[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73568KZA5ENNVTA05J27K6H":3,"skill-same:01M73568KZA5ENNVTA05J27K6H":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M73568KZA5ENNVTA05J27K6H","productize-validate-data",null,"QA an analysis before sharing, including methodology, accuracy, calculation, visualization, and bias checks. Use when reviewing analysis for stakeholders, spot-checking SQL results, validating aggregation logic, or assessing whether conclusions are supported by the data.","itseffi\u002Fproductize","itseffi","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F15998472?v=4","01M734C5RJ7CKRTPB3FX84VZV7","Effi","01M734C5S6B7FW62ZNWYBZ9GG7",3,"MIT","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-validate-data\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: productize-validate-data\ndescription: >-\n  QA an analysis before sharing, including methodology, accuracy, calculation, visualization,\n  and bias checks. Use when reviewing analysis for stakeholders, spot-checking SQL results,\n  validating aggregation logic, or assessing whether conclusions are supported by the data.\n---\n\u003C!-- AUTO-GENERATED from SKILL.md.tmpl - do not edit directly -->\n\u003C!-- Regenerate: npm run skills:generate -->\n\n# Validate Data\n\n## Productize Preamble\n\nBefore producing the artifact, implementation step, or code change, classify the work:\n\n- **User\u002Fpersona**: founder, product leader, AI PM, AI builder, stakeholder, or mixed\u002Funknown.\n- **Product stage**: idea, validation, PMF search, growth, scale, pivot, or unknown.\n- **Artifact mode**: strategy memo, PRD, research plan, positioning, experiment, deck, roadmap, execution brief, diagnostic, or decision record.\n- **Artifact format**: Markdown for short, repo-native, diff-sensitive artifacts; self-contained HTML for long, visual, shareable, interactive, or explicitly requested artifacts.\n- **Evidence standard**: what is known, assumed, missing, and risky.\n- **Decision mode**: recommend, ask for a blocking input, or proceed with explicit assumptions.\n\nOperating rules:\n\n1. Do not produce generic product strategy filler. Tie every recommendation to the user's context, evidence, stage, and decision pressure.\n2. Separate facts from assumptions. Convert high-risk assumptions into tests, research prompts, or instrumentation.\n3. Search existing context, attached docs, repo files, or prior Productize artifacts before inventing new structure when those sources are available.\n4. Ask only for inputs that materially change the output. If the next step is obvious, proceed and state assumptions.\n5. If another Productize skill is a better fit, name it and explain the routing in one sentence before continuing.\n6. Enforce the output contract for this skill. Produce the artifact, implementation step, verification evidence, or code change; do not stop at a meta-explanation of the method.\n7. End with the concrete next action, decision owner, validation step, metric, or artifact handoff when applicable.\n8. Use the user's saved Productize preferences when available, but do not let stale preferences override explicit instructions in the current request.\n9. If you must ask a blocking question, use this compact format: `AskUserQuestion: \u003Cone question> Why it matters: \u003Cdecision it changes>`.\n10. Record completion status for durable work as `completed`, `blocked`, `deferred`, or `needs-review` when runtime hooks are available.\n\nArtifact format policy:\n\n- Default to Markdown for short notes, repo-native documentation, changelog fragments, or artifacts where clean source diffs matter.\n- Use a self-contained HTML file when the user asks for HTML, the artifact is likely to exceed about 100 lines, the reader needs diagrams\u002Ftables\u002Fcomparisons\u002Fscreenshots, the artifact is meant to be shared, or interaction\u002Fexport controls would help the user stay in the loop.\n- Route by product job first, then choose the format. Do not create a generic HTML workflow when a Productize playbook, gate, or routed skill owns the work.\n- HTML artifacts must be local-first and portable: one file, embedded CSS\u002FJS, no remote dependencies unless explicitly requested, readable without a dev server, responsive, accessible, and easy to skim.\n- Prefer semantic sections, tables, SVG diagrams, annotated code blocks, status chips, collapsible detail, and copy\u002Fexport buttons when they improve review speed. Avoid decorative complexity that hides the decision.\n- For implementation work with ambiguities, use `$implementation-notes` when the user asks for a running notes file, especially `implementation-notes.html` or `implementation-notes.md`.\n\nRuntime hooks, if available:\n\n- Use `productize-workflow start \"\u003Cuser request>\"` at the beginning of durable product work; it restores context, routes the request, records the session, and returns the required artifact contract.\n- Use `productize-workflow complete --id \u003Cid> --status completed|blocked|deferred|needs-review --artifact-type \u003Ctype> --summary \u003Csummary>` before ending durable product work; it records the artifact, saves context, and logs completion status.\n- Use `productize-update-check --strict` at the start of maintenance, setup, release, or generated-output work.\n- Use `productize-config` to read or write user\u002Fteam preferences such as persona, artifact mode, evidence threshold, or update-check policy.\n- Use `productize-session-log` to record important workflow decisions.\n- Use `productize-artifact-log` when a durable artifact is produced.\n- Use `productize-context-restore` before restarting long-running product work from scratch.\n- Use `productize-context-save` after producing a durable strategy, research, spec, or stakeholder artifact.\n- Use `productize-registry-search` or `productize-skill-router` when routing is ambiguous.\n- Use `productize-completion-status` to log whether the workflow completed, blocked, deferred, or needs review.\n\nTelemetry standard:\n\n- Keep telemetry local by default in `.productize\u002F` or `PRODUCTIZE_STATE_DIR`.\n- Log artifact type, routing decision, evidence gaps, and completion status; do not log secrets or private customer data unless the user explicitly asks for it.\n\nCurrent skill metadata:\n\n- **Skill**: `validate-data`\n- **Lifecycle**: Measure\n- **Category**: Analytics\n- **Primary artifact**: Data validation report with quality issues, methodology checks, and confidence level\n\nReview an analysis for accuracy, methodology, and potential bias before it is shared with stakeholders.\n\n## Argument Hint\n\n`\u003Canalysis to review>`\n\n## Usage\n\n```text\n\u002Fvalidate-data \u003Canalysis to review>\n```\n\nThe analysis can be a document, report, file, SQL query and results, chart, dataset, notebook, spreadsheet, or methodology summary.\n\n## Workflow\n\n### 1. Review Methodology and Assumptions\n\nCheck:\n- Question framing: whether the analysis answers the right question.\n- Data selection: source tables, files, date ranges, and inclusion criteria.\n- Population definition: who or what is included and excluded.\n- Metric definitions: whether definitions are explicit and stakeholder-compatible.\n- Baseline and comparison: whether comparison periods, cohorts, and contexts are fair.\n- Assumptions: whether assumptions are stated and defensible.\n\n### 2. Run Pre-Delivery QA\n\nReview data quality:\n- Sources are correct.\n- Data freshness and \"as of\" date are stated.\n- Time series and segments are complete.\n- Null handling is appropriate.\n- Deduplication and filters are correct.\n\nReview calculations:\n- Aggregation grain matches the analysis question.\n- Denominators are correct and non-zero.\n- Date comparisons use equal and complete periods unless caveated.\n- Join types are intentional.\n- Many-to-many joins are not inflating counts.\n- Metrics match stakeholder definitions.\n- Subtotals reconcile with totals where expected.\n\nReview reasonableness:\n- Numbers are plausible.\n- Percentages are between 0 and 100 when applicable.\n- Trends do not have unexplained jumps.\n- Results reconcile with dashboards, finance reports, or prior analyses when possible.\n- Boundary cases are sensible.\n\nReview presentation:\n- Charts use honest axes and consistent scales.\n- Titles, labels, date ranges, and units are clear.\n- Number formatting is appropriate.\n- Caveats are explicit.\n- The analysis is reproducible.\n\n### 3. Check Analytical Pitfalls\n\nLook specifically for:\n- Join explosion from many-to-many joins.\n- Survivorship bias.\n- Partial-period comparisons.\n- Denominator shifting.\n- Average of averages.\n- Timezone mismatches.\n- Selection bias in segmentation.\n- Simpson's paradox.\n- Correlation presented as causation.\n- Small sample overclaiming.\n- Outlier-distorted averages.\n- Multiple testing and cherry-picking.\n- Look-ahead bias.\n- Cherry-picked time ranges.\n\n### 4. Verify Calculations\n\nWhere possible:\n- Recalculate key numbers independently.\n- Check row counts before and after joins.\n- Confirm subtotals and percentages.\n- Verify YoY, MoM, and WoW base periods.\n- Check that filters are applied consistently.\n- Spot-check individual records or small slices.\n- Calculate the same metric two ways when feasible.\n\nFor SQL, inspect grain, joins, filters, grouping, denominator logic, and null handling. Use `sql-queries` for dialect-specific review when needed.\n\n### 5. Assess Visualizations\n\nIf charts are included, verify:\n- Bar charts start at zero.\n- Scales are consistent across comparison panels.\n- Titles accurately describe what is shown.\n- Axes, units, date ranges, and sources are visible.\n- Visual encodings do not mislead fast readers.\n- No 3D effects, unexplained truncation, or inconsistent intervals.\n\nUse `data-visualization` if chart-design guidance is needed.\n\n### 6. Evaluate Narrative and Conclusions\n\nReview whether:\n- Conclusions are directly supported by the data.\n- Alternative explanations are acknowledged.\n- Uncertainty is communicated.\n- Recommendations follow from findings.\n- Confidence level matches evidence strength.\n- Practical significance is separated from statistical significance.\n\nUse `statistical-analysis` for significance, outlier, anomaly, correlation, or sample-size concerns.\n\n### 7. Produce Confidence Assessment\n\nChoose one:\n- **Ready to share**: sound methodology, verified calculations, caveats noted.\n- **Share with noted caveats**: largely correct, but limitations must be communicated.\n- **Needs revision**: errors, methodological issues, or missing analyses should be fixed first.\n\n## Output Format\n\n```markdown\n## Validation Report\n\n### Overall Assessment: [Ready to share | Share with caveats | Needs revision]\n\n### Methodology Review\n[Findings about approach, data selection, definitions, comparison logic, and assumptions]\n\n### Issues Found\n1. [Severity: High\u002FMedium\u002FLow] [Issue description, evidence, and impact]\n\n### Calculation Spot-Checks\n- [Metric]: [Verified \u002F Discrepancy found \u002F Could not verify] - [notes]\n\n### Visualization Review\n[Chart issues or confirmation that visuals are sound]\n\n### Suggested Improvements\n1. [Improvement and why it matters]\n\n### Required Caveats for Stakeholders\n- [Caveat that must be communicated]\n```\n\n## Pitfall Reference\n\n### Join Explosion\n\nMany-to-many joins silently multiply rows and inflate counts or sums. Check row counts before and after joins, investigate unexpected increases, and use `COUNT(DISTINCT entity_id)` when counting entities through joins.\n\n### Survivorship Bias\n\nAnalyzing only current or surviving entities ignores churned, deleted, failed, or excluded entities. Ask who is missing from the dataset.\n\n### Incomplete Period Comparison\n\nDo not compare a partial week, month, or quarter to a full prior period unless explicitly caveated. Use complete periods or same-number-of-days comparisons.\n\n### Denominator Shifting\n\nRate changes are not comparable if the eligible population or active-user definition changed between periods.\n\n### Average of Averages\n\nNever average pre-computed averages when group sizes differ. Recompute from raw numerators and denominators or use weighted averages.\n\n### Timezone Mismatches\n\nStandardize timestamps before comparison and document the timezone used.\n\n### Selection Bias\n\nDo not define segments using the outcome being measured. Prefer pre-treatment characteristics.\n\n## Red Flags\n\nInvestigate:\n- Metrics changing more than 50 percent without an obvious cause.\n- Exact round-number counts or sums.\n- Rates exactly 0 percent or 100 percent.\n- Results that perfectly confirm the hypothesis.\n- Identical values across periods or segments.\n- Percentages that should sum to 100 percent but do not.\n\n## Reproducibility Standard\n\nFor non-trivial analyses, ensure the report includes:\n- Specific question.\n- Data sources and \"as of\" dates.\n- Metric and segment definitions.\n- Time period and timezone.\n- Methodology.\n- Assumptions and limitations.\n- Queries or code.\n- Caveats and known gaps.\n","\u003C!-- AUTO-GENERATED from SKILL.md.tmpl - do not edit directly -->\n\u003C!-- Regenerate: npm run skills:generate -->\n\n# Validate Data\n\n## Productize Preamble\n\nBefore producing the artifact, implementation step, or code change, classify the work:\n\n- **User\u002Fpersona**: founder, product leader, AI PM, AI builder, stakeholder, or mixed\u002Funknown.\n- **Product stage**: idea, validation, PMF search, growth, scale, pivot, or unknown.\n- **Artifact mode**: strategy memo, PRD, research plan, positioning, experiment, deck, roadmap, execution brief, diagnostic, or decision record.\n- **Artifact format**: Markdown for short, repo-native, diff-sensitive artifacts; self-contained HTML for long, visual, shareable, interactive, or explicitly requested artifacts.\n- **Evidence standard**: what is known, assumed, missing, and risky.\n- **Decision mode**: recommend, ask for a blocking input, or proceed with explicit assumptions.\n\nOperating rules:\n\n1. Do not produce generic product strategy filler. Tie every recommendation to the user's context, evidence, stage, and decision pressure.\n2. Separate facts from assumptions. Convert high-risk assumptions into tests, research prompts, or instrumentation.\n3. Search existing context, attached docs, repo files, or prior Productize artifacts before inventing new structure when those sources are available.\n4. Ask only for inputs that materially change the output. If the next step is obvious, proceed and state assumptions.\n5. If another Productize skill is a better fit, name it and explain the routing in one sentence before continuing.\n6. Enforce the output contract for this skill. Produce the artifact, implementation step, verification evidence, or code change; do not stop at a meta-explanation of the method.\n7. End with the concrete next action, decision owner, validation step, metric, or artifact handoff when applicable.\n8. Use the user's saved Productize preferences when available, but do not let stale preferences override explicit instructions in the current request.\n9. If you must ask a blocking question, use this compact format: `AskUserQuestion: \u003Cone question> Why it matters: \u003Cdecision it changes>`.\n10. Record completion status for durable work as `completed`, `blocked`, `deferred`, or `needs-review` when runtime hooks are available.\n\nArtifact format policy:\n\n- Default to Markdown for short notes, repo-native documentation, changelog fragments, or artifacts where clean source diffs matter.\n- Use a self-contained HTML file when the user asks for HTML, the artifact is likely to exceed about 100 lines, the reader needs diagrams\u002Ftables\u002Fcomparisons\u002Fscreenshots, the artifact is meant to be shared, or interaction\u002Fexport controls would help the user stay in the loop.\n- Route by product job first, then choose the format. Do not create a generic HTML workflow when a Productize playbook, gate, or routed skill owns the work.\n- HTML artifacts must be local-first and portable: one file, embedded CSS\u002FJS, no remote dependencies unless explicitly requested, readable without a dev server, responsive, accessible, and easy to skim.\n- Prefer semantic sections, tables, SVG diagrams, annotated code blocks, status chips, collapsible detail, and copy\u002Fexport buttons when they improve review speed. Avoid decorative complexity that hides the decision.\n- For implementation work with ambiguities, use `$implementation-notes` when the user asks for a running notes file, especially `implementation-notes.html` or `implementation-notes.md`.\n\nRuntime hooks, if available:\n\n- Use `productize-workflow start \"\u003Cuser request>\"` at the beginning of durable product work; it restores context, routes the request, records the session, and returns the required artifact contract.\n- Use `productize-workflow complete --id \u003Cid> --status completed|blocked|deferred|needs-review --artifact-type \u003Ctype> --summary \u003Csummary>` before ending durable product work; it records the artifact, saves context, and logs completion status.\n- Use `productize-update-check --strict` at the start of maintenance, setup, release, or generated-output work.\n- Use `productize-config` to read or write user\u002Fteam preferences such as persona, artifact mode, evidence threshold, or update-check policy.\n- Use `productize-session-log` to record important workflow decisions.\n- Use `productize-artifact-log` when a durable artifact is produced.\n- Use `productize-context-restore` before restarting long-running product work from scratch.\n- Use `productize-context-save` after producing a durable strategy, research, spec, or stakeholder artifact.\n- Use `productize-registry-search` or `productize-skill-router` when routing is ambiguous.\n- Use `productize-completion-status` to log whether the workflow completed, blocked, deferred, or needs review.\n\nTelemetry standard:\n\n- Keep telemetry local by default in `.productize\u002F` or `PRODUCTIZE_STATE_DIR`.\n- Log artifact type, routing decision, evidence gaps, and completion status; do not log secrets or private customer data unless the user explicitly asks for it.\n\nCurrent skill metadata:\n\n- **Skill**: `validate-data`\n- **Lifecycle**: Measure\n- **Category**: Analytics\n- **Primary artifact**: Data validation report with quality issues, methodology checks, and confidence level\n\nReview an analysis for accuracy, methodology, and potential bias before it is shared with stakeholders.\n\n## Argument Hint\n\n`\u003Canalysis to review>`\n\n## Usage\n\n```text\n\u002Fvalidate-data \u003Canalysis to review>\n```\n\nThe analysis can be a document, report, file, SQL query and results, chart, dataset, notebook, spreadsheet, or methodology summary.\n\n## Workflow\n\n### 1. Review Methodology and Assumptions\n\nCheck:\n- Question framing: whether the analysis answers the right question.\n- Data selection: source tables, files, date ranges, and inclusion criteria.\n- Population definition: who or what is included and excluded.\n- Metric definitions: whether definitions are explicit and stakeholder-compatible.\n- Baseline and comparison: whether comparison periods, cohorts, and contexts are fair.\n- Assumptions: whether assumptions are stated and defensible.\n\n### 2. Run Pre-Delivery QA\n\nReview data quality:\n- Sources are correct.\n- Data freshness and \"as of\" date are stated.\n- Time series and segments are complete.\n- Null handling is appropriate.\n- Deduplication and filters are correct.\n\nReview calculations:\n- Aggregation grain matches the analysis question.\n- Denominators are correct and non-zero.\n- Date comparisons use equal and complete periods unless caveated.\n- Join types are intentional.\n- Many-to-many joins are not inflating counts.\n- Metrics match stakeholder definitions.\n- Subtotals reconcile with totals where expected.\n\nReview reasonableness:\n- Numbers are plausible.\n- Percentages are between 0 and 100 when applicable.\n- Trends do not have unexplained jumps.\n- Results reconcile with dashboards, finance reports, or prior analyses when possible.\n- Boundary cases are sensible.\n\nReview presentation:\n- Charts use honest axes and consistent scales.\n- Titles, labels, date ranges, and units are clear.\n- Number formatting is appropriate.\n- Caveats are explicit.\n- The analysis is reproducible.\n\n### 3. Check Analytical Pitfalls\n\nLook specifically for:\n- Join explosion from many-to-many joins.\n- Survivorship bias.\n- Partial-period comparisons.\n- Denominator shifting.\n- Average of averages.\n- Timezone mismatches.\n- Selection bias in segmentation.\n- Simpson's paradox.\n- Correlation presented as causation.\n- Small sample overclaiming.\n- Outlier-distorted averages.\n- Multiple testing and cherry-picking.\n- Look-ahead bias.\n- Cherry-picked time ranges.\n\n### 4. Verify Calculations\n\nWhere possible:\n- Recalculate key numbers independently.\n- Check row counts before and after joins.\n- Confirm subtotals and percentages.\n- Verify YoY, MoM, and WoW base periods.\n- Check that filters are applied consistently.\n- Spot-check individual records or small slices.\n- Calculate the same metric two ways when feasible.\n\nFor SQL, inspect grain, joins, filters, grouping, denominator logic, and null handling. Use `sql-queries` for dialect-specific review when needed.\n\n### 5. Assess Visualizations\n\nIf charts are included, verify:\n- Bar charts start at zero.\n- Scales are consistent across comparison panels.\n- Titles accurately describe what is shown.\n- Axes, units, date ranges, and sources are visible.\n- Visual encodings do not mislead fast readers.\n- No 3D effects, unexplained truncation, or inconsistent intervals.\n\nUse `data-visualization` if chart-design guidance is needed.\n\n### 6. Evaluate Narrative and Conclusions\n\nReview whether:\n- Conclusions are directly supported by the data.\n- Alternative explanations are acknowledged.\n- Uncertainty is communicated.\n- Recommendations follow from findings.\n- Confidence level matches evidence strength.\n- Practical significance is separated from statistical significance.\n\nUse `statistical-analysis` for significance, outlier, anomaly, correlation, or sample-size concerns.\n\n### 7. Produce Confidence Assessment\n\nChoose one:\n- **Ready to share**: sound methodology, verified calculations, caveats noted.\n- **Share with noted caveats**: largely correct, but limitations must be communicated.\n- **Needs revision**: errors, methodological issues, or missing analyses should be fixed first.\n\n## Output Format\n\n```markdown\n## Validation Report\n\n### Overall Assessment: [Ready to share | Share with caveats | Needs revision]\n\n### Methodology Review\n[Findings about approach, data selection, definitions, comparison logic, and assumptions]\n\n### Issues Found\n1. [Severity: High\u002FMedium\u002FLow] [Issue description, evidence, and impact]\n\n### Calculation Spot-Checks\n- [Metric]: [Verified \u002F Discrepancy found \u002F Could not verify] - [notes]\n\n### Visualization Review\n[Chart issues or confirmation that visuals are sound]\n\n### Suggested Improvements\n1. [Improvement and why it matters]\n\n### Required Caveats for Stakeholders\n- [Caveat that must be communicated]\n```\n\n## Pitfall Reference\n\n### Join Explosion\n\nMany-to-many joins silently multiply rows and inflate counts or sums. Check row counts before and after joins, investigate unexpected increases, and use `COUNT(DISTINCT entity_id)` when counting entities through joins.\n\n### Survivorship Bias\n\nAnalyzing only current or surviving entities ignores churned, deleted, failed, or excluded entities. Ask who is missing from the dataset.\n\n### Incomplete Period Comparison\n\nDo not compare a partial week, month, or quarter to a full prior period unless explicitly caveated. Use complete periods or same-number-of-days comparisons.\n\n### Denominator Shifting\n\nRate changes are not comparable if the eligible population or active-user definition changed between periods.\n\n### Average of Averages\n\nNever average pre-computed averages when group sizes differ. Recompute from raw numerators and denominators or use weighted averages.\n\n### Timezone Mismatches\n\nStandardize timestamps before comparison and document the timezone used.\n\n### Selection Bias\n\nDo not define segments using the outcome being measured. Prefer pre-treatment characteristics.\n\n## Red Flags\n\nInvestigate:\n- Metrics changing more than 50 percent without an obvious cause.\n- Exact round-number counts or sums.\n- Rates exactly 0 percent or 100 percent.\n- Results that perfectly confirm the hypothesis.\n- Identical values across periods or segments.\n- Percentages that should sum to 100 percent but do not.\n\n## Reproducibility Standard\n\nFor non-trivial analyses, ensure the report includes:\n- Specific question.\n- Data sources and \"as of\" dates.\n- Metric and segment definitions.\n- Time period and timezone.\n- Methodology.\n- Assumptions and limitations.\n- Queries or code.\n- Caveats and known gaps.\n",{"name":5,"description":7},"main","f177680a573a242a81bd0a776f9681f620e6d74c","skills\u002Fproductize-validate-data",0,"https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize","https:\u002F\u002Fgithub.com\u002Fitseffi","2026-08-07 20:07:32",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add itseffi\u002Fproductize --skill productize-validate-data",{"tool":37,"command":38},"bunx","bunx skills add itseffi\u002Fproductize --skill productize-validate-data",{"tool":40,"command":41},"pnpm","pnpm dlx skills add itseffi\u002Fproductize --skill productize-validate-data","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-validate-data\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",325,"https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-validate-data\u002Fagents\u002Fopenai.yaml",[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7357QB5M87V95F82E73V2TF","workflow-memory","Maintains workflow-scoped task memory for Productize runs using .productize\u002Ftasks\u002F\u003Cname>\u002Fmemory\u002F files. Use when a task prompt provides workflow memory paths and requires the agent to read, update, compact, and promote durable context across PRD task executions. Do not use for PR review remediation, global user preferences, or programmatic event-log summarization.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-memory\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7357K97HSYEHAQTW5ZKM4CE","review-round","Performs a comprehensive code review of a PRD implementation and generates a review round directory with issue files compatible with fix-reviews. Use when reviewing implemented PRD tasks, creating a manual review round without an external provider, or performing a quality audit of code changes. Do not use for fetching reviews from external providers, fixing existing review issues, executing PRD tasks, or editing source code.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Freview-round\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7357F2NZE5NSYM2SJXEGBFZ","productize","Productize root skill for building, shipping, operating, and growing AI products inside a coding harness. Routes work across thesis framing, discovery, research, positioning, finance, decision making, requirements, design, metrics, AI-builder execution, code implementation, verification, stakeholder narratives, growth, launch, operation, and learning workflows. Use when the user wants to build a product from zero, improve an existing product, or needs product work that spans multiple lifecycle stages before code, launch, operation, or growth execution.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7357B48F8MK86EQF135FJQ6","productize-wwas","Why-What-Acceptance. Use when writing backlog items in Why-What-Acceptance format, breaking features into independent valuable work, or adding strategic context to delivery items.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-wwas\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M735783CDA9MQ0SPR9X6QZSE","productize-writing-plans","Create comprehensive implementation plans with bite-sized tasks. Use when you have requirements before touching code.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-writing-plans\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M735750V5Q6WRBX1ZFGNRMEB","productize-write-spec","Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea into a structured document, scoping goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into phases.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-write-spec\u002FSKILL.md",[],[]]