[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-metric-diagnostics":3,"mdc-xm2oll-key":36,"related-repo-openai-metric-diagnostics":471,"related-org-openai-metric-diagnostics":584},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":25,"repoUrl":26,"updatedAt":27,"license":28,"forks":29,"topics":30,"repo":31,"sourceUrl":34,"mdContent":35},"metric-diagnostics","diagnose changes in business metrics","Diagnose why a metric changed or differs from expectation. Use when the task is to identify likely drivers of a metric movement, anomaly, gap, or discrepancy.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,16,19,22],{"name":13,"slug":14,"type":15},"Variance Analysis","variance-analysis","tag",{"name":17,"slug":18,"type":15},"Data Analysis","data-analysis",{"name":20,"slug":21,"type":15},"Analytics","analytics",{"name":23,"slug":24,"type":15},"Statistics","statistics",427,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Frole-specific-plugins","2026-07-01T07:55:02.500753",null,65,[],{"repoUrl":26,"stars":25,"forks":29,"topics":32,"description":33},[],"Role-specific Codex plugin templates","https:\u002F\u002Fgithub.com\u002Fopenai\u002Frole-specific-plugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fdata-analytics\u002Fskills\u002Fmetric-diagnostics","---\nname: metric-diagnostics\ndescription: \"Diagnose why a metric changed or differs from expectation. Use when the task is to identify likely drivers of a metric movement, anomaly, gap, or discrepancy.\"\n---\n\n## Related Skills\n\nUse $gather-business-context when business context is needed to understand the metric, analysis period, ownership, or plausible explanations.\n\nUse $product-business-analysis when the task asks for a recommendation or tradeoff decision after diagnosing the movement.\n\nUse $analyze-data-quality when dashboard trust, grain, freshness, or source disagreement could affect the metric.\n\n# Metric Diagnostics\n\nUse this skill to diagnose why a metric changed or differs from expectation. Reproduce the metric, define the comparison, quantify the movement, validate likely drivers, and state what is verified, likely, unresolved, and useful to do next.\n\nClarify with the user when a missing input would materially change the analytical frame or recommendation. Otherwise make a reasonable assumption, state it, and proceed.\n\n## Skill Configuration\n\n### Source Discovery And Verification\n\nUse the relevant semantic layer as a starting map, not a boundary.\n\n1. **Explore all possible sources.** Search every connected or provided source that could contain task-relevant data or change the interpretation. Within each structured-data source, run fresh catalog or metadata discovery for relevant schemas, datasets, tables, views, models, and metrics. Known sources, tables, dashboards, and semantic mappings are starting points, not stopping points.\n2. **Compare duplicates and conflicts.** When sources overlap or disagree, compare ownership, freshness, definition, grain, coverage, and directness. Use the best authoritative source, or combine complementary sources when needed. Note material conflicts, explain why the selected source or sources control the answer, and verify selected data through live reads before concluding.\n\n### Source Access Guardrail\n\nBefore querying sources, building artifacts, or drawing conclusions, determine whether the answer requires a specific source of truth.\n\nIf a required source is unavailable, stop that path. Tell the user what source is needed, ask them to make it available or provide a reviewed fallback, and do not treat weaker substitutes as equivalent.\n\nIf the missing source is only optional enrichment, continue with the strongest available evidence and label the gap when it materially affects the answer.\n\n## Workflow\n\n### 1. Define The Diagnostic Question\n\nFrame the diagnostic so it is clear what changed and what comparison would prove it.\n\nDefine:\n\n- what the metric means in business terms\n- the time window and comparison that make the change measurable\n- the population and grain that determine what counts\n- the source that owns the metric definition\n- the diagnostic question being answered, for example movement, concentration, or reconciliation\n\nUse $gather-business-context when business context is needed to understand what the metric means, what changed around the analysis period, or which explanations are plausible.\n\n### 2. Validate The Metric Definition And Source\n\nBefore explaining the movement, confirm that the metric is defined correctly and that the source data can measure it reliably.\n\nConfirm the metric definition, grain, aggregation logic, filters, joins, exclusions, freshness, lineage, and any disagreement between trusted surfaces. Keep this source check focused on issues that could change the answer.\n\nTreat current context, named semantic layers, and familiar table names as source candidates, not source selection. For broad metric questions, run live source discovery against available tables, dashboards, metric docs, semantic layers, or other source-of-truth surfaces before choosing the controlling source. When both are available, inspect at least one business-facing or top-line surface and one lower-level source surface, then state why the selected source owns the answer.\n\nUse $analyze-data-quality when freshness, grain, joins, missingness, schema drift, outliers, unexpected categories, or distribution shifts could affect trust.\n\nUse $jupyter-notebooks when fresh SQL, Python, statistical modeling, reusable calculations, or multi-step decomposition need an inspectable analytical record.\n\n### 3. Establish The Metric Pattern\n\nBefore looking for drivers, establish the metric pattern the diagnostic needs to explain. Quantify the metric over the relevant period and scope. If the question includes a comparison, reproduce that comparison.\n\nDo not search for causes until the size, timing, and scope of the pattern are verified or explicitly marked uncertain.\n\n### 4. Choose The Diagnostic Plan\n\nChoose the smallest set of cuts and checks likely to explain the pattern or strengthen confidence.\n\nChoose driver dimensions from the metric's operating logic, business context, and source shape. Prioritize drivers the business usually monitors or can act on, not every field available in the source. If the relevant drivers are unclear, use current context, a named semantic layer, or $gather-business-context to understand how the business explains the metric and what changed around the analysis period.\n\nWhen using a lower-level table, do not limit the driver analysis to fields surfaced by the first query. Recreate or join the business grouping needed to answer the question, such as model family, model superfamily, segment, region, cohort, product taxonomy, or customer hierarchy. If the grouping cannot be reconstructed, say so before simplifying the analysis.\n\nUse the explanation mode that fits the question. Common examples:\n\n- **Metric change**: compare the focal window with a baseline, rank segment contributions, check peer or historical context, and test mix shift versus within-segment movement.\n- **Spike, regression, or incident**: pin down onset, peak, recovery,\n  distribution shape rather than only averages, affected slices, broad versus localized degradation, and whether traffic or failure behavior changed.\n- **Largest contributors or concentration**: define \"largest\", rank entities,\n  compare total share and change, and look for major movers, entrants, and exits.\n- **Reconciliation or difference analysis**: align definitions, filters, grain,\n  numerator, denominator, and exclusions; quantify the components explaining the gap and state any residual.\n\n### 5. Decompose And Validate Drivers\n\nQuantify the main drivers and validate whether they explain the pattern.\n\nSize each major driver with the strongest readily available evidence. Show whether it explains the pattern, how large it is relative to the relevant base, trend, or gap, whether it is broad or concentrated, and whether it holds under the right comparison or scope.\n\nIterate on driver hypotheses until the explanation answers why in a way that is relevant to the business. Follow promising cross-cuts and drill-downs when they could reveal the key explanation, and stop when additional cuts are unlikely to change the conclusion or materially improve confidence.\n\nInterpret driver results in context:\n\n- Use the relevant base, comparison, or share of total to make the driver meaningful.\n- For rates, check whether the numerator, denominator, or both explain the change.\n- For additive metrics, calculate contribution share when it sharpens the story.\n- Separate composition effects from within-segment performance effects when that distinction changes the explanation.\n- Prefer mutually exclusive driver buckets when additive contributions need to be interpreted; reconcile the decomposition exactly or size and explain the residual.\n\nTreat measurement issues as possible explanations, not just cleanup details. For example, the pattern may come from logging changes, incomplete recent data, duplicated rows, or a shifted denominator rather than an underlying business change.\n\nCalibrate the explanation to the evidence, and make important uncertainty visible. Use context when it changes interpretation, such as whether the pattern is ordinary, unusual, expected, or tied to a known change.\n\nUse $visualize-data when a chart would make the diagnostic claim easier to understand or verify.\n\n### 6. State Implications And Follow-Up\n\nLead with the answer to the diagnostic question, then state the practical implications when the evidence supports them.\n\nThe answer should make clear:\n\n- the pattern being explained\n- the strongest driver explanation and supporting evidence\n- why it matters for the business\n- how much confidence to place in the explanation\n- the implication, next action, or follow-up that matters most\n\nUse $product-business-analysis when the user needs a recommendation or tradeoff decision, not just the diagnostic implication.\n\nKeep implications distinguishable from verified factual reporting so a reader can tell where evidence ends and interpretation begins. Do not claim causality from timing alone; state when an explanation is only a plausible hypothesis.\n\nUse $gather-business-context when the metric result is clear but business context is needed to interpret the `so what` or identify realistic next actions.\n\nUse $validate-data when methodology, calculations, caveats, or the evidentiary support for the diagnostic conclusion need review before sharing.\n\nDo not treat artifact or report validation as analytical validation. Before handing off, confirm the analysis has the headline metric movement, driver contribution shares or effect sizes, source\u002Fwindow reconciliation, exact executed SQL or query references when queries were used, and caveats that would change interpretation.\n\nPass the diagnostic substance and supporting evidence to $build-report unless the user explicitly requests an inline, chat-only, brief\u002Fno-artifact answer, asks not to create a report\u002Ffile\u002Fartifact, or selects another primary artifact. This handoff is mandatory when no explicit human waiver was given; do not infer a waiver because the user asked a direct diagnostic question or did not use the word \"report\". Let $build-report own the report surface, presentation polish, reproducibility treatment, and sharing handoff.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,50,56,61,66,72,77,82,88,95,100,126,132,137,142,147,153,159,164,169,198,203,209,214,219,224,229,234,240,245,250,256,261,266,271,276,319,325,330,335,340,345,373,378,383,388,394,399,404,432,437,442,456,461,466],{"type":42,"tag":43,"props":44,"children":46},"element","h2",{"id":45},"related-skills",[47],{"type":48,"value":49},"text","Related Skills",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54],{"type":48,"value":55},"Use $gather-business-context when business context is needed to understand the metric, analysis period, ownership, or plausible explanations.",{"type":42,"tag":51,"props":57,"children":58},{},[59],{"type":48,"value":60},"Use $product-business-analysis when the task asks for a recommendation or tradeoff decision after diagnosing the movement.",{"type":42,"tag":51,"props":62,"children":63},{},[64],{"type":48,"value":65},"Use $analyze-data-quality when dashboard trust, grain, freshness, or source disagreement could affect the metric.",{"type":42,"tag":67,"props":68,"children":69},"h1",{"id":4},[70],{"type":48,"value":71},"Metric Diagnostics",{"type":42,"tag":51,"props":73,"children":74},{},[75],{"type":48,"value":76},"Use this skill to diagnose why a metric changed or differs from expectation. Reproduce the metric, define the comparison, quantify the movement, validate likely drivers, and state what is verified, likely, unresolved, and useful to do next.",{"type":42,"tag":51,"props":78,"children":79},{},[80],{"type":48,"value":81},"Clarify with the user when a missing input would materially change the analytical frame or recommendation. Otherwise make a reasonable assumption, state it, and proceed.",{"type":42,"tag":43,"props":83,"children":85},{"id":84},"skill-configuration",[86],{"type":48,"value":87},"Skill Configuration",{"type":42,"tag":89,"props":90,"children":92},"h3",{"id":91},"source-discovery-and-verification",[93],{"type":48,"value":94},"Source Discovery And Verification",{"type":42,"tag":51,"props":96,"children":97},{},[98],{"type":48,"value":99},"Use the relevant semantic layer as a starting map, not a boundary.",{"type":42,"tag":101,"props":102,"children":103},"ol",{},[104,116],{"type":42,"tag":105,"props":106,"children":107},"li",{},[108,114],{"type":42,"tag":109,"props":110,"children":111},"strong",{},[112],{"type":48,"value":113},"Explore all possible sources.",{"type":48,"value":115}," Search every connected or provided source that could contain task-relevant data or change the interpretation. Within each structured-data source, run fresh catalog or metadata discovery for relevant schemas, datasets, tables, views, models, and metrics. Known sources, tables, dashboards, and semantic mappings are starting points, not stopping points.",{"type":42,"tag":105,"props":117,"children":118},{},[119,124],{"type":42,"tag":109,"props":120,"children":121},{},[122],{"type":48,"value":123},"Compare duplicates and conflicts.",{"type":48,"value":125}," When sources overlap or disagree, compare ownership, freshness, definition, grain, coverage, and directness. Use the best authoritative source, or combine complementary sources when needed. Note material conflicts, explain why the selected source or sources control the answer, and verify selected data through live reads before concluding.",{"type":42,"tag":89,"props":127,"children":129},{"id":128},"source-access-guardrail",[130],{"type":48,"value":131},"Source Access Guardrail",{"type":42,"tag":51,"props":133,"children":134},{},[135],{"type":48,"value":136},"Before querying sources, building artifacts, or drawing conclusions, determine whether the answer requires a specific source of truth.",{"type":42,"tag":51,"props":138,"children":139},{},[140],{"type":48,"value":141},"If a required source is unavailable, stop that path. Tell the user what source is needed, ask them to make it available or provide a reviewed fallback, and do not treat weaker substitutes as equivalent.",{"type":42,"tag":51,"props":143,"children":144},{},[145],{"type":48,"value":146},"If the missing source is only optional enrichment, continue with the strongest available evidence and label the gap when it materially affects the answer.",{"type":42,"tag":43,"props":148,"children":150},{"id":149},"workflow",[151],{"type":48,"value":152},"Workflow",{"type":42,"tag":89,"props":154,"children":156},{"id":155},"_1-define-the-diagnostic-question",[157],{"type":48,"value":158},"1. Define The Diagnostic Question",{"type":42,"tag":51,"props":160,"children":161},{},[162],{"type":48,"value":163},"Frame the diagnostic so it is clear what changed and what comparison would prove it.",{"type":42,"tag":51,"props":165,"children":166},{},[167],{"type":48,"value":168},"Define:",{"type":42,"tag":170,"props":171,"children":172},"ul",{},[173,178,183,188,193],{"type":42,"tag":105,"props":174,"children":175},{},[176],{"type":48,"value":177},"what the metric means in business terms",{"type":42,"tag":105,"props":179,"children":180},{},[181],{"type":48,"value":182},"the time window and comparison that make the change measurable",{"type":42,"tag":105,"props":184,"children":185},{},[186],{"type":48,"value":187},"the population and grain that determine what counts",{"type":42,"tag":105,"props":189,"children":190},{},[191],{"type":48,"value":192},"the source that owns the metric definition",{"type":42,"tag":105,"props":194,"children":195},{},[196],{"type":48,"value":197},"the diagnostic question being answered, for example movement, concentration, or reconciliation",{"type":42,"tag":51,"props":199,"children":200},{},[201],{"type":48,"value":202},"Use $gather-business-context when business context is needed to understand what the metric means, what changed around the analysis period, or which explanations are plausible.",{"type":42,"tag":89,"props":204,"children":206},{"id":205},"_2-validate-the-metric-definition-and-source",[207],{"type":48,"value":208},"2. Validate The Metric Definition And Source",{"type":42,"tag":51,"props":210,"children":211},{},[212],{"type":48,"value":213},"Before explaining the movement, confirm that the metric is defined correctly and that the source data can measure it reliably.",{"type":42,"tag":51,"props":215,"children":216},{},[217],{"type":48,"value":218},"Confirm the metric definition, grain, aggregation logic, filters, joins, exclusions, freshness, lineage, and any disagreement between trusted surfaces. Keep this source check focused on issues that could change the answer.",{"type":42,"tag":51,"props":220,"children":221},{},[222],{"type":48,"value":223},"Treat current context, named semantic layers, and familiar table names as source candidates, not source selection. For broad metric questions, run live source discovery against available tables, dashboards, metric docs, semantic layers, or other source-of-truth surfaces before choosing the controlling source. When both are available, inspect at least one business-facing or top-line surface and one lower-level source surface, then state why the selected source owns the answer.",{"type":42,"tag":51,"props":225,"children":226},{},[227],{"type":48,"value":228},"Use $analyze-data-quality when freshness, grain, joins, missingness, schema drift, outliers, unexpected categories, or distribution shifts could affect trust.",{"type":42,"tag":51,"props":230,"children":231},{},[232],{"type":48,"value":233},"Use $jupyter-notebooks when fresh SQL, Python, statistical modeling, reusable calculations, or multi-step decomposition need an inspectable analytical record.",{"type":42,"tag":89,"props":235,"children":237},{"id":236},"_3-establish-the-metric-pattern",[238],{"type":48,"value":239},"3. Establish The Metric Pattern",{"type":42,"tag":51,"props":241,"children":242},{},[243],{"type":48,"value":244},"Before looking for drivers, establish the metric pattern the diagnostic needs to explain. Quantify the metric over the relevant period and scope. If the question includes a comparison, reproduce that comparison.",{"type":42,"tag":51,"props":246,"children":247},{},[248],{"type":48,"value":249},"Do not search for causes until the size, timing, and scope of the pattern are verified or explicitly marked uncertain.",{"type":42,"tag":89,"props":251,"children":253},{"id":252},"_4-choose-the-diagnostic-plan",[254],{"type":48,"value":255},"4. Choose The Diagnostic Plan",{"type":42,"tag":51,"props":257,"children":258},{},[259],{"type":48,"value":260},"Choose the smallest set of cuts and checks likely to explain the pattern or strengthen confidence.",{"type":42,"tag":51,"props":262,"children":263},{},[264],{"type":48,"value":265},"Choose driver dimensions from the metric's operating logic, business context, and source shape. Prioritize drivers the business usually monitors or can act on, not every field available in the source. If the relevant drivers are unclear, use current context, a named semantic layer, or $gather-business-context to understand how the business explains the metric and what changed around the analysis period.",{"type":42,"tag":51,"props":267,"children":268},{},[269],{"type":48,"value":270},"When using a lower-level table, do not limit the driver analysis to fields surfaced by the first query. Recreate or join the business grouping needed to answer the question, such as model family, model superfamily, segment, region, cohort, product taxonomy, or customer hierarchy. If the grouping cannot be reconstructed, say so before simplifying the analysis.",{"type":42,"tag":51,"props":272,"children":273},{},[274],{"type":48,"value":275},"Use the explanation mode that fits the question. Common examples:",{"type":42,"tag":170,"props":277,"children":278},{},[279,289,299,309],{"type":42,"tag":105,"props":280,"children":281},{},[282,287],{"type":42,"tag":109,"props":283,"children":284},{},[285],{"type":48,"value":286},"Metric change",{"type":48,"value":288},": compare the focal window with a baseline, rank segment contributions, check peer or historical context, and test mix shift versus within-segment movement.",{"type":42,"tag":105,"props":290,"children":291},{},[292,297],{"type":42,"tag":109,"props":293,"children":294},{},[295],{"type":48,"value":296},"Spike, regression, or incident",{"type":48,"value":298},": pin down onset, peak, recovery,\ndistribution shape rather than only averages, affected slices, broad versus localized degradation, and whether traffic or failure behavior changed.",{"type":42,"tag":105,"props":300,"children":301},{},[302,307],{"type":42,"tag":109,"props":303,"children":304},{},[305],{"type":48,"value":306},"Largest contributors or concentration",{"type":48,"value":308},": define \"largest\", rank entities,\ncompare total share and change, and look for major movers, entrants, and exits.",{"type":42,"tag":105,"props":310,"children":311},{},[312,317],{"type":42,"tag":109,"props":313,"children":314},{},[315],{"type":48,"value":316},"Reconciliation or difference analysis",{"type":48,"value":318},": align definitions, filters, grain,\nnumerator, denominator, and exclusions; quantify the components explaining the gap and state any residual.",{"type":42,"tag":89,"props":320,"children":322},{"id":321},"_5-decompose-and-validate-drivers",[323],{"type":48,"value":324},"5. Decompose And Validate Drivers",{"type":42,"tag":51,"props":326,"children":327},{},[328],{"type":48,"value":329},"Quantify the main drivers and validate whether they explain the pattern.",{"type":42,"tag":51,"props":331,"children":332},{},[333],{"type":48,"value":334},"Size each major driver with the strongest readily available evidence. Show whether it explains the pattern, how large it is relative to the relevant base, trend, or gap, whether it is broad or concentrated, and whether it holds under the right comparison or scope.",{"type":42,"tag":51,"props":336,"children":337},{},[338],{"type":48,"value":339},"Iterate on driver hypotheses until the explanation answers why in a way that is relevant to the business. Follow promising cross-cuts and drill-downs when they could reveal the key explanation, and stop when additional cuts are unlikely to change the conclusion or materially improve confidence.",{"type":42,"tag":51,"props":341,"children":342},{},[343],{"type":48,"value":344},"Interpret driver results in context:",{"type":42,"tag":170,"props":346,"children":347},{},[348,353,358,363,368],{"type":42,"tag":105,"props":349,"children":350},{},[351],{"type":48,"value":352},"Use the relevant base, comparison, or share of total to make the driver meaningful.",{"type":42,"tag":105,"props":354,"children":355},{},[356],{"type":48,"value":357},"For rates, check whether the numerator, denominator, or both explain the change.",{"type":42,"tag":105,"props":359,"children":360},{},[361],{"type":48,"value":362},"For additive metrics, calculate contribution share when it sharpens the story.",{"type":42,"tag":105,"props":364,"children":365},{},[366],{"type":48,"value":367},"Separate composition effects from within-segment performance effects when that distinction changes the explanation.",{"type":42,"tag":105,"props":369,"children":370},{},[371],{"type":48,"value":372},"Prefer mutually exclusive driver buckets when additive contributions need to be interpreted; reconcile the decomposition exactly or size and explain the residual.",{"type":42,"tag":51,"props":374,"children":375},{},[376],{"type":48,"value":377},"Treat measurement issues as possible explanations, not just cleanup details. For example, the pattern may come from logging changes, incomplete recent data, duplicated rows, or a shifted denominator rather than an underlying business change.",{"type":42,"tag":51,"props":379,"children":380},{},[381],{"type":48,"value":382},"Calibrate the explanation to the evidence, and make important uncertainty visible. Use context when it changes interpretation, such as whether the pattern is ordinary, unusual, expected, or tied to a known change.",{"type":42,"tag":51,"props":384,"children":385},{},[386],{"type":48,"value":387},"Use $visualize-data when a chart would make the diagnostic claim easier to understand or verify.",{"type":42,"tag":89,"props":389,"children":391},{"id":390},"_6-state-implications-and-follow-up",[392],{"type":48,"value":393},"6. State Implications And Follow-Up",{"type":42,"tag":51,"props":395,"children":396},{},[397],{"type":48,"value":398},"Lead with the answer to the diagnostic question, then state the practical implications when the evidence supports them.",{"type":42,"tag":51,"props":400,"children":401},{},[402],{"type":48,"value":403},"The answer should make clear:",{"type":42,"tag":170,"props":405,"children":406},{},[407,412,417,422,427],{"type":42,"tag":105,"props":408,"children":409},{},[410],{"type":48,"value":411},"the pattern being explained",{"type":42,"tag":105,"props":413,"children":414},{},[415],{"type":48,"value":416},"the strongest driver explanation and supporting evidence",{"type":42,"tag":105,"props":418,"children":419},{},[420],{"type":48,"value":421},"why it matters for the business",{"type":42,"tag":105,"props":423,"children":424},{},[425],{"type":48,"value":426},"how much confidence to place in the explanation",{"type":42,"tag":105,"props":428,"children":429},{},[430],{"type":48,"value":431},"the implication, next action, or follow-up that matters most",{"type":42,"tag":51,"props":433,"children":434},{},[435],{"type":48,"value":436},"Use $product-business-analysis when the user needs a recommendation or tradeoff decision, not just the diagnostic implication.",{"type":42,"tag":51,"props":438,"children":439},{},[440],{"type":48,"value":441},"Keep implications distinguishable from verified factual reporting so a reader can tell where evidence ends and interpretation begins. Do not claim causality from timing alone; state when an explanation is only a plausible hypothesis.",{"type":42,"tag":51,"props":443,"children":444},{},[445,447,454],{"type":48,"value":446},"Use $gather-business-context when the metric result is clear but business context is needed to interpret the ",{"type":42,"tag":448,"props":449,"children":451},"code",{"className":450},[],[452],{"type":48,"value":453},"so what",{"type":48,"value":455}," or identify realistic next actions.",{"type":42,"tag":51,"props":457,"children":458},{},[459],{"type":48,"value":460},"Use $validate-data when methodology, calculations, caveats, or the evidentiary support for the diagnostic conclusion need review before sharing.",{"type":42,"tag":51,"props":462,"children":463},{},[464],{"type":48,"value":465},"Do not treat artifact or report validation as analytical validation. Before handing off, confirm the analysis has the headline metric movement, driver contribution shares or effect sizes, source\u002Fwindow reconciliation, exact executed SQL or query references when queries were used, and caveats that would change interpretation.",{"type":42,"tag":51,"props":467,"children":468},{},[469],{"type":48,"value":470},"Pass the diagnostic substance and supporting evidence to $build-report unless the user explicitly requests an inline, chat-only, brief\u002Fno-artifact answer, asks not to create a report\u002Ffile\u002Fartifact, or selects another primary artifact. This handoff is mandatory when no explicit human waiver was given; do not infer a waiver because the user asked a direct diagnostic question or did not use the word \"report\". Let $build-report own the report surface, presentation polish, reproducibility treatment, and sharing handoff.",{"items":472,"total":583},[473,490,506,519,535,551,568],{"slug":474,"name":474,"fn":475,"description":476,"org":477,"tags":478,"stars":25,"repoUrl":26,"updatedAt":489},"analyze-account-signals","analyze account signals for sales intelligence","Use when the user wants to know what changed with one account, monitor an owner portfolio or watchlist, or rank accounts needing attention from recent evidence. Produce an evidence-backed account brief or bounded watchlist summary with recommended actions.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[479,480,483,486],{"name":20,"slug":21,"type":15},{"name":481,"slug":482,"type":15},"CRM","crm",{"name":484,"slug":485,"type":15},"Research","research",{"name":487,"slug":488,"type":15},"Sales","sales","2026-07-01T07:54:11.79288",{"slug":491,"name":491,"fn":492,"description":493,"org":494,"tags":495,"stars":25,"repoUrl":26,"updatedAt":505},"analyze-data-quality","assess data quality for analysis","Assess whether structured data, query results, dashboards, or analytical evidence are trustworthy enough to use. Use when the task is to check data quality, reconcile conflicting sources or metric definitions, or decide whether evidence is safe to cite.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[496,499,502],{"name":497,"slug":498,"type":15},"Audit","audit",{"name":500,"slug":501,"type":15},"Data Engineering","data-engineering",{"name":503,"slug":504,"type":15},"Data Quality","data-quality","2026-07-01T07:55:01.146961",{"slug":507,"name":507,"fn":508,"description":509,"org":510,"tags":511,"stars":25,"repoUrl":26,"updatedAt":518},"answers-ask-user-input","request missing context from users","Use when a small amount of missing context would materially improve the answer and tappable options plus a free-text answer can gather it efficiently.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[512,515],{"name":513,"slug":514,"type":15},"Communications","communications",{"name":516,"slug":517,"type":15},"Productivity","productivity","2026-07-14T05:43:36.096323",{"slug":520,"name":520,"fn":521,"description":522,"org":523,"tags":524,"stars":25,"repoUrl":26,"updatedAt":534},"apollo","prospect and enrich leads with Apollo","Use only when a focused Sales workflow has selected a present and connected Apollo connector, or the user explicitly asks for Apollo prospecting, enrichment, Company Details, records, sequences, or outbound planning. Apply Apollo v2-specific behavior only after verifying app version 2.0.0 or later.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[525,527,530,533],{"name":526,"slug":520,"type":15},"Apollo",{"name":528,"slug":529,"type":15},"Lead Enrichment","lead-enrichment",{"name":531,"slug":532,"type":15},"Prospecting","prospecting",{"name":487,"slug":488,"type":15},"2026-07-14T05:43:34.800076",{"slug":498,"name":498,"fn":536,"description":537,"org":538,"tags":539,"stars":25,"repoUrl":26,"updatedAt":550},"audit product flows and user journeys","Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[540,541,544,547],{"name":497,"slug":498,"type":15},{"name":542,"slug":543,"type":15},"Design","design",{"name":545,"slug":546,"type":15},"Product Management","product-management",{"name":548,"slug":549,"type":15},"UX Design","ux-design","2026-07-01T07:54:30.613428",{"slug":552,"name":552,"fn":553,"description":554,"org":555,"tags":556,"stars":25,"repoUrl":26,"updatedAt":567},"build-business-case","build customer-led business cases and ROI","Review commercial proposals and build customer-led business cases, ROI or value models, pricing or investment rationales, executive summaries, and customer-ready value stories tied to a customer, workflow, initiative, or decision.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[557,560,563,566],{"name":558,"slug":559,"type":15},"Content Creation","content-creation",{"name":561,"slug":562,"type":15},"Finance","finance",{"name":564,"slug":565,"type":15},"Financial Modeling","financial-modeling",{"name":487,"slug":488,"type":15},"2026-07-01T07:54:02.779003",{"slug":569,"name":569,"fn":570,"description":571,"org":572,"tags":573,"stars":25,"repoUrl":26,"updatedAt":582},"build-competitive-brief","build competitive briefs and battlecards","Use when the user wants a competitor or vendor comparison, market-landscape analysis, battlecard, objection package, positioning brief, or account-specific competitive view. Produce an evidence-backed comparison, guidance, and brief, using supplied materials, connected research, and public evidence when appropriate.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[574,577,580,581],{"name":575,"slug":576,"type":15},"Competitive Intelligence","competitive-intelligence",{"name":578,"slug":579,"type":15},"Marketing","marketing",{"name":484,"slug":485,"type":15},{"name":487,"slug":488,"type":15},"2026-07-01T07:54:13.073252",43,{"items":585,"total":786},[586,607,630,647,663,682,699,713,729,743,755,770],{"slug":587,"name":587,"fn":588,"description":589,"org":590,"tags":591,"stars":604,"repoUrl":605,"updatedAt":606},"prior-auth-packet-builder","build healthcare prior authorization packets","Build a concise prior authorization packet from local case files and payer policy docs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[592,595,598,601],{"name":593,"slug":594,"type":15},"Documents","documents",{"name":596,"slug":597,"type":15},"Healthcare","healthcare",{"name":599,"slug":600,"type":15},"Insurance","insurance",{"name":602,"slug":603,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":608,"name":608,"fn":609,"description":610,"org":611,"tags":612,"stars":627,"repoUrl":628,"updatedAt":629},"aspnet-core","build ASP.NET Core web applications","Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[613,616,618,621,624],{"name":614,"slug":615,"type":15},".NET","dotnet",{"name":617,"slug":608,"type":15},"ASP.NET Core",{"name":619,"slug":620,"type":15},"Blazor","blazor",{"name":622,"slug":623,"type":15},"C#","csharp",{"name":625,"slug":626,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":631,"name":631,"fn":632,"description":633,"org":634,"tags":635,"stars":627,"repoUrl":628,"updatedAt":646},"chatgpt-apps","build ChatGPT Apps SDK applications","Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[636,639,642,645],{"name":637,"slug":638,"type":15},"Apps SDK","apps-sdk",{"name":640,"slug":641,"type":15},"ChatGPT","chatgpt",{"name":643,"slug":644,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":648,"name":648,"fn":649,"description":650,"org":651,"tags":652,"stars":627,"repoUrl":628,"updatedAt":662},"cli-creator","build CLIs from API docs","Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read\u002Fwrite commands, return stable JSON, manage auth, and pair with a companion skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[653,656,659],{"name":654,"slug":655,"type":15},"API Development","api-development",{"name":657,"slug":658,"type":15},"CLI","cli",{"name":660,"slug":661,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":664,"name":664,"fn":665,"description":666,"org":667,"tags":668,"stars":627,"repoUrl":628,"updatedAt":681},"cloudflare-deploy","deploy projects 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":8},[669,672,675,678],{"name":670,"slug":671,"type":15},"Cloudflare","cloudflare",{"name":673,"slug":674,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":676,"slug":677,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":679,"slug":680,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":683,"name":683,"fn":684,"description":685,"org":686,"tags":687,"stars":627,"repoUrl":628,"updatedAt":698},"define-goal","define and set measurable project goals","Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[688,689,692,695],{"name":516,"slug":517,"type":15},{"name":690,"slug":691,"type":15},"Project Management","project-management",{"name":693,"slug":694,"type":15},"Strategy","strategy",{"name":696,"slug":697,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":700,"name":700,"fn":701,"description":702,"org":703,"tags":704,"stars":627,"repoUrl":628,"updatedAt":712},"figma","translate Figma designs into code","Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[705,706,708,711],{"name":542,"slug":543,"type":15},{"name":707,"slug":700,"type":15},"Figma",{"name":709,"slug":710,"type":15},"Frontend","frontend",{"name":643,"slug":644,"type":15},"2026-04-12T05:06:47.939943",{"slug":714,"name":714,"fn":715,"description":716,"org":717,"tags":718,"stars":627,"repoUrl":628,"updatedAt":728},"figma-code-connect-components","connect Figma designs to code components","Connects Figma design components to code components using Code Connect mapping tools. Use when user says \"code connect\", \"connect this component to code\", \"map this component\", \"link component to code\", \"create code connect mapping\", or wants to establish mappings between Figma designs and code implementations. For canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[719,720,723,724,725],{"name":542,"slug":543,"type":15},{"name":721,"slug":722,"type":15},"Design System","design-system",{"name":707,"slug":700,"type":15},{"name":709,"slug":710,"type":15},{"name":726,"slug":727,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":730,"name":730,"fn":731,"description":732,"org":733,"tags":734,"stars":627,"repoUrl":628,"updatedAt":742},"figma-create-design-system-rules","generate design system rules from Figma","Generates custom design system rules for the user's codebase. Use when user says \"create design system rules\", \"generate rules for my project\", \"set up design rules\", \"customize design system guidelines\", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[735,736,737,740,741],{"name":542,"slug":543,"type":15},{"name":721,"slug":722,"type":15},{"name":738,"slug":739,"type":15},"Documentation","documentation",{"name":707,"slug":700,"type":15},{"name":709,"slug":710,"type":15},"2026-05-16T06:07:47.821474",{"slug":744,"name":744,"fn":745,"description":746,"org":747,"tags":748,"stars":627,"repoUrl":628,"updatedAt":754},"figma-implement-design","translate Figma designs into application code","Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions \"implement design\", \"generate code\", \"implement component\", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[749,750,751,752,753],{"name":542,"slug":543,"type":15},{"name":707,"slug":700,"type":15},{"name":709,"slug":710,"type":15},{"name":726,"slug":727,"type":15},{"name":625,"slug":626,"type":15},"2026-05-16T06:07:40.583615",{"slug":756,"name":756,"fn":757,"description":758,"org":759,"tags":760,"stars":627,"repoUrl":628,"updatedAt":769},"hatch-pet","create animated pets for Codex","Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[761,764,765,768],{"name":762,"slug":763,"type":15},"Animation","animation",{"name":660,"slug":661,"type":15},{"name":766,"slug":767,"type":15},"Creative","creative",{"name":542,"slug":543,"type":15},"2026-05-02T05:31:48.48485",{"slug":771,"name":771,"fn":772,"description":773,"org":774,"tags":775,"stars":627,"repoUrl":628,"updatedAt":785},"imagegen","generate and edit raster images","Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG\u002Fvector\u002Fcode-native assets, extending an established icon or logo system, or building the visual directly in HTML\u002FCSS\u002Fcanvas.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[776,777,778,781,784],{"name":766,"slug":767,"type":15},{"name":542,"slug":543,"type":15},{"name":779,"slug":780,"type":15},"Image Generation","image-generation",{"name":782,"slug":783,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675]