[1433,1438],{"type":41,"tag":119,"props":1434,"children":1435},{},[1436],{"type":46,"value":1437},"Severity",{"type":46,"value":1439},": How much does this issue impact users when it occurs? (Blocker, significant friction, minor annoyance)",{"type":41,"tag":115,"props":1441,"children":1442},{},[1443,1448],{"type":41,"tag":119,"props":1444,"children":1445},{},[1446],{"type":46,"value":1447},"Willingness to pay",{"type":46,"value":1449},": Would addressing this drive upgrades, retention, or new customer acquisition?",{"type":41,"tag":99,"props":1451,"children":1453},{"id":1452},"opportunity-scoring",[1454],{"type":46,"value":1455},"Opportunity Scoring",{"type":41,"tag":53,"props":1457,"children":1458},{},[1459],{"type":46,"value":1460},"Score opportunities on a simple matrix:",{"type":41,"tag":111,"props":1462,"children":1463},{},[1464,1473,1483,1493],{"type":41,"tag":115,"props":1465,"children":1466},{},[1467,1471],{"type":41,"tag":119,"props":1468,"children":1469},{},[1470],{"type":46,"value":436},{"type":46,"value":1472},": (Users affected) x (Frequency) x (Severity) = impact score",{"type":41,"tag":115,"props":1474,"children":1475},{},[1476,1481],{"type":41,"tag":119,"props":1477,"children":1478},{},[1479],{"type":46,"value":1480},"Evidence strength",{"type":46,"value":1482},": How confident are we in the finding? (Multiple sources > single source, behavioral data > stated preferences)",{"type":41,"tag":115,"props":1484,"children":1485},{},[1486,1491],{"type":41,"tag":119,"props":1487,"children":1488},{},[1489],{"type":46,"value":1490},"Strategic alignment",{"type":46,"value":1492},": Does this opportunity align with company strategy and product vision?",{"type":41,"tag":115,"props":1494,"children":1495},{},[1496,1501],{"type":41,"tag":119,"props":1497,"children":1498},{},[1499],{"type":46,"value":1500},"Feasibility",{"type":46,"value":1502},": Can we realistically address this? (Technical feasibility, resource availability, time to impact)",{"type":41,"tag":99,"props":1504,"children":1506},{"id":1505},"presenting-opportunity-sizing",[1507],{"type":46,"value":1508},"Presenting Opportunity Sizing",{"type":41,"tag":111,"props":1510,"children":1511},{},[1512,1517,1522,1527],{"type":41,"tag":115,"props":1513,"children":1514},{},[1515],{"type":46,"value":1516},"Be transparent about assumptions and confidence levels",{"type":41,"tag":115,"props":1518,"children":1519},{},[1520],{"type":46,"value":1521},"Show the math: \"Based on support ticket volume, approximately 2,000 users per month encounter this issue. Interview data suggests 60% of them consider it a significant blocker.\"",{"type":41,"tag":115,"props":1523,"children":1524},{},[1525],{"type":46,"value":1526},"Use ranges rather than false precision: \"This affects 1,500-2,500 users monthly\" not \"This affects 2,137 users monthly\"",{"type":41,"tag":115,"props":1528,"children":1529},{},[1530],{"type":46,"value":1531},"Compare opportunities against each other to create a relative ranking, not just absolute scores",{"type":41,"tag":73,"props":1533,"children":1535},{"id":1534},"output-format",[1536],{"type":46,"value":1537},"Output Format",{"type":41,"tag":53,"props":1539,"children":1540},{},[1541],{"type":46,"value":1542},"Use clear headers and structured formatting. Each finding should stand on its own — a reader should be able to read any single finding and understand it without reading the rest.",{"type":41,"tag":73,"props":1544,"children":1546},{"id":1545},"tips",[1547],{"type":46,"value":1548},"Tips",{"type":41,"tag":111,"props":1550,"children":1551},{},[1552,1557,1562,1567,1572,1577,1582],{"type":41,"tag":115,"props":1553,"children":1554},{},[1555],{"type":46,"value":1556},"Let the data speak. Do not force findings into a predetermined narrative.",{"type":41,"tag":115,"props":1558,"children":1559},{},[1560],{"type":46,"value":1561},"Distinguish between what users say and what they do. Behavioral data is stronger than stated preferences.",{"type":41,"tag":115,"props":1563,"children":1564},{},[1565],{"type":46,"value":1566},"Quotes are powerful evidence. Include them generously, with attribution to participant type (not name).",{"type":41,"tag":115,"props":1568,"children":1569},{},[1570],{"type":46,"value":1571},"Be explicit about confidence levels. A finding from 2 interviews is a hypothesis, not a conclusion.",{"type":41,"tag":115,"props":1573,"children":1574},{},[1575],{"type":46,"value":1576},"Contradictions in the data are interesting, not inconvenient. They often reveal distinct user segments.",{"type":41,"tag":115,"props":1578,"children":1579},{},[1580],{"type":46,"value":1581},"Recommendations should be specific enough to act on. \"Improve onboarding\" is not actionable. \"Add a progress indicator to the setup flow\" is.",{"type":41,"tag":115,"props":1583,"children":1584},{},[1585],{"type":46,"value":1586},"Resist the temptation to synthesize too many themes. 5-8 strong findings are better than 20 weak ones.",{"items":1588,"total":1703},[1589,1605,1619,1635,1653,1672,1688],{"slug":1590,"name":1590,"fn":1591,"description":1592,"org":1593,"tags":1594,"stars":23,"repoUrl":24,"updatedAt":1604},"accessibility-review","run WCAG accessibility audits","Run a WCAG 2.1 AA accessibility audit on a design or page. Trigger with \"audit accessibility\", \"check a11y\", \"is this accessible?\", or when reviewing a design for color contrast, keyboard navigation, touch target size, or screen reader behavior before handoff.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1595,1598,1601],{"name":1596,"slug":1597,"type":16},"Accessibility","accessibility",{"name":1599,"slug":1600,"type":16},"Design","design",{"name":1602,"slug":1603,"type":16},"WCAG","wcag","2026-04-06T17:58:05.682394",{"slug":1606,"name":1606,"fn":1607,"description":1608,"org":1609,"tags":1610,"stars":23,"repoUrl":24,"updatedAt":1618},"account-research","research accounts for sales intel","Research a company or person and get actionable sales intel. Works standalone with web search, supercharged when you connect enrichment tools or your CRM. Trigger with \"research [company]\", \"look up [person]\", \"intel on [prospect]\", \"who is [name] at [company]\", or \"tell me about [company]\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1611,1614,1615],{"name":1612,"slug":1613,"type":16},"CRM","crm",{"name":14,"slug":15,"type":16},{"name":1616,"slug":1617,"type":16},"Sales","sales","2026-04-06T17:56:41.410418",{"slug":1620,"name":1620,"fn":1621,"description":1622,"org":1623,"tags":1624,"stars":23,"repoUrl":24,"updatedAt":1634},"analyze","answer data questions and run analyses","Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1625,1628,1631],{"name":1626,"slug":1627,"type":16},"Analytics","analytics",{"name":1629,"slug":1630,"type":16},"Data Analysis","data-analysis",{"name":1632,"slug":1633,"type":16},"SQL","sql","2026-04-06T17:57:21.593647",{"slug":1636,"name":1636,"fn":1637,"description":1638,"org":1639,"tags":1640,"stars":23,"repoUrl":24,"updatedAt":1652},"architecture","create and evaluate architecture decision records","Create or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and consequences, reviewing a system design proposal, or designing a new component from requirements and constraints.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1641,1644,1646,1649],{"name":1642,"slug":1643,"type":16},"ADR","adr",{"name":1645,"slug":1636,"type":16},"Architecture",{"name":1647,"slug":1648,"type":16},"Documentation","documentation",{"name":1650,"slug":1651,"type":16},"Engineering","engineering","2026-04-06T17:57:49.26444",{"slug":1654,"name":1654,"fn":1655,"description":1656,"org":1657,"tags":1658,"stars":23,"repoUrl":24,"updatedAt":1671},"audit-support","support SOX 404 control testing","Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1659,1662,1665,1668],{"name":1660,"slug":1661,"type":16},"Audit","audit",{"name":1663,"slug":1664,"type":16},"Finance","finance",{"name":1666,"slug":1667,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":1669,"slug":1670,"type":16},"SOX","sox","2026-04-06T17:57:36.714815",{"slug":1673,"name":1673,"fn":1674,"description":1675,"org":1676,"tags":1677,"stars":23,"repoUrl":24,"updatedAt":1687},"brand-review","review content against brand voice","Review content against your brand voice, style guide, and messaging pillars, flagging deviations by severity with specific before\u002Fafter fixes. Use when checking a draft before it ships, when auditing copy for voice consistency and terminology, or when screening for unsubstantiated claims, missing disclaimers, and other legal flags.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1678,1681,1684],{"name":1679,"slug":1680,"type":16},"Branding","branding",{"name":1682,"slug":1683,"type":16},"Marketing","marketing",{"name":1685,"slug":1686,"type":16},"Writing","writing","2026-04-06T17:58:19.548331",{"slug":1689,"name":1689,"fn":1690,"description":1691,"org":1692,"tags":1693,"stars":23,"repoUrl":24,"updatedAt":1702},"brand-voice-enforcement","enforce brand voice in content","This skill applies brand guidelines to content creation. It should be used when the user asks to \"write an email\", \"draft a proposal\", \"create a pitch deck\", \"write a LinkedIn post\", \"draft a presentation\", \"write a Slack message\", \"draft sales content\", or any content creation request where brand voice should be applied. Also triggers on \"on-brand\", \"brand voice\", \"enforce voice\", \"apply brand guidelines\", \"brand-aligned content\", \"write in our voice\", \"use our brand tone\", \"make this sound like us\", \"rewrite this in our tone\", or \"this doesn't sound on-brand\". Not for generating guidelines from scratch (use guideline-generation) or discovering brand materials (use discover-brand).\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1694,1695,1698,1701],{"name":1679,"slug":1680,"type":16},{"name":1696,"slug":1697,"type":16},"Communications","communications",{"name":1699,"slug":1700,"type":16},"Content Creation","content-creation",{"name":1685,"slug":1686,"type":16},"2026-04-06T18:00:23.528956",200,{"items":1705,"total":1882},[1706,1725,1737,1749,1768,1779,1800,1820,1830,1845,1853,1866],{"slug":1707,"name":1707,"fn":1708,"description":1709,"org":1710,"tags":1711,"stars":1722,"repoUrl":1723,"updatedAt":1724},"algorithmic-art","create algorithmic art with p5.js","Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1712,1715,1716,1719],{"name":1713,"slug":1714,"type":16},"Creative","creative",{"name":1599,"slug":1600,"type":16},{"name":1717,"slug":1718,"type":16},"Generative Art","generative-art",{"name":1720,"slug":1721,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":1726,"name":1726,"fn":1727,"description":1728,"org":1729,"tags":1730,"stars":1722,"repoUrl":1723,"updatedAt":1736},"brand-guidelines","apply Anthropic brand colors and typography","Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1731,1732,1733],{"name":1679,"slug":1680,"type":16},{"name":1599,"slug":1600,"type":16},{"name":1734,"slug":1735,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":1738,"name":1738,"fn":1739,"description":1740,"org":1741,"tags":1742,"stars":1722,"repoUrl":1723,"updatedAt":1748},"canvas-design","create posters and visual art as PNG or PDF","Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1743,1744,1745],{"name":1713,"slug":1714,"type":16},{"name":1599,"slug":1600,"type":16},{"name":1746,"slug":1747,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":1750,"name":1750,"fn":1751,"description":1752,"org":1753,"tags":1754,"stars":1722,"repoUrl":1723,"updatedAt":1767},"claude-api","build apps with the Claude API","Reference for the Claude API \u002F Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude\u002FAnthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing\u002Fmodel choice\u002Flimits\u002Fcaching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent\u002FMCP\u002Ftool-definition\u002Fmulti-agent\u002FRAG\u002FLLM-judge\u002Fcomputer-use; generate\u002Fsummarize\u002Fextract\u002Fclassify\u002Frewrite\u002Fconverse over NL; debugging refusals\u002Fcutoffs\u002Fstreaming\u002Ftool-calls\u002Ftokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI\u002FGPT\u002FGemini\u002FLlama\u002FMistral\u002FCohere\u002FOllama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1755,1758,1759,1762,1764],{"name":1756,"slug":1757,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":1760,"slug":1761,"type":16},"Anthropic SDK","anthropic-sdk",{"name":1763,"slug":1750,"type":16},"Claude API",{"name":1765,"slug":1766,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":1769,"name":1769,"fn":1770,"description":1771,"org":1772,"tags":1773,"stars":1722,"repoUrl":1723,"updatedAt":1778},"doc-coauthoring","co-author documentation and technical specs","Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1774,1775],{"name":1647,"slug":1648,"type":16},{"name":1776,"slug":1777,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":1780,"name":1780,"fn":1781,"description":1782,"org":1783,"tags":1784,"stars":1722,"repoUrl":1723,"updatedAt":1799},"docx","create and edit Word documents","Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1785,1788,1790,1793,1796],{"name":1786,"slug":1787,"type":16},"Documents","documents",{"name":1789,"slug":1780,"type":16},"DOCX",{"name":1791,"slug":1792,"type":16},"Office","office",{"name":1794,"slug":1795,"type":16},"Templates","templates",{"name":1797,"slug":1798,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":1801,"name":1801,"fn":1802,"description":1803,"org":1804,"tags":1805,"stars":1722,"repoUrl":1723,"updatedAt":1819},"frontend-design","design production-grade frontend interfaces","Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1806,1807,1810,1813,1816],{"name":1599,"slug":1600,"type":16},{"name":1808,"slug":1809,"type":16},"Frontend","frontend",{"name":1811,"slug":1812,"type":16},"React","react",{"name":1814,"slug":1815,"type":16},"Tailwind CSS","tailwind-css",{"name":1817,"slug":1818,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":1821,"name":1821,"fn":1822,"description":1823,"org":1824,"tags":1825,"stars":1722,"repoUrl":1723,"updatedAt":1829},"internal-comms","write internal company communications","A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1826,1827,1828],{"name":1696,"slug":1697,"type":16},{"name":1794,"slug":1795,"type":16},{"name":1685,"slug":1686,"type":16},"2026-04-06T17:56:20.695522",{"slug":1831,"name":1831,"fn":1832,"description":1833,"org":1834,"tags":1835,"stars":1722,"repoUrl":1723,"updatedAt":1844},"mcp-builder","build MCP servers","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node\u002FTypeScript (MCP SDK).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1836,1837,1840,1841],{"name":1756,"slug":1757,"type":16},{"name":1838,"slug":1839,"type":16},"API Development","api-development",{"name":1765,"slug":1766,"type":16},{"name":1842,"slug":1843,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":1747,"name":1747,"fn":1846,"description":1847,"org":1848,"tags":1849,"stars":1722,"repoUrl":1723,"updatedAt":1852},"read edit and manipulate PDF files","Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text\u002Ftables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting\u002Fdecrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1850,1851],{"name":1786,"slug":1787,"type":16},{"name":1746,"slug":1747,"type":16},"2026-04-06T17:56:02.483316",{"slug":1854,"name":1854,"fn":1855,"description":1856,"org":1857,"tags":1858,"stars":1722,"repoUrl":1723,"updatedAt":1865},"pptx","create and edit PowerPoint presentations","Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1859,1862],{"name":1860,"slug":1861,"type":16},"PowerPoint","powerpoint",{"name":1863,"slug":1864,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":1867,"name":1867,"fn":1868,"description":1869,"org":1870,"tags":1871,"stars":1722,"repoUrl":1723,"updatedAt":1881},"skill-creator","create and optimize agent skills","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1872,1873,1874,1877,1880],{"name":1756,"slug":1757,"type":16},{"name":1647,"slug":1648,"type":16},{"name":1875,"slug":1876,"type":16},"Evals","evals",{"name":1878,"slug":1879,"type":16},"Performance","performance",{"name":1776,"slug":1777,"type":16},"2026-04-19T06:45:40.804",490]