[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-jetbrains-doc-coauthoring":3,"mdc--2v8466-key":33,"related-repo-jetbrains-doc-coauthoring":1517,"related-org-jetbrains-doc-coauthoring":1643},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":31,"mdContent":32},"doc-coauthoring","co-author technical documentation and proposals","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":9},"jetbrains","JetBrains","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fjetbrains.png",[12,16,19],{"name":13,"slug":14,"type":15},"Documentation","documentation","tag",{"name":17,"slug":18,"type":15},"Collaboration","collaboration",{"name":20,"slug":21,"type":15},"Technical Writing","technical-writing",252,"https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fskills","2026-07-13T06:43:00.899672",null,17,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"Curated agent skills collection verified by JetBrains","https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fskills\u002Ftree\u002FHEAD\u002Fdoc-coauthoring","---\nname: doc-coauthoring\ndescription: 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.\nmetadata:\n  short-description: \"Co-author structured documents iteratively\"\n  author: Anthropic\n  source: https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fdoc-coauthoring\n---\n\n# Doc Co-Authoring Workflow\n\nThis skill provides a structured workflow for guiding users through collaborative document creation. Act as an active guide, walking users through three stages: Context Gathering, Refinement & Structure, and Reader Testing.\n\n## When to Offer This Workflow\n\n**Trigger conditions:**\n- User mentions writing documentation: \"write a doc\", \"draft a proposal\", \"create a spec\", \"write up\"\n- User mentions specific doc types: \"PRD\", \"design doc\", \"decision doc\", \"RFC\"\n- User seems to be starting a substantial writing task\n\n**Initial offer:**\nOffer the user a structured workflow for co-authoring the document. Explain the three stages:\n\n1. **Context Gathering**: User provides all relevant context while Claude asks clarifying questions\n2. **Refinement & Structure**: Iteratively build each section through brainstorming and editing\n3. **Reader Testing**: Test the doc with a fresh Claude (no context) to catch blind spots before others read it\n\nExplain that this approach helps ensure the doc works well when others read it (including when they paste it into Claude). Ask if they want to try this workflow or prefer to work freeform.\n\nIf user declines, work freeform. If user accepts, proceed to Stage 1.\n\n## Stage 1: Context Gathering\n\n**Goal:** Close the gap between what the user knows and what Claude knows, enabling smart guidance later.\n\n### Initial Questions\n\nStart by asking the user for meta-context about the document:\n\n1. What type of document is this? (e.g., technical spec, decision doc, proposal)\n2. Who's the primary audience?\n3. What's the desired impact when someone reads this?\n4. Is there a template or specific format to follow?\n5. Any other constraints or context to know?\n\nInform them they can answer in shorthand or dump information however works best for them.\n\n**If user provides a template or mentions a doc type:**\n- Ask if they have a template document to share\n- If they provide a link to a shared document, use the appropriate integration to fetch it\n- If they provide a file, read it\n\n**If user mentions editing an existing shared document:**\n- Use the appropriate integration to read the current state\n- Check for images without alt-text\n- If images exist without alt-text, explain that when others use Claude to understand the doc, Claude won't be able to see them. Ask if they want alt-text generated. If so, request they paste each image into chat for descriptive alt-text generation.\n\n### Info Dumping\n\nOnce initial questions are answered, encourage the user to dump all the context they have. Request information such as:\n- Background on the project\u002Fproblem\n- Related team discussions or shared documents\n- Why alternative solutions aren't being used\n- Organizational context (team dynamics, past incidents, politics)\n- Timeline pressures or constraints\n- Technical architecture or dependencies\n- Stakeholder concerns\n\nAdvise them not to worry about organizing it - just get it all out. Offer multiple ways to provide context:\n- Info dump stream-of-consciousness\n- Point to team channels or threads to read\n- Link to shared documents\n\n**If integrations are available** (e.g., Slack, Teams, Google Drive, SharePoint, or other MCP servers), mention that these can be used to pull in context directly.\n\n**If no integrations are detected and in Claude.ai or Claude app:** Suggest they can enable connectors in their Claude settings to allow pulling context from messaging apps and document storage directly.\n\nInform them clarifying questions will be asked once they've done their initial dump.\n\n**During context gathering:**\n\n- If user mentions team channels or shared documents:\n  - If integrations available: Inform them the content will be read now, then use the appropriate integration\n  - If integrations not available: Explain lack of access. Suggest they enable connectors in Claude settings, or paste the relevant content directly.\n\n- If user mentions entities\u002Fprojects that are unknown:\n  - Ask if connected tools should be searched to learn more\n  - Wait for user confirmation before searching\n\n- As user provides context, track what's being learned and what's still unclear\n\n**Asking clarifying questions:**\n\nWhen user signals they've done their initial dump (or after substantial context provided), ask clarifying questions to ensure understanding:\n\nGenerate 5-10 numbered questions based on gaps in the context.\n\nInform them they can use shorthand to answer (e.g., \"1: yes, 2: see #channel, 3: no because backwards compat\"), link to more docs, point to channels to read, or just keep info-dumping. Whatever's most efficient for them.\n\n**Exit condition:**\nSufficient context has been gathered when questions show understanding - when edge cases and trade-offs can be asked about without needing basics explained.\n\n**Transition:**\nAsk if there's any more context they want to provide at this stage, or if it's time to move on to drafting the document.\n\nIf user wants to add more, let them. When ready, proceed to Stage 2.\n\n## Stage 2: Refinement & Structure\n\n**Goal:** Build the document section by section through brainstorming, curation, and iterative refinement.\n\n**Instructions to user:**\nExplain that the document will be built section by section. For each section:\n1. Clarifying questions will be asked about what to include\n2. 5-20 options will be brainstormed\n3. User will indicate what to keep\u002Fremove\u002Fcombine\n4. The section will be drafted\n5. It will be refined through surgical edits\n\nStart with whichever section has the most unknowns (usually the core decision\u002Fproposal), then work through the rest.\n\n**Section ordering:**\n\nIf the document structure is clear:\nAsk which section they'd like to start with.\n\nSuggest starting with whichever section has the most unknowns. For decision docs, that's usually the core proposal. For specs, it's typically the technical approach. Summary sections are best left for last.\n\nIf user doesn't know what sections they need:\nBased on the type of document and template, suggest 3-5 sections appropriate for the doc type.\n\nAsk if this structure works, or if they want to adjust it.\n\n**Once structure is agreed:**\n\nCreate the initial document structure with placeholder text for all sections.\n\n**If access to artifacts is available:**\nUse `create_file` to create an artifact. This gives both Claude and the user a scaffold to work from.\n\nInform them that the initial structure with placeholders for all sections will be created.\n\nCreate artifact with all section headers and brief placeholder text like \"[To be written]\" or \"[Content here]\".\n\nProvide the scaffold link and indicate it's time to fill in each section.\n\n**If no access to artifacts:**\nCreate a markdown file in the working directory. Name it appropriately (e.g., `decision-doc.md`, `technical-spec.md`).\n\nInform them that the initial structure with placeholders for all sections will be created.\n\nCreate file with all section headers and placeholder text.\n\nConfirm the filename has been created and indicate it's time to fill in each section.\n\n**For each section:**\n\n### Step 1: Clarifying Questions\n\nAnnounce work will begin on the [SECTION NAME] section. Ask 5-10 clarifying questions about what should be included:\n\nGenerate 5-10 specific questions based on context and section purpose.\n\nInform them they can answer in shorthand or just indicate what's important to cover.\n\n### Step 2: Brainstorming\n\nFor the [SECTION NAME] section, brainstorm [5-20] things that might be included, depending on the section's complexity. Look for:\n- Context shared that might have been forgotten\n- Angles or considerations not yet mentioned\n\nGenerate 5-20 numbered options based on section complexity. At the end, offer to brainstorm more if they want additional options.\n\n### Step 3: Curation\n\nAsk which points should be kept, removed, or combined. Request brief justifications to help learn priorities for the next sections.\n\nProvide examples:\n- \"Keep 1,4,7,9\"\n- \"Remove 3 (duplicates 1)\"\n- \"Remove 6 (audience already knows this)\"\n- \"Combine 11 and 12\"\n\n**If user gives freeform feedback** (e.g., \"looks good\" or \"I like most of it but...\") instead of numbered selections, extract their preferences and proceed. Parse what they want kept\u002Fremoved\u002Fchanged and apply it.\n\n### Step 4: Gap Check\n\nBased on what they've selected, ask if there's anything important missing for the [SECTION NAME] section.\n\n### Step 5: Drafting\n\nUse `str_replace` to replace the placeholder text for this section with the actual drafted content.\n\nAnnounce the [SECTION NAME] section will be drafted now based on what they've selected.\n\n**If using artifacts:**\nAfter drafting, provide a link to the artifact.\n\nAsk them to read through it and indicate what to change. Note that being specific helps learning for the next sections.\n\n**If using a file (no artifacts):**\nAfter drafting, confirm completion.\n\nInform them the [SECTION NAME] section has been drafted in [filename]. Ask them to read through it and indicate what to change. Note that being specific helps learning for the next sections.\n\n**Key instruction for user (include when drafting the first section):**\nProvide a note: Instead of editing the doc directly, ask them to indicate what to change. This helps learning of their style for future sections. For example: \"Remove the X bullet - already covered by Y\" or \"Make the third paragraph more concise\".\n\n### Step 6: Iterative Refinement\n\nAs user provides feedback:\n- Use `str_replace` to make edits (never reprint the whole doc)\n- **If using artifacts:** Provide link to artifact after each edit\n- **If using files:** Just confirm edits are complete\n- If user edits doc directly and asks to read it: mentally note the changes they made and keep them in mind for future sections (this shows their preferences)\n\n**Continue iterating** until user is satisfied with the section.\n\n### Quality Checking\n\nAfter 3 consecutive iterations with no substantial changes, ask if anything can be removed without losing important information.\n\nWhen section is done, confirm [SECTION NAME] is complete. Ask if ready to move to the next section.\n\n**Repeat for all sections.**\n\n### Near Completion\n\nAs approaching completion (80%+ of sections done), announce intention to re-read the entire document and check for:\n- Flow and consistency across sections\n- Redundancy or contradictions\n- Anything that feels like \"slop\" or generic filler\n- Whether every sentence carries weight\n\nRead entire document and provide feedback.\n\n**When all sections are drafted and refined:**\nAnnounce all sections are drafted. Indicate intention to review the complete document one more time.\n\nReview for overall coherence, flow, completeness.\n\nProvide any final suggestions.\n\nAsk if ready to move to Reader Testing, or if they want to refine anything else.\n\n## Stage 3: Reader Testing\n\n**Goal:** Test the document with a fresh Claude (no context bleed) to verify it works for readers.\n\n**Instructions to user:**\nExplain that testing will now occur to see if the document actually works for readers. This catches blind spots - things that make sense to the authors but might confuse others.\n\n### Testing Approach\n\n**If access to sub-agents is available (e.g., in Claude Code):**\n\nPerform the testing directly without user involvement.\n\n### Step 1: Predict Reader Questions\n\nAnnounce intention to predict what questions readers might ask when trying to discover this document.\n\nGenerate 5-10 questions that readers would realistically ask.\n\n### Step 2: Test with Sub-Agent\n\nAnnounce that these questions will be tested with a fresh Claude instance (no context from this conversation).\n\nFor each question, invoke a sub-agent with just the document content and the question.\n\nSummarize what Reader Claude got right\u002Fwrong for each question.\n\n### Step 3: Run Additional Checks\n\nAnnounce additional checks will be performed.\n\nInvoke sub-agent to check for ambiguity, false assumptions, contradictions.\n\nSummarize any issues found.\n\n### Step 4: Report and Fix\n\nIf issues found:\nReport that Reader Claude struggled with specific issues.\n\nList the specific issues.\n\nIndicate intention to fix these gaps.\n\nLoop back to refinement for problematic sections.\n\n---\n\n**If no access to sub-agents (e.g., claude.ai web interface):**\n\nThe user will need to do the testing manually.\n\n### Step 1: Predict Reader Questions\n\nAsk what questions people might ask when trying to discover this document. What would they type into Claude.ai?\n\nGenerate 5-10 questions that readers would realistically ask.\n\n### Step 2: Setup Testing\n\nProvide testing instructions:\n1. Open a fresh Claude conversation: https:\u002F\u002Fclaude.ai\n2. Paste or share the document content (if using a shared doc platform with connectors enabled, provide the link)\n3. Ask Reader Claude the generated questions\n\nFor each question, instruct Reader Claude to provide:\n- The answer\n- Whether anything was ambiguous or unclear\n- What knowledge\u002Fcontext the doc assumes is already known\n\nCheck if Reader Claude gives correct answers or misinterprets anything.\n\n### Step 3: Additional Checks\n\nAlso ask Reader Claude:\n- \"What in this doc might be ambiguous or unclear to readers?\"\n- \"What knowledge or context does this doc assume readers already have?\"\n- \"Are there any internal contradictions or inconsistencies?\"\n\n### Step 4: Iterate Based on Results\n\nAsk what Reader Claude got wrong or struggled with. Indicate intention to fix those gaps.\n\nLoop back to refinement for any problematic sections.\n\n---\n\n### Exit Condition (Both Approaches)\n\nWhen Reader Claude consistently answers questions correctly and doesn't surface new gaps or ambiguities, the doc is ready.\n\n## Final Review\n\nWhen Reader Testing passes:\nAnnounce the doc has passed Reader Claude testing. Before completion:\n\n1. Recommend they do a final read-through themselves - they own this document and are responsible for its quality\n2. Suggest double-checking any facts, links, or technical details\n3. Ask them to verify it achieves the impact they wanted\n\nAsk if they want one more review, or if the work is done.\n\n**If user wants final review, provide it. Otherwise:**\nAnnounce document completion. Provide a few final tips:\n- Consider linking this conversation in an appendix so readers can see how the doc was developed\n- Use appendices to provide depth without bloating the main doc\n- Update the doc as feedback is received from real readers\n\n## Tips for Effective Guidance\n\n**Tone:**\n- Be direct and procedural\n- Explain rationale briefly when it affects user behavior\n- Don't try to \"sell\" the approach - just execute it\n\n**Handling Deviations:**\n- If user wants to skip a stage: Ask if they want to skip this and write freeform\n- If user seems frustrated: Acknowledge this is taking longer than expected. Suggest ways to move faster\n- Always give user agency to adjust the process\n\n**Context Management:**\n- Throughout, if context is missing on something mentioned, proactively ask\n- Don't let gaps accumulate - address them as they come up\n\n**Artifact Management:**\n- Use `create_file` for drafting full sections\n- Use `str_replace` for all edits\n- Provide artifact link after every change\n- Never use artifacts for brainstorming lists - that's just conversation\n\n**Quality over Speed:**\n- Don't rush through stages\n- Each iteration should make meaningful improvements\n- The goal is a document that actually works for readers\n",{"data":34,"body":39},{"name":4,"description":6,"metadata":35},{"short-description":36,"author":37,"source":38},"Co-author structured documents iteratively","Anthropic","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fdoc-coauthoring",{"type":40,"children":41},"root",[42,51,57,64,73,93,103,137,142,147,153,163,170,175,203,208,216,234,242,260,266,271,309,314,332,342,352,357,365,409,417,422,427,432,442,452,457,463,472,482,510,515,523,528,533,538,543,551,556,575,580,600,605,631,635,640,645,653,659,671,676,681,687,705,718,723,729,734,739,762,772,778,789,795,808,819,829,834,844,862,872,878,883,921,931,937,942,953,961,967,972,995,1000,1010,1015,1020,1025,1031,1040,1049,1055,1063,1068,1074,1079,1084,1090,1095,1100,1105,1111,1116,1121,1126,1132,1137,1142,1147,1152,1156,1164,1169,1174,1179,1183,1189,1194,1220,1225,1243,1248,1254,1259,1277,1283,1288,1293,1296,1302,1307,1313,1318,1336,1341,1351,1369,1375,1383,1401,1409,1427,1435,1448,1456,1491,1499],{"type":43,"tag":44,"props":45,"children":47},"element","h1",{"id":46},"doc-co-authoring-workflow",[48],{"type":49,"value":50},"text","Doc Co-Authoring Workflow",{"type":43,"tag":52,"props":53,"children":54},"p",{},[55],{"type":49,"value":56},"This skill provides a structured workflow for guiding users through collaborative document creation. Act as an active guide, walking users through three stages: Context Gathering, Refinement & Structure, and Reader Testing.",{"type":43,"tag":58,"props":59,"children":61},"h2",{"id":60},"when-to-offer-this-workflow",[62],{"type":49,"value":63},"When to Offer This Workflow",{"type":43,"tag":52,"props":65,"children":66},{},[67],{"type":43,"tag":68,"props":69,"children":70},"strong",{},[71],{"type":49,"value":72},"Trigger conditions:",{"type":43,"tag":74,"props":75,"children":76},"ul",{},[77,83,88],{"type":43,"tag":78,"props":79,"children":80},"li",{},[81],{"type":49,"value":82},"User mentions writing documentation: \"write a doc\", \"draft a proposal\", \"create a spec\", \"write up\"",{"type":43,"tag":78,"props":84,"children":85},{},[86],{"type":49,"value":87},"User mentions specific doc types: \"PRD\", \"design doc\", \"decision doc\", \"RFC\"",{"type":43,"tag":78,"props":89,"children":90},{},[91],{"type":49,"value":92},"User seems to be starting a substantial writing task",{"type":43,"tag":52,"props":94,"children":95},{},[96,101],{"type":43,"tag":68,"props":97,"children":98},{},[99],{"type":49,"value":100},"Initial offer:",{"type":49,"value":102},"\nOffer the user a structured workflow for co-authoring the document. Explain the three stages:",{"type":43,"tag":104,"props":105,"children":106},"ol",{},[107,117,127],{"type":43,"tag":78,"props":108,"children":109},{},[110,115],{"type":43,"tag":68,"props":111,"children":112},{},[113],{"type":49,"value":114},"Context Gathering",{"type":49,"value":116},": User provides all relevant context while Claude asks clarifying questions",{"type":43,"tag":78,"props":118,"children":119},{},[120,125],{"type":43,"tag":68,"props":121,"children":122},{},[123],{"type":49,"value":124},"Refinement & Structure",{"type":49,"value":126},": Iteratively build each section through brainstorming and editing",{"type":43,"tag":78,"props":128,"children":129},{},[130,135],{"type":43,"tag":68,"props":131,"children":132},{},[133],{"type":49,"value":134},"Reader Testing",{"type":49,"value":136},": Test the doc with a fresh Claude (no context) to catch blind spots before others read it",{"type":43,"tag":52,"props":138,"children":139},{},[140],{"type":49,"value":141},"Explain that this approach helps ensure the doc works well when others read it (including when they paste it into Claude). Ask if they want to try this workflow or prefer to work freeform.",{"type":43,"tag":52,"props":143,"children":144},{},[145],{"type":49,"value":146},"If user declines, work freeform. If user accepts, proceed to Stage 1.",{"type":43,"tag":58,"props":148,"children":150},{"id":149},"stage-1-context-gathering",[151],{"type":49,"value":152},"Stage 1: Context Gathering",{"type":43,"tag":52,"props":154,"children":155},{},[156,161],{"type":43,"tag":68,"props":157,"children":158},{},[159],{"type":49,"value":160},"Goal:",{"type":49,"value":162}," Close the gap between what the user knows and what Claude knows, enabling smart guidance later.",{"type":43,"tag":164,"props":165,"children":167},"h3",{"id":166},"initial-questions",[168],{"type":49,"value":169},"Initial Questions",{"type":43,"tag":52,"props":171,"children":172},{},[173],{"type":49,"value":174},"Start by asking the user for meta-context about the document:",{"type":43,"tag":104,"props":176,"children":177},{},[178,183,188,193,198],{"type":43,"tag":78,"props":179,"children":180},{},[181],{"type":49,"value":182},"What type of document is this? (e.g., technical spec, decision doc, proposal)",{"type":43,"tag":78,"props":184,"children":185},{},[186],{"type":49,"value":187},"Who's the primary audience?",{"type":43,"tag":78,"props":189,"children":190},{},[191],{"type":49,"value":192},"What's the desired impact when someone reads this?",{"type":43,"tag":78,"props":194,"children":195},{},[196],{"type":49,"value":197},"Is there a template or specific format to follow?",{"type":43,"tag":78,"props":199,"children":200},{},[201],{"type":49,"value":202},"Any other constraints or context to know?",{"type":43,"tag":52,"props":204,"children":205},{},[206],{"type":49,"value":207},"Inform them they can answer in shorthand or dump information however works best for them.",{"type":43,"tag":52,"props":209,"children":210},{},[211],{"type":43,"tag":68,"props":212,"children":213},{},[214],{"type":49,"value":215},"If user provides a template or mentions a doc type:",{"type":43,"tag":74,"props":217,"children":218},{},[219,224,229],{"type":43,"tag":78,"props":220,"children":221},{},[222],{"type":49,"value":223},"Ask if they have a template document to share",{"type":43,"tag":78,"props":225,"children":226},{},[227],{"type":49,"value":228},"If they provide a link to a shared document, use the appropriate integration to fetch it",{"type":43,"tag":78,"props":230,"children":231},{},[232],{"type":49,"value":233},"If they provide a file, read it",{"type":43,"tag":52,"props":235,"children":236},{},[237],{"type":43,"tag":68,"props":238,"children":239},{},[240],{"type":49,"value":241},"If user mentions editing an existing shared document:",{"type":43,"tag":74,"props":243,"children":244},{},[245,250,255],{"type":43,"tag":78,"props":246,"children":247},{},[248],{"type":49,"value":249},"Use the appropriate integration to read the current state",{"type":43,"tag":78,"props":251,"children":252},{},[253],{"type":49,"value":254},"Check for images without alt-text",{"type":43,"tag":78,"props":256,"children":257},{},[258],{"type":49,"value":259},"If images exist without alt-text, explain that when others use Claude to understand the doc, Claude won't be able to see them. Ask if they want alt-text generated. If so, request they paste each image into chat for descriptive alt-text generation.",{"type":43,"tag":164,"props":261,"children":263},{"id":262},"info-dumping",[264],{"type":49,"value":265},"Info Dumping",{"type":43,"tag":52,"props":267,"children":268},{},[269],{"type":49,"value":270},"Once initial questions are answered, encourage the user to dump all the context they have. Request information such as:",{"type":43,"tag":74,"props":272,"children":273},{},[274,279,284,289,294,299,304],{"type":43,"tag":78,"props":275,"children":276},{},[277],{"type":49,"value":278},"Background on the project\u002Fproblem",{"type":43,"tag":78,"props":280,"children":281},{},[282],{"type":49,"value":283},"Related team discussions or shared documents",{"type":43,"tag":78,"props":285,"children":286},{},[287],{"type":49,"value":288},"Why alternative solutions aren't being used",{"type":43,"tag":78,"props":290,"children":291},{},[292],{"type":49,"value":293},"Organizational context (team dynamics, past incidents, politics)",{"type":43,"tag":78,"props":295,"children":296},{},[297],{"type":49,"value":298},"Timeline pressures or constraints",{"type":43,"tag":78,"props":300,"children":301},{},[302],{"type":49,"value":303},"Technical architecture or dependencies",{"type":43,"tag":78,"props":305,"children":306},{},[307],{"type":49,"value":308},"Stakeholder concerns",{"type":43,"tag":52,"props":310,"children":311},{},[312],{"type":49,"value":313},"Advise them not to worry about organizing it - just get it all out. Offer multiple ways to provide context:",{"type":43,"tag":74,"props":315,"children":316},{},[317,322,327],{"type":43,"tag":78,"props":318,"children":319},{},[320],{"type":49,"value":321},"Info dump stream-of-consciousness",{"type":43,"tag":78,"props":323,"children":324},{},[325],{"type":49,"value":326},"Point to team channels or threads to read",{"type":43,"tag":78,"props":328,"children":329},{},[330],{"type":49,"value":331},"Link to shared documents",{"type":43,"tag":52,"props":333,"children":334},{},[335,340],{"type":43,"tag":68,"props":336,"children":337},{},[338],{"type":49,"value":339},"If integrations are available",{"type":49,"value":341}," (e.g., Slack, Teams, Google Drive, SharePoint, or other MCP servers), mention that these can be used to pull in context directly.",{"type":43,"tag":52,"props":343,"children":344},{},[345,350],{"type":43,"tag":68,"props":346,"children":347},{},[348],{"type":49,"value":349},"If no integrations are detected and in Claude.ai or Claude app:",{"type":49,"value":351}," Suggest they can enable connectors in their Claude settings to allow pulling context from messaging apps and document storage directly.",{"type":43,"tag":52,"props":353,"children":354},{},[355],{"type":49,"value":356},"Inform them clarifying questions will be asked once they've done their initial dump.",{"type":43,"tag":52,"props":358,"children":359},{},[360],{"type":43,"tag":68,"props":361,"children":362},{},[363],{"type":49,"value":364},"During context gathering:",{"type":43,"tag":74,"props":366,"children":367},{},[368,386,404],{"type":43,"tag":78,"props":369,"children":370},{},[371,373],{"type":49,"value":372},"If user mentions team channels or shared documents:",{"type":43,"tag":74,"props":374,"children":375},{},[376,381],{"type":43,"tag":78,"props":377,"children":378},{},[379],{"type":49,"value":380},"If integrations available: Inform them the content will be read now, then use the appropriate integration",{"type":43,"tag":78,"props":382,"children":383},{},[384],{"type":49,"value":385},"If integrations not available: Explain lack of access. Suggest they enable connectors in Claude settings, or paste the relevant content directly.",{"type":43,"tag":78,"props":387,"children":388},{},[389,391],{"type":49,"value":390},"If user mentions entities\u002Fprojects that are unknown:",{"type":43,"tag":74,"props":392,"children":393},{},[394,399],{"type":43,"tag":78,"props":395,"children":396},{},[397],{"type":49,"value":398},"Ask if connected tools should be searched to learn more",{"type":43,"tag":78,"props":400,"children":401},{},[402],{"type":49,"value":403},"Wait for user confirmation before searching",{"type":43,"tag":78,"props":405,"children":406},{},[407],{"type":49,"value":408},"As user provides context, track what's being learned and what's still unclear",{"type":43,"tag":52,"props":410,"children":411},{},[412],{"type":43,"tag":68,"props":413,"children":414},{},[415],{"type":49,"value":416},"Asking clarifying questions:",{"type":43,"tag":52,"props":418,"children":419},{},[420],{"type":49,"value":421},"When user signals they've done their initial dump (or after substantial context provided), ask clarifying questions to ensure understanding:",{"type":43,"tag":52,"props":423,"children":424},{},[425],{"type":49,"value":426},"Generate 5-10 numbered questions based on gaps in the context.",{"type":43,"tag":52,"props":428,"children":429},{},[430],{"type":49,"value":431},"Inform them they can use shorthand to answer (e.g., \"1: yes, 2: see #channel, 3: no because backwards compat\"), link to more docs, point to channels to read, or just keep info-dumping. Whatever's most efficient for them.",{"type":43,"tag":52,"props":433,"children":434},{},[435,440],{"type":43,"tag":68,"props":436,"children":437},{},[438],{"type":49,"value":439},"Exit condition:",{"type":49,"value":441},"\nSufficient context has been gathered when questions show understanding - when edge cases and trade-offs can be asked about without needing basics explained.",{"type":43,"tag":52,"props":443,"children":444},{},[445,450],{"type":43,"tag":68,"props":446,"children":447},{},[448],{"type":49,"value":449},"Transition:",{"type":49,"value":451},"\nAsk if there's any more context they want to provide at this stage, or if it's time to move on to drafting the document.",{"type":43,"tag":52,"props":453,"children":454},{},[455],{"type":49,"value":456},"If user wants to add more, let them. When ready, proceed to Stage 2.",{"type":43,"tag":58,"props":458,"children":460},{"id":459},"stage-2-refinement-structure",[461],{"type":49,"value":462},"Stage 2: Refinement & Structure",{"type":43,"tag":52,"props":464,"children":465},{},[466,470],{"type":43,"tag":68,"props":467,"children":468},{},[469],{"type":49,"value":160},{"type":49,"value":471}," Build the document section by section through brainstorming, curation, and iterative refinement.",{"type":43,"tag":52,"props":473,"children":474},{},[475,480],{"type":43,"tag":68,"props":476,"children":477},{},[478],{"type":49,"value":479},"Instructions to user:",{"type":49,"value":481},"\nExplain that the document will be built section by section. For each section:",{"type":43,"tag":104,"props":483,"children":484},{},[485,490,495,500,505],{"type":43,"tag":78,"props":486,"children":487},{},[488],{"type":49,"value":489},"Clarifying questions will be asked about what to include",{"type":43,"tag":78,"props":491,"children":492},{},[493],{"type":49,"value":494},"5-20 options will be brainstormed",{"type":43,"tag":78,"props":496,"children":497},{},[498],{"type":49,"value":499},"User will indicate what to keep\u002Fremove\u002Fcombine",{"type":43,"tag":78,"props":501,"children":502},{},[503],{"type":49,"value":504},"The section will be drafted",{"type":43,"tag":78,"props":506,"children":507},{},[508],{"type":49,"value":509},"It will be refined through surgical edits",{"type":43,"tag":52,"props":511,"children":512},{},[513],{"type":49,"value":514},"Start with whichever section has the most unknowns (usually the core decision\u002Fproposal), then work through the rest.",{"type":43,"tag":52,"props":516,"children":517},{},[518],{"type":43,"tag":68,"props":519,"children":520},{},[521],{"type":49,"value":522},"Section ordering:",{"type":43,"tag":52,"props":524,"children":525},{},[526],{"type":49,"value":527},"If the document structure is clear:\nAsk which section they'd like to start with.",{"type":43,"tag":52,"props":529,"children":530},{},[531],{"type":49,"value":532},"Suggest starting with whichever section has the most unknowns. For decision docs, that's usually the core proposal. For specs, it's typically the technical approach. Summary sections are best left for last.",{"type":43,"tag":52,"props":534,"children":535},{},[536],{"type":49,"value":537},"If user doesn't know what sections they need:\nBased on the type of document and template, suggest 3-5 sections appropriate for the doc type.",{"type":43,"tag":52,"props":539,"children":540},{},[541],{"type":49,"value":542},"Ask if this structure works, or if they want to adjust it.",{"type":43,"tag":52,"props":544,"children":545},{},[546],{"type":43,"tag":68,"props":547,"children":548},{},[549],{"type":49,"value":550},"Once structure is agreed:",{"type":43,"tag":52,"props":552,"children":553},{},[554],{"type":49,"value":555},"Create the initial document structure with placeholder text for all sections.",{"type":43,"tag":52,"props":557,"children":558},{},[559,564,566,573],{"type":43,"tag":68,"props":560,"children":561},{},[562],{"type":49,"value":563},"If access to artifacts is available:",{"type":49,"value":565},"\nUse ",{"type":43,"tag":567,"props":568,"children":570},"code",{"className":569},[],[571],{"type":49,"value":572},"create_file",{"type":49,"value":574}," to create an artifact. This gives both Claude and the user a scaffold to work from.",{"type":43,"tag":52,"props":576,"children":577},{},[578],{"type":49,"value":579},"Inform them that the initial structure with placeholders for all sections will be created.",{"type":43,"tag":52,"props":581,"children":582},{},[583,585,591,593,598],{"type":49,"value":584},"Create artifact with all section headers and brief placeholder text like \"",{"type":43,"tag":586,"props":587,"children":588},"span",{},[589],{"type":49,"value":590},"To be written",{"type":49,"value":592},"\" or \"",{"type":43,"tag":586,"props":594,"children":595},{},[596],{"type":49,"value":597},"Content here",{"type":49,"value":599},"\".",{"type":43,"tag":52,"props":601,"children":602},{},[603],{"type":49,"value":604},"Provide the scaffold link and indicate it's time to fill in each section.",{"type":43,"tag":52,"props":606,"children":607},{},[608,613,615,621,623,629],{"type":43,"tag":68,"props":609,"children":610},{},[611],{"type":49,"value":612},"If no access to artifacts:",{"type":49,"value":614},"\nCreate a markdown file in the working directory. Name it appropriately (e.g., ",{"type":43,"tag":567,"props":616,"children":618},{"className":617},[],[619],{"type":49,"value":620},"decision-doc.md",{"type":49,"value":622},", ",{"type":43,"tag":567,"props":624,"children":626},{"className":625},[],[627],{"type":49,"value":628},"technical-spec.md",{"type":49,"value":630},").",{"type":43,"tag":52,"props":632,"children":633},{},[634],{"type":49,"value":579},{"type":43,"tag":52,"props":636,"children":637},{},[638],{"type":49,"value":639},"Create file with all section headers and placeholder text.",{"type":43,"tag":52,"props":641,"children":642},{},[643],{"type":49,"value":644},"Confirm the filename has been created and indicate it's time to fill in each section.",{"type":43,"tag":52,"props":646,"children":647},{},[648],{"type":43,"tag":68,"props":649,"children":650},{},[651],{"type":49,"value":652},"For each section:",{"type":43,"tag":164,"props":654,"children":656},{"id":655},"step-1-clarifying-questions",[657],{"type":49,"value":658},"Step 1: Clarifying Questions",{"type":43,"tag":52,"props":660,"children":661},{},[662,664,669],{"type":49,"value":663},"Announce work will begin on the ",{"type":43,"tag":586,"props":665,"children":666},{},[667],{"type":49,"value":668},"SECTION NAME",{"type":49,"value":670}," section. Ask 5-10 clarifying questions about what should be included:",{"type":43,"tag":52,"props":672,"children":673},{},[674],{"type":49,"value":675},"Generate 5-10 specific questions based on context and section purpose.",{"type":43,"tag":52,"props":677,"children":678},{},[679],{"type":49,"value":680},"Inform them they can answer in shorthand or just indicate what's important to cover.",{"type":43,"tag":164,"props":682,"children":684},{"id":683},"step-2-brainstorming",[685],{"type":49,"value":686},"Step 2: Brainstorming",{"type":43,"tag":52,"props":688,"children":689},{},[690,692,696,698,703],{"type":49,"value":691},"For the ",{"type":43,"tag":586,"props":693,"children":694},{},[695],{"type":49,"value":668},{"type":49,"value":697}," section, brainstorm ",{"type":43,"tag":586,"props":699,"children":700},{},[701],{"type":49,"value":702},"5-20",{"type":49,"value":704}," things that might be included, depending on the section's complexity. Look for:",{"type":43,"tag":74,"props":706,"children":707},{},[708,713],{"type":43,"tag":78,"props":709,"children":710},{},[711],{"type":49,"value":712},"Context shared that might have been forgotten",{"type":43,"tag":78,"props":714,"children":715},{},[716],{"type":49,"value":717},"Angles or considerations not yet mentioned",{"type":43,"tag":52,"props":719,"children":720},{},[721],{"type":49,"value":722},"Generate 5-20 numbered options based on section complexity. At the end, offer to brainstorm more if they want additional options.",{"type":43,"tag":164,"props":724,"children":726},{"id":725},"step-3-curation",[727],{"type":49,"value":728},"Step 3: Curation",{"type":43,"tag":52,"props":730,"children":731},{},[732],{"type":49,"value":733},"Ask which points should be kept, removed, or combined. Request brief justifications to help learn priorities for the next sections.",{"type":43,"tag":52,"props":735,"children":736},{},[737],{"type":49,"value":738},"Provide examples:",{"type":43,"tag":74,"props":740,"children":741},{},[742,747,752,757],{"type":43,"tag":78,"props":743,"children":744},{},[745],{"type":49,"value":746},"\"Keep 1,4,7,9\"",{"type":43,"tag":78,"props":748,"children":749},{},[750],{"type":49,"value":751},"\"Remove 3 (duplicates 1)\"",{"type":43,"tag":78,"props":753,"children":754},{},[755],{"type":49,"value":756},"\"Remove 6 (audience already knows this)\"",{"type":43,"tag":78,"props":758,"children":759},{},[760],{"type":49,"value":761},"\"Combine 11 and 12\"",{"type":43,"tag":52,"props":763,"children":764},{},[765,770],{"type":43,"tag":68,"props":766,"children":767},{},[768],{"type":49,"value":769},"If user gives freeform feedback",{"type":49,"value":771}," (e.g., \"looks good\" or \"I like most of it but...\") instead of numbered selections, extract their preferences and proceed. Parse what they want kept\u002Fremoved\u002Fchanged and apply it.",{"type":43,"tag":164,"props":773,"children":775},{"id":774},"step-4-gap-check",[776],{"type":49,"value":777},"Step 4: Gap Check",{"type":43,"tag":52,"props":779,"children":780},{},[781,783,787],{"type":49,"value":782},"Based on what they've selected, ask if there's anything important missing for the ",{"type":43,"tag":586,"props":784,"children":785},{},[786],{"type":49,"value":668},{"type":49,"value":788}," section.",{"type":43,"tag":164,"props":790,"children":792},{"id":791},"step-5-drafting",[793],{"type":49,"value":794},"Step 5: Drafting",{"type":43,"tag":52,"props":796,"children":797},{},[798,800,806],{"type":49,"value":799},"Use ",{"type":43,"tag":567,"props":801,"children":803},{"className":802},[],[804],{"type":49,"value":805},"str_replace",{"type":49,"value":807}," to replace the placeholder text for this section with the actual drafted content.",{"type":43,"tag":52,"props":809,"children":810},{},[811,813,817],{"type":49,"value":812},"Announce the ",{"type":43,"tag":586,"props":814,"children":815},{},[816],{"type":49,"value":668},{"type":49,"value":818}," section will be drafted now based on what they've selected.",{"type":43,"tag":52,"props":820,"children":821},{},[822,827],{"type":43,"tag":68,"props":823,"children":824},{},[825],{"type":49,"value":826},"If using artifacts:",{"type":49,"value":828},"\nAfter drafting, provide a link to the artifact.",{"type":43,"tag":52,"props":830,"children":831},{},[832],{"type":49,"value":833},"Ask them to read through it and indicate what to change. Note that being specific helps learning for the next sections.",{"type":43,"tag":52,"props":835,"children":836},{},[837,842],{"type":43,"tag":68,"props":838,"children":839},{},[840],{"type":49,"value":841},"If using a file (no artifacts):",{"type":49,"value":843},"\nAfter drafting, confirm completion.",{"type":43,"tag":52,"props":845,"children":846},{},[847,849,853,855,860],{"type":49,"value":848},"Inform them the ",{"type":43,"tag":586,"props":850,"children":851},{},[852],{"type":49,"value":668},{"type":49,"value":854}," section has been drafted in ",{"type":43,"tag":586,"props":856,"children":857},{},[858],{"type":49,"value":859},"filename",{"type":49,"value":861},". Ask them to read through it and indicate what to change. Note that being specific helps learning for the next sections.",{"type":43,"tag":52,"props":863,"children":864},{},[865,870],{"type":43,"tag":68,"props":866,"children":867},{},[868],{"type":49,"value":869},"Key instruction for user (include when drafting the first section):",{"type":49,"value":871},"\nProvide a note: Instead of editing the doc directly, ask them to indicate what to change. This helps learning of their style for future sections. For example: \"Remove the X bullet - already covered by Y\" or \"Make the third paragraph more concise\".",{"type":43,"tag":164,"props":873,"children":875},{"id":874},"step-6-iterative-refinement",[876],{"type":49,"value":877},"Step 6: Iterative Refinement",{"type":43,"tag":52,"props":879,"children":880},{},[881],{"type":49,"value":882},"As user provides feedback:",{"type":43,"tag":74,"props":884,"children":885},{},[886,897,906,916],{"type":43,"tag":78,"props":887,"children":888},{},[889,890,895],{"type":49,"value":799},{"type":43,"tag":567,"props":891,"children":893},{"className":892},[],[894],{"type":49,"value":805},{"type":49,"value":896}," to make edits (never reprint the whole doc)",{"type":43,"tag":78,"props":898,"children":899},{},[900,904],{"type":43,"tag":68,"props":901,"children":902},{},[903],{"type":49,"value":826},{"type":49,"value":905}," Provide link to artifact after each edit",{"type":43,"tag":78,"props":907,"children":908},{},[909,914],{"type":43,"tag":68,"props":910,"children":911},{},[912],{"type":49,"value":913},"If using files:",{"type":49,"value":915}," Just confirm edits are complete",{"type":43,"tag":78,"props":917,"children":918},{},[919],{"type":49,"value":920},"If user edits doc directly and asks to read it: mentally note the changes they made and keep them in mind for future sections (this shows their preferences)",{"type":43,"tag":52,"props":922,"children":923},{},[924,929],{"type":43,"tag":68,"props":925,"children":926},{},[927],{"type":49,"value":928},"Continue iterating",{"type":49,"value":930}," until user is satisfied with the section.",{"type":43,"tag":164,"props":932,"children":934},{"id":933},"quality-checking",[935],{"type":49,"value":936},"Quality Checking",{"type":43,"tag":52,"props":938,"children":939},{},[940],{"type":49,"value":941},"After 3 consecutive iterations with no substantial changes, ask if anything can be removed without losing important information.",{"type":43,"tag":52,"props":943,"children":944},{},[945,947,951],{"type":49,"value":946},"When section is done, confirm ",{"type":43,"tag":586,"props":948,"children":949},{},[950],{"type":49,"value":668},{"type":49,"value":952}," is complete. Ask if ready to move to the next section.",{"type":43,"tag":52,"props":954,"children":955},{},[956],{"type":43,"tag":68,"props":957,"children":958},{},[959],{"type":49,"value":960},"Repeat for all sections.",{"type":43,"tag":164,"props":962,"children":964},{"id":963},"near-completion",[965],{"type":49,"value":966},"Near Completion",{"type":43,"tag":52,"props":968,"children":969},{},[970],{"type":49,"value":971},"As approaching completion (80%+ of sections done), announce intention to re-read the entire document and check for:",{"type":43,"tag":74,"props":973,"children":974},{},[975,980,985,990],{"type":43,"tag":78,"props":976,"children":977},{},[978],{"type":49,"value":979},"Flow and consistency across sections",{"type":43,"tag":78,"props":981,"children":982},{},[983],{"type":49,"value":984},"Redundancy or contradictions",{"type":43,"tag":78,"props":986,"children":987},{},[988],{"type":49,"value":989},"Anything that feels like \"slop\" or generic filler",{"type":43,"tag":78,"props":991,"children":992},{},[993],{"type":49,"value":994},"Whether every sentence carries weight",{"type":43,"tag":52,"props":996,"children":997},{},[998],{"type":49,"value":999},"Read entire document and provide feedback.",{"type":43,"tag":52,"props":1001,"children":1002},{},[1003,1008],{"type":43,"tag":68,"props":1004,"children":1005},{},[1006],{"type":49,"value":1007},"When all sections are drafted and refined:",{"type":49,"value":1009},"\nAnnounce all sections are drafted. Indicate intention to review the complete document one more time.",{"type":43,"tag":52,"props":1011,"children":1012},{},[1013],{"type":49,"value":1014},"Review for overall coherence, flow, completeness.",{"type":43,"tag":52,"props":1016,"children":1017},{},[1018],{"type":49,"value":1019},"Provide any final suggestions.",{"type":43,"tag":52,"props":1021,"children":1022},{},[1023],{"type":49,"value":1024},"Ask if ready to move to Reader Testing, or if they want to refine anything else.",{"type":43,"tag":58,"props":1026,"children":1028},{"id":1027},"stage-3-reader-testing",[1029],{"type":49,"value":1030},"Stage 3: Reader Testing",{"type":43,"tag":52,"props":1032,"children":1033},{},[1034,1038],{"type":43,"tag":68,"props":1035,"children":1036},{},[1037],{"type":49,"value":160},{"type":49,"value":1039}," Test the document with a fresh Claude (no context bleed) to verify it works for readers.",{"type":43,"tag":52,"props":1041,"children":1042},{},[1043,1047],{"type":43,"tag":68,"props":1044,"children":1045},{},[1046],{"type":49,"value":479},{"type":49,"value":1048},"\nExplain that testing will now occur to see if the document actually works for readers. This catches blind spots - things that make sense to the authors but might confuse others.",{"type":43,"tag":164,"props":1050,"children":1052},{"id":1051},"testing-approach",[1053],{"type":49,"value":1054},"Testing Approach",{"type":43,"tag":52,"props":1056,"children":1057},{},[1058],{"type":43,"tag":68,"props":1059,"children":1060},{},[1061],{"type":49,"value":1062},"If access to sub-agents is available (e.g., in Claude Code):",{"type":43,"tag":52,"props":1064,"children":1065},{},[1066],{"type":49,"value":1067},"Perform the testing directly without user involvement.",{"type":43,"tag":164,"props":1069,"children":1071},{"id":1070},"step-1-predict-reader-questions",[1072],{"type":49,"value":1073},"Step 1: Predict Reader Questions",{"type":43,"tag":52,"props":1075,"children":1076},{},[1077],{"type":49,"value":1078},"Announce intention to predict what questions readers might ask when trying to discover this document.",{"type":43,"tag":52,"props":1080,"children":1081},{},[1082],{"type":49,"value":1083},"Generate 5-10 questions that readers would realistically ask.",{"type":43,"tag":164,"props":1085,"children":1087},{"id":1086},"step-2-test-with-sub-agent",[1088],{"type":49,"value":1089},"Step 2: Test with Sub-Agent",{"type":43,"tag":52,"props":1091,"children":1092},{},[1093],{"type":49,"value":1094},"Announce that these questions will be tested with a fresh Claude instance (no context from this conversation).",{"type":43,"tag":52,"props":1096,"children":1097},{},[1098],{"type":49,"value":1099},"For each question, invoke a sub-agent with just the document content and the question.",{"type":43,"tag":52,"props":1101,"children":1102},{},[1103],{"type":49,"value":1104},"Summarize what Reader Claude got right\u002Fwrong for each question.",{"type":43,"tag":164,"props":1106,"children":1108},{"id":1107},"step-3-run-additional-checks",[1109],{"type":49,"value":1110},"Step 3: Run Additional Checks",{"type":43,"tag":52,"props":1112,"children":1113},{},[1114],{"type":49,"value":1115},"Announce additional checks will be performed.",{"type":43,"tag":52,"props":1117,"children":1118},{},[1119],{"type":49,"value":1120},"Invoke sub-agent to check for ambiguity, false assumptions, contradictions.",{"type":43,"tag":52,"props":1122,"children":1123},{},[1124],{"type":49,"value":1125},"Summarize any issues found.",{"type":43,"tag":164,"props":1127,"children":1129},{"id":1128},"step-4-report-and-fix",[1130],{"type":49,"value":1131},"Step 4: Report and Fix",{"type":43,"tag":52,"props":1133,"children":1134},{},[1135],{"type":49,"value":1136},"If issues found:\nReport that Reader Claude struggled with specific issues.",{"type":43,"tag":52,"props":1138,"children":1139},{},[1140],{"type":49,"value":1141},"List the specific issues.",{"type":43,"tag":52,"props":1143,"children":1144},{},[1145],{"type":49,"value":1146},"Indicate intention to fix these gaps.",{"type":43,"tag":52,"props":1148,"children":1149},{},[1150],{"type":49,"value":1151},"Loop back to refinement for problematic sections.",{"type":43,"tag":1153,"props":1154,"children":1155},"hr",{},[],{"type":43,"tag":52,"props":1157,"children":1158},{},[1159],{"type":43,"tag":68,"props":1160,"children":1161},{},[1162],{"type":49,"value":1163},"If no access to sub-agents (e.g., claude.ai web interface):",{"type":43,"tag":52,"props":1165,"children":1166},{},[1167],{"type":49,"value":1168},"The user will need to do the testing manually.",{"type":43,"tag":164,"props":1170,"children":1172},{"id":1171},"step-1-predict-reader-questions-1",[1173],{"type":49,"value":1073},{"type":43,"tag":52,"props":1175,"children":1176},{},[1177],{"type":49,"value":1178},"Ask what questions people might ask when trying to discover this document. What would they type into Claude.ai?",{"type":43,"tag":52,"props":1180,"children":1181},{},[1182],{"type":49,"value":1083},{"type":43,"tag":164,"props":1184,"children":1186},{"id":1185},"step-2-setup-testing",[1187],{"type":49,"value":1188},"Step 2: Setup Testing",{"type":43,"tag":52,"props":1190,"children":1191},{},[1192],{"type":49,"value":1193},"Provide testing instructions:",{"type":43,"tag":104,"props":1195,"children":1196},{},[1197,1210,1215],{"type":43,"tag":78,"props":1198,"children":1199},{},[1200,1202],{"type":49,"value":1201},"Open a fresh Claude conversation: ",{"type":43,"tag":1203,"props":1204,"children":1208},"a",{"href":1205,"rel":1206},"https:\u002F\u002Fclaude.ai",[1207],"nofollow",[1209],{"type":49,"value":1205},{"type":43,"tag":78,"props":1211,"children":1212},{},[1213],{"type":49,"value":1214},"Paste or share the document content (if using a shared doc platform with connectors enabled, provide the link)",{"type":43,"tag":78,"props":1216,"children":1217},{},[1218],{"type":49,"value":1219},"Ask Reader Claude the generated questions",{"type":43,"tag":52,"props":1221,"children":1222},{},[1223],{"type":49,"value":1224},"For each question, instruct Reader Claude to provide:",{"type":43,"tag":74,"props":1226,"children":1227},{},[1228,1233,1238],{"type":43,"tag":78,"props":1229,"children":1230},{},[1231],{"type":49,"value":1232},"The answer",{"type":43,"tag":78,"props":1234,"children":1235},{},[1236],{"type":49,"value":1237},"Whether anything was ambiguous or unclear",{"type":43,"tag":78,"props":1239,"children":1240},{},[1241],{"type":49,"value":1242},"What knowledge\u002Fcontext the doc assumes is already known",{"type":43,"tag":52,"props":1244,"children":1245},{},[1246],{"type":49,"value":1247},"Check if Reader Claude gives correct answers or misinterprets anything.",{"type":43,"tag":164,"props":1249,"children":1251},{"id":1250},"step-3-additional-checks",[1252],{"type":49,"value":1253},"Step 3: Additional Checks",{"type":43,"tag":52,"props":1255,"children":1256},{},[1257],{"type":49,"value":1258},"Also ask Reader Claude:",{"type":43,"tag":74,"props":1260,"children":1261},{},[1262,1267,1272],{"type":43,"tag":78,"props":1263,"children":1264},{},[1265],{"type":49,"value":1266},"\"What in this doc might be ambiguous or unclear to readers?\"",{"type":43,"tag":78,"props":1268,"children":1269},{},[1270],{"type":49,"value":1271},"\"What knowledge or context does this doc assume readers already have?\"",{"type":43,"tag":78,"props":1273,"children":1274},{},[1275],{"type":49,"value":1276},"\"Are there any internal contradictions or inconsistencies?\"",{"type":43,"tag":164,"props":1278,"children":1280},{"id":1279},"step-4-iterate-based-on-results",[1281],{"type":49,"value":1282},"Step 4: Iterate Based on Results",{"type":43,"tag":52,"props":1284,"children":1285},{},[1286],{"type":49,"value":1287},"Ask what Reader Claude got wrong or struggled with. Indicate intention to fix those gaps.",{"type":43,"tag":52,"props":1289,"children":1290},{},[1291],{"type":49,"value":1292},"Loop back to refinement for any problematic sections.",{"type":43,"tag":1153,"props":1294,"children":1295},{},[],{"type":43,"tag":164,"props":1297,"children":1299},{"id":1298},"exit-condition-both-approaches",[1300],{"type":49,"value":1301},"Exit Condition (Both Approaches)",{"type":43,"tag":52,"props":1303,"children":1304},{},[1305],{"type":49,"value":1306},"When Reader Claude consistently answers questions correctly and doesn't surface new gaps or ambiguities, the doc is ready.",{"type":43,"tag":58,"props":1308,"children":1310},{"id":1309},"final-review",[1311],{"type":49,"value":1312},"Final Review",{"type":43,"tag":52,"props":1314,"children":1315},{},[1316],{"type":49,"value":1317},"When Reader Testing passes:\nAnnounce the doc has passed Reader Claude testing. Before completion:",{"type":43,"tag":104,"props":1319,"children":1320},{},[1321,1326,1331],{"type":43,"tag":78,"props":1322,"children":1323},{},[1324],{"type":49,"value":1325},"Recommend they do a final read-through themselves - they own this document and are responsible for its quality",{"type":43,"tag":78,"props":1327,"children":1328},{},[1329],{"type":49,"value":1330},"Suggest double-checking any facts, links, or technical details",{"type":43,"tag":78,"props":1332,"children":1333},{},[1334],{"type":49,"value":1335},"Ask them to verify it achieves the impact they wanted",{"type":43,"tag":52,"props":1337,"children":1338},{},[1339],{"type":49,"value":1340},"Ask if they want one more review, or if the work is done.",{"type":43,"tag":52,"props":1342,"children":1343},{},[1344,1349],{"type":43,"tag":68,"props":1345,"children":1346},{},[1347],{"type":49,"value":1348},"If user wants final review, provide it. Otherwise:",{"type":49,"value":1350},"\nAnnounce document completion. Provide a few final tips:",{"type":43,"tag":74,"props":1352,"children":1353},{},[1354,1359,1364],{"type":43,"tag":78,"props":1355,"children":1356},{},[1357],{"type":49,"value":1358},"Consider linking this conversation in an appendix so readers can see how the doc was developed",{"type":43,"tag":78,"props":1360,"children":1361},{},[1362],{"type":49,"value":1363},"Use appendices to provide depth without bloating the main doc",{"type":43,"tag":78,"props":1365,"children":1366},{},[1367],{"type":49,"value":1368},"Update the doc as feedback is received from real readers",{"type":43,"tag":58,"props":1370,"children":1372},{"id":1371},"tips-for-effective-guidance",[1373],{"type":49,"value":1374},"Tips for Effective Guidance",{"type":43,"tag":52,"props":1376,"children":1377},{},[1378],{"type":43,"tag":68,"props":1379,"children":1380},{},[1381],{"type":49,"value":1382},"Tone:",{"type":43,"tag":74,"props":1384,"children":1385},{},[1386,1391,1396],{"type":43,"tag":78,"props":1387,"children":1388},{},[1389],{"type":49,"value":1390},"Be direct and procedural",{"type":43,"tag":78,"props":1392,"children":1393},{},[1394],{"type":49,"value":1395},"Explain rationale briefly when it affects user behavior",{"type":43,"tag":78,"props":1397,"children":1398},{},[1399],{"type":49,"value":1400},"Don't try to \"sell\" the approach - just execute it",{"type":43,"tag":52,"props":1402,"children":1403},{},[1404],{"type":43,"tag":68,"props":1405,"children":1406},{},[1407],{"type":49,"value":1408},"Handling Deviations:",{"type":43,"tag":74,"props":1410,"children":1411},{},[1412,1417,1422],{"type":43,"tag":78,"props":1413,"children":1414},{},[1415],{"type":49,"value":1416},"If user wants to skip a stage: Ask if they want to skip this and write freeform",{"type":43,"tag":78,"props":1418,"children":1419},{},[1420],{"type":49,"value":1421},"If user seems frustrated: Acknowledge this is taking longer than expected. Suggest ways to move faster",{"type":43,"tag":78,"props":1423,"children":1424},{},[1425],{"type":49,"value":1426},"Always give user agency to adjust the process",{"type":43,"tag":52,"props":1428,"children":1429},{},[1430],{"type":43,"tag":68,"props":1431,"children":1432},{},[1433],{"type":49,"value":1434},"Context Management:",{"type":43,"tag":74,"props":1436,"children":1437},{},[1438,1443],{"type":43,"tag":78,"props":1439,"children":1440},{},[1441],{"type":49,"value":1442},"Throughout, if context is missing on something mentioned, proactively ask",{"type":43,"tag":78,"props":1444,"children":1445},{},[1446],{"type":49,"value":1447},"Don't let gaps accumulate - address them as they come up",{"type":43,"tag":52,"props":1449,"children":1450},{},[1451],{"type":43,"tag":68,"props":1452,"children":1453},{},[1454],{"type":49,"value":1455},"Artifact Management:",{"type":43,"tag":74,"props":1457,"children":1458},{},[1459,1470,1481,1486],{"type":43,"tag":78,"props":1460,"children":1461},{},[1462,1463,1468],{"type":49,"value":799},{"type":43,"tag":567,"props":1464,"children":1466},{"className":1465},[],[1467],{"type":49,"value":572},{"type":49,"value":1469}," for drafting full sections",{"type":43,"tag":78,"props":1471,"children":1472},{},[1473,1474,1479],{"type":49,"value":799},{"type":43,"tag":567,"props":1475,"children":1477},{"className":1476},[],[1478],{"type":49,"value":805},{"type":49,"value":1480}," for all edits",{"type":43,"tag":78,"props":1482,"children":1483},{},[1484],{"type":49,"value":1485},"Provide artifact link after every change",{"type":43,"tag":78,"props":1487,"children":1488},{},[1489],{"type":49,"value":1490},"Never use artifacts for brainstorming lists - that's just conversation",{"type":43,"tag":52,"props":1492,"children":1493},{},[1494],{"type":43,"tag":68,"props":1495,"children":1496},{},[1497],{"type":49,"value":1498},"Quality over Speed:",{"type":43,"tag":74,"props":1500,"children":1501},{},[1502,1507,1512],{"type":43,"tag":78,"props":1503,"children":1504},{},[1505],{"type":49,"value":1506},"Don't rush through stages",{"type":43,"tag":78,"props":1508,"children":1509},{},[1510],{"type":49,"value":1511},"Each iteration should make meaningful improvements",{"type":43,"tag":78,"props":1513,"children":1514},{},[1515],{"type":49,"value":1516},"The goal is a document that actually works for readers",{"items":1518,"total":1642},[1519,1538,1555,1571,1586,1609,1626],{"slug":1520,"name":1520,"fn":1521,"description":1522,"org":1523,"tags":1524,"stars":22,"repoUrl":23,"updatedAt":1537},"algorithmic-art","create generative 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":9},[1525,1528,1531,1534],{"name":1526,"slug":1527,"type":15},"Creative","creative",{"name":1529,"slug":1530,"type":15},"Generative Art","generative-art",{"name":1532,"slug":1533,"type":15},"Graphics","graphics",{"name":1535,"slug":1536,"type":15},"JavaScript","javascript","2026-07-13T06:41:35.540127",{"slug":1539,"name":1539,"fn":1540,"description":1541,"org":1542,"tags":1543,"stars":22,"repoUrl":23,"updatedAt":1554},"antfu","configure JavaScript projects with Anthony Fu's tools","Anthony Fu's opinionated tooling and conventions for JavaScript\u002FTypeScript projects. Use when setting up new projects, configuring ESLint\u002FPrettier alternatives, monorepos, library publishing, or when the user mentions Anthony Fu's preferences.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1544,1547,1550,1551],{"name":1545,"slug":1546,"type":15},"Best Practices","best-practices",{"name":1548,"slug":1549,"type":15},"Engineering","engineering",{"name":1535,"slug":1536,"type":15},{"name":1552,"slug":1553,"type":15},"TypeScript","typescript","2026-07-13T06:43:13.153309",{"slug":1556,"name":1556,"fn":1557,"description":1558,"org":1559,"tags":1560,"stars":22,"repoUrl":23,"updatedAt":1570},"brand-guidelines","apply Anthropic brand guidelines","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":9},[1561,1564,1567],{"name":1562,"slug":1563,"type":15},"Branding","branding",{"name":1565,"slug":1566,"type":15},"Design","design",{"name":1568,"slug":1569,"type":15},"Typography","typography","2026-07-13T06:43:06.077629",{"slug":1572,"name":1572,"fn":1573,"description":1574,"org":1575,"tags":1576,"stars":22,"repoUrl":23,"updatedAt":1585},"canvas-design","create visual art and design assets","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":9},[1577,1578,1579,1582],{"name":1526,"slug":1527,"type":15},{"name":1565,"slug":1566,"type":15},{"name":1580,"slug":1581,"type":15},"Images","images",{"name":1583,"slug":1584,"type":15},"PDF","pdf","2026-07-13T06:39:58.803113",{"slug":1587,"name":1587,"fn":1588,"description":1589,"org":1590,"tags":1591,"stars":22,"repoUrl":23,"updatedAt":1608},"ci-cd-containerization-advisor","design CI\u002FCD pipelines for Kotlin applications","Design reproducible build, image, and deployment pipelines for Kotlin plus Spring applications, including CI verification, layered containers, rollout safety, and deployment-time migration coordination. Use when creating or improving Dockerfiles, CI workflows, image hardening, Kubernetes manifests, release gates, or deployment strategies for Spring Boot services, especially where build reproducibility and operational safety matter.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1592,1595,1598,1601,1602,1605],{"name":1593,"slug":1594,"type":15},"CI\u002FCD","ci-cd",{"name":1596,"slug":1597,"type":15},"Containers","containers",{"name":1599,"slug":1600,"type":15},"Deployment","deployment",{"name":1548,"slug":1549,"type":15},{"name":1603,"slug":1604,"type":15},"Kotlin","kotlin",{"name":1606,"slug":1607,"type":15},"Spring","spring","2026-07-13T06:41:47.83899",{"slug":1610,"name":1610,"fn":1611,"description":1612,"org":1613,"tags":1614,"stars":22,"repoUrl":23,"updatedAt":1625},"cloudflare-deploy","deploy applications to Cloudflare","Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1615,1618,1621,1624],{"name":1616,"slug":1617,"type":15},"Cloudflare","cloudflare",{"name":1619,"slug":1620,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1622,"slug":1623,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1599,"slug":1600,"type":15},"2026-07-17T06:04:42.853896",{"slug":1627,"name":1627,"fn":1628,"description":1629,"org":1630,"tags":1631,"stars":22,"repoUrl":23,"updatedAt":1641},"compose-ui-control","interact with Compose Desktop applications","Control a running Compose Desktop application via HTTP. Use when you need to interact with UI elements, click buttons, enter text, wait for elements to appear, or capture screenshots in a Compose Desktop app that has compose-ui-test-server enabled.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1632,1635,1638],{"name":1633,"slug":1634,"type":15},"Automation","automation",{"name":1636,"slug":1637,"type":15},"Desktop","desktop",{"name":1639,"slug":1640,"type":15},"UI Components","ui-components","2026-07-13T06:40:38.798626",128,{"items":1644,"total":1769},[1645,1661,1670,1679,1690,1700,1709,1718,1727,1737,1746,1759],{"slug":1646,"name":1646,"fn":1647,"description":1648,"org":1649,"tags":1650,"stars":1658,"repoUrl":1659,"updatedAt":1660},"mps-aspect-accessories","configure JetBrains MPS module dependencies","Wire MPS module and model dependencies, used languages, used devkits, extended languages, runtime solutions, accessory models, and language\u002Fdependency versions. Use when adding\u002Fremoving module dependencies, importing languages or devkits into a model, declaring runtime solutions, or shipping accessory content visible to consumers without explicit import.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1651,1654,1657],{"name":1652,"slug":1653,"type":15},"Architecture","architecture",{"name":1655,"slug":1656,"type":15},"Configuration","configuration",{"name":1548,"slug":1549,"type":15},1650,"https:\u002F\u002Fgithub.com\u002FJetBrains\u002FMPS","2026-07-17T06:06:57.311661",{"slug":1662,"name":1662,"fn":1663,"description":1664,"org":1665,"tags":1666,"stars":1658,"repoUrl":1659,"updatedAt":1669},"mps-aspect-actions","define and edit MPS node factories","Use when defining or editing MPS node factories (the \"actions\" aspect) — `NodeFactories` roots, per-concept `NodeFactory` setup functions that initialize a freshly created node and optionally copy data from a replaced `sampleNode`, plus the actions aspect's `CopyPasteHandlers` and `PasteWrappers` roots. Reach for this skill when a substitution, side transform, completion replacement, or `add new initialized(...)` should preserve fields from the node it is replacing, or when defaults set in a constructor are not enough.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1667,1668],{"name":1652,"slug":1653,"type":15},{"name":1548,"slug":1549,"type":15},"2026-07-17T06:04:48.066901",{"slug":1671,"name":1671,"fn":1672,"description":1673,"org":1674,"tags":1675,"stars":1658,"repoUrl":1659,"updatedAt":1678},"mps-aspect-behavior","define and edit MPS concept behavior","Use when defining or editing MPS `ConceptBehavior` — per-concept methods (non-virtual \u002F virtual \u002F abstract \u002F static \u002F virtual static), constructors, virtual dispatch (MRO), super and interface-default calls (`super\u003CInterface>.method`), overriding methods from `lang.core.behavior` interfaces such as `ScopeProvider.getScope` \u002F `INamedConcept.getName` \u002F `BaseConcept.getPresentation`, calling sibling methods (`LocalBehaviorMethodCall`) and behavior methods from other aspects via `node.method(...)`. Reach for this skill whenever the task involves authoring or modifying `\u003Clang>\u002FlanguageModels\u002Fbehavior.mps`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1676,1677],{"name":1652,"slug":1653,"type":15},{"name":1548,"slug":1549,"type":15},"2026-07-13T06:45:21.757084",{"slug":1680,"name":1680,"fn":1681,"description":1682,"org":1683,"tags":1684,"stars":1658,"repoUrl":1659,"updatedAt":1689},"mps-aspect-constraints","define JetBrains MPS language constraints","Use when defining or editing MPS language constraints — property validators \u002F setters \u002F getters, referent search scopes (imperative or inherited via `ScopeProvider.getScope`), `referentSetHandler` side effects, default-scope blocks, `canBeChild` \u002F `canBeParent` \u002F `canBeAncestor` \u002F `canBeRoot` placement rules, `defaultConcreteConcept` for abstract concepts, `set \u003Cread-only>` and `{name}` aliasing, and scope helpers (`SimpleRoleScope`, `ListScope`, `CompositeScope`, `HidingByNameScope`). Reach for this skill whenever the task involves authoring or modifying `\u003Clang>\u002FlanguageModels\u002Fconstraints.mps`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1685,1686],{"name":1652,"slug":1653,"type":15},{"name":1687,"slug":1688,"type":15},"Code Analysis","code-analysis","2026-07-23T05:41:33.639365",{"slug":1691,"name":1691,"fn":1692,"description":1693,"org":1694,"tags":1695,"stars":1658,"repoUrl":1659,"updatedAt":1699},"mps-aspect-dataflow","define and debug MPS dataflow builders","Use when defining or debugging MPS dataflow builders for a concept — control\u002Fdata flow declarations that drive reachability analysis and variable-use checking. Covers DataFlowBuilderDeclaration, BuilderBlock, emit instructions (code for, jump, ifjump, label, read, write, ret, mayBeUnreachable), positions (AfterPosition, BeforePosition, LabelPosition), the jetbrains.mps.lang.dataFlow language, the NodeParameter implicit, BL+smodel usage inside builder bodies, and IBuilderMode for advanced analyses such as nullable\u002Fnon-null tracking.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1696],{"name":1697,"slug":1698,"type":15},"Data Analysis","data-analysis","2026-07-13T06:45:19.114674",{"slug":1701,"name":1701,"fn":1702,"description":1703,"org":1704,"tags":1705,"stars":1658,"repoUrl":1659,"updatedAt":1708},"mps-aspect-editor","define MPS editor layouts","Use when creating or changing MPS editor definitions — the overall workflow from scaffolding a `ConceptEditorDeclaration` through componentizing reusable `EditorComponentDeclaration`s, refining cell models and cell layouts, applying style sheets and indent-layout style items, wiring smart references, leveraging inheritance via super-concepts and interfaces, inspecting (`print_node_json`, `show_node_representation`) and validating (`check_root_node_problems`). Covers `jetbrains.mps.lang.editor` cell models (`CellModel_RefNode`\u002F`CellModel_RefNodeList`\u002F`CellModel_RefCell`\u002F`CellModel_Property`\u002F`CellModel_Constant`), layout choices, and JSON blueprints for common editor shapes. For the non-layout side (action maps, keymaps, transformation\u002Fsubstitute menus) use `mps-aspect-editor-menus-and-keymaps`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1706,1707],{"name":1565,"slug":1566,"type":15},{"name":1639,"slug":1640,"type":15},"2026-07-23T05:41:56.638151",{"slug":1710,"name":1710,"fn":1711,"description":1712,"org":1713,"tags":1714,"stars":1658,"repoUrl":1659,"updatedAt":1717},"mps-aspect-editor-menus-and-keymaps","author MPS editor menus and keymaps","Use when authoring the **non-layout** parts of the MPS editor aspect — what happens when the user types, presses a key, triggers completion, pastes, or invokes a context action. Covers action maps (`CellActionMapDeclaration`), cell keymaps (`CellKeyMapDeclaration`), transformation menus (`TransformationMenu_Default` \u002F `_Named` \u002F `_Contribution`), substitute menus (`SubstituteMenu_Default` \u002F `SubstituteMenu` \u002F contributions), side transforms (LEFT\u002FRIGHT), legacy cell menus, paste wrappers and copy-paste handlers (in the actions language), completion styling, reference presentation, two-step deletion, and the editor selection API. Trigger terms: `actionMap`, `keyMap`, `delete_action_id`, `transformationMenu`, `substituteMenu`, `Ctrl+Space`, `Ctrl+Alt+B`, side transform, paste wrapper, completion styling, `PasteWrappers`, `CopyPasteHandlers`. For the **layout** side (cells, layouts, style sheets) use `mps-aspect-editor` instead.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1715,1716],{"name":1548,"slug":1549,"type":15},{"name":1639,"slug":1640,"type":15},"2026-07-23T05:41:49.666535",{"slug":1719,"name":1719,"fn":1720,"description":1721,"org":1722,"tags":1723,"stars":1658,"repoUrl":1659,"updatedAt":1726},"mps-aspect-generation-plan","modify MPS generation plans","Use when defining or modifying an MPS generation plan — explicit ordering of generators, checkpoints for cross-model reference resolution, forks for parallel branches, IncludePlan composition, conditional PlanContribution activation, ParameterEquals\u002FConceptListSelector fork selectors, and InitModelAttributes for targetFacet routing. Apply when working with @genplan models, the jetbrains.mps.lang.generator.plan language, attaching plans via DevKits or the Custom generation facet, or debugging cross-model mapping label resolution.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1724,1725],{"name":1652,"slug":1653,"type":15},{"name":1548,"slug":1549,"type":15},"2026-07-13T06:44:59.507855",{"slug":1728,"name":1728,"fn":1729,"description":1730,"org":1731,"tags":1732,"stars":1658,"repoUrl":1659,"updatedAt":1736},"mps-aspect-generator","define JetBrains MPS generator rules","Use when defining or modifying MPS generators — author a generator module, add or edit root\u002Freduction\u002Fweaving\u002Fpattern mapping rules, attach template macros ($COPY_SRC, $LOOP, $IF, $PROPERTY, $REF, $SWITCH, $MAP_SRC, $WEAVE, $INSERT, $LABEL, $TRACE, $VAR), wire mapping labels, build template switches, write pre\u002Fpost mapping scripts, navigate `genContext`, or debug \"rule didn't fire\", missing references, empty output, infinite reduction loops, and generated-Java compile failures.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1733,1734,1735],{"name":1652,"slug":1653,"type":15},{"name":1687,"slug":1688,"type":15},{"name":1548,"slug":1549,"type":15},"2026-07-17T06:06:58.042999",{"slug":1738,"name":1738,"fn":1739,"description":1740,"org":1741,"tags":1742,"stars":1658,"repoUrl":1659,"updatedAt":1745},"mps-aspect-intentions","define and edit MPS intentions","Use when defining or editing MPS intentions (the Alt+Enter context-action aspect) — adding `IntentionDeclaration` roots, parameterized or surround-with variants, description\u002FisApplicable\u002Fexecute blocks, child-filter functions, factory-initialized AST splicing, or debugging why an intention is not offered. Lives in the language's `intentions` model and uses `jetbrains.mps.lang.intentions`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1743,1744],{"name":1652,"slug":1653,"type":15},{"name":1548,"slug":1549,"type":15},"2026-07-23T05:41:48.692899",{"slug":1747,"name":1747,"fn":1748,"description":1749,"org":1750,"tags":1751,"stars":1658,"repoUrl":1659,"updatedAt":1758},"mps-aspect-migrations","author and debug MPS migration scripts","Use when authoring or debugging MPS migration scripts that upgrade user models after a language definition changes — covers jetbrains.mps.lang.migration (MigrationScript class-based, PureMigrationScript declarative, MoveConcept\u002FMoveContainmentLink\u002FMoveReferenceLink\u002FMoveProperty, ordering via OrderDependency, data exchange via putData\u002FgetData, RefactoringLog, ConceptMigrationReference) and jetbrains.mps.lang.script Enhancement Scripts (MigrationScript with MigrationScriptPart_Instance, ExtractInterfaceMigration, FactoryMigrationScriptPart, CommentMigrationScriptPart) — when a model needs version-gated upgrade, concept rename or removal, link or property rename, instance-level transformation, or composition of migration steps.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1752,1755],{"name":1753,"slug":1754,"type":15},"Debugging","debugging",{"name":1756,"slug":1757,"type":15},"Migration","migration","2026-07-13T06:45:20.372122",{"slug":1760,"name":1760,"fn":1761,"description":1762,"org":1763,"tags":1764,"stars":1658,"repoUrl":1659,"updatedAt":1768},"mps-aspect-structure-concepts","define concepts in MPS structure aspect","Define concepts, interface concepts, enumerations, and constrained data types in an MPS language's `structure` aspect. Covers smart-reference detection, alias rules, cardinality, INamedConcept usage, bulk creation, and the full `mps_mcp_alter_structure` \u002F `mps_mcp_query_structure` reference. Use when authoring or modifying a language's structure model.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1765],{"name":1766,"slug":1767,"type":15},"Data Modeling","data-modeling","2026-07-23T05:41:30.705975",188]