[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X2TF6C1F7D3SC03A4VJSG8":3,"skill-same:01M6X2TF6C1F7D3SC03A4VJSG8":89},{"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":34,"publishedAt":55,"linkOnly":56,"markdownContent":57,"markdownBody":58,"frontMatter":59,"refName":68,"commitSha":69,"skillDirectory":70,"forksCount":14,"repositoryHtmlUrl":71,"repositoryHomepageUrl":72,"ownerHtmlUrl":73,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":74,"install":75,"resources":88},"01M6X2TF6C1F7D3SC03A4VJSG8","data-storytelling",null,"Translates data analysis into clear narratives and recommendations that non-technical audiences can act on. Use when presenting analysis results, writing data-driven reports, creating executive summaries from dashboards, or when data needs to be communicated as a decision rather than as numbers.","projectious-work\u002Fprocesskit","projectious-work","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F263889726?v=4","01M6N97TJJ118WQ35CHRV8RD0E","projectious.work","01M6N97TPWJPF0BMKYQ4PBY5W8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.23.1\u002Fcontext\u002Fskills\u002Fdocuments\u002Fdata-storytelling\u002FSKILL.md",[18,23,26,31],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",{"categoryNo":32,"categoryName":33,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000036","内容创作者",[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54],"data","storytelling","data storytelling","reports","when","data-driven","summaries","v1","can","writing data","as","writing","use","results","technical","work","decision","analysis","documents","data analysis","2026-11-10 10:12:30",false,"---\nname: data-storytelling\ndescription: |\n  Translates data analysis into clear narratives and recommendations that non-technical audiences can act on. Use when presenting analysis results, writing data-driven reports, creating executive summaries from dashboards, or when data needs to be communicated as a decision rather than as numbers.\nmetadata:\n  processkit:\n    apiVersion: processkit.projectious.work\u002Fv1\n    id: SKILL-data-storytelling\n    version: \"1.0.0\"\n    created: 2026-04-08T00:00:00Z\n    category: documents\n    layer: 2\n---\n\n# Data Storytelling\n\n## Intro\n\nData storytelling is the discipline of turning analysis into\ndecisions. Numbers alone rarely change behavior — context, narrative,\nand a clear recommendation do. A data story answers: what happened,\nwhy it matters, and what to do next. The analyst's job is not to\npresent data; it is to reduce the decision cost for the audience.\n\n## Overview\n\n### The data story structure\n\nEvery data communication follows this arc:\n\n```\nSituation → Complication → Insight → Recommendation → Action\n```\n\n- **Situation** — what the world looks like (baseline, context)\n- **Complication** — what changed or what problem emerged\n- **Insight** — what the data reveals about why, or what it implies\n- **Recommendation** — what should happen as a result\n- **Action** — who does what by when\n\nThis is the Minto Pyramid adapted for data: answer first, support\nsecond. The most common mistake is reversing the order — building\nto the conclusion instead of leading with it.\n\n### Lead with the finding, not the method\n\n**Bad (method-first):**\n> \"I pulled the last 90 days of session data from the analytics\n> platform, joined it with the conversion events table, and\n> filtered for users in the onboarding cohort. After controlling\n> for device type, I found...\"\n\n**Good (finding-first):**\n> \"Mobile onboarding conversions dropped 23% in Q1. The root cause\n> is a single screen — the account verification step — where 61%\n> of mobile users abandon. Here's what we should do.\"\n\nThe method belongs in an appendix, not in the lede. Executives\nand stakeholders need the finding; analysts need the method.\n\n### Choosing the right visual\n\n| Data relationship | Best chart | Avoid |\n|---|---|---|\n| Trend over time | Line chart | Bar chart for many points |\n| Category comparison | Bar chart (horizontal for long labels) | Pie chart |\n| Part-to-whole | Stacked bar, treemap | Pie with >4 slices |\n| Distribution | Histogram, box plot | Line chart |\n| Correlation | Scatter plot | Line chart (implies causation) |\n| Single big number | Bold number + context | Chart (overly complex) |\n\n**The \"so what\" test:** every chart should have a title that states\nthe finding, not the topic. \"Revenue by Region\" is a topic;\n\"APAC Revenue Is Growing 3× Faster Than Other Regions\" is a finding.\n\n### Writing the narrative\n\n**Executive summary format:**\n```\n**Bottom line:** [One sentence — the most important finding]\n\n**Evidence:**\n- [Finding 1] — [significance\u002Fmagnitude]\n- [Finding 2] — [significance\u002Fmagnitude]\n\n**Recommendation:**\n- [Specific action] — **owner:** [name], **by:** [date]\n\n**Context:** [1-2 sentences on methodology and data source, for\ncredibility — not detail]\n```\n\n**Slide narrative format** (one insight per slide):\n- Title: the finding (claim, not topic)\n- Chart: the evidence\n- Annotation: the key number called out directly on the chart\n- Caption: the implication (\"This suggests we should...\")\n- Footer: data source and date range\n\n**Report format** (for longer analysis):\n```markdown\n# [Report Title] — [Date Range] — [Prepared by]\n\n## Summary (read this first)\n[3-5 bullets, each a finding + implication]\n\n## Key findings\n\n### Finding 1: [Title — a claim]\n[Chart or table]\n[2-3 sentences interpreting the chart]\n[Implication]\n\n### Finding 2: [Title]\n...\n\n## Recommendations\n| Recommendation | Expected impact | Owner | Timeline |\n|---|---|---|---|\n| [Action] | [Metric change] | [Name] | [Date] |\n\n## Methodology\n[Source, date range, definitions, caveats]\n```\n\n### Making numbers meaningful\n\nContext transforms numbers:\n\n**Raw number:** \"Users completed 4,200 tasks last month.\"  \n**With comparison:** \"Users completed 4,200 tasks last month, up 18% from the prior month.\"  \n**With benchmark:** \"Users completed 4,200 tasks — roughly 3.5 tasks per active user, vs. our target of 5.\"  \n**With implication:** \"At the current completion rate, we'll hit our Q2 target of 20K tasks if growth holds.\"\n\nAlways answer: compared to what? Is this good or bad? What does\nthis mean for the decision at hand?\n\n### Handling uncertainty\n\nData stories must acknowledge their limits:\n- Name the confidence level for projections: \"Based on the last 3 months, we estimate...\"\n- Surface data quality issues: \"This metric excludes mobile app events, which represent ~15% of sessions\"\n- Distinguish correlation from causation: \"This is associated with higher retention — we have not established causation\"\n\nAcknowledging uncertainty builds credibility; hiding it destroys it\nwhen discovered.\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Building to the conclusion instead of leading with it.** Audiences who have not yet heard the finding cannot follow a long setup. Lead with the recommendation or the most important finding, then provide the supporting evidence. \"Revenue is at risk if we don't fix onboarding — here's why\" beats three paragraphs of context before the punchline.\n- **Using chart titles that describe the chart instead of stating the finding.** \"Revenue by Quarter\" tells the reader what to look at; \"Revenue Growth Stalled in Q3 for the First Time in Two Years\" tells them what to conclude. Every chart title should be a complete sentence that states the finding — not a label.\n- **Presenting percentages without the base.** \"Conversion improved by 50%\" means nothing without the base — going from 2% to 3% and from 20% to 30% are very different outcomes. Always include the denominator: \"from 2% to 3% (N=12,000 sessions).\"\n- **Using precision to signal confidence that isn't there.** Reporting \"23.47% conversion rate\" instead of \"~23%\" implies a precision the data probably does not warrant. Match significant figures to the actual certainty of the measurement; over-precision undermines credibility with sophisticated audiences.\n- **Presenting data without a recommendation.** A report that describes what happened but doesn't say what to do leaves all the decision work to the audience. The analyst who understands the data is better positioned to recommend the next action than the executive who just received it. Always end with a specific recommendation and owner.\n- **Treating association as causation.** Showing that users who use feature X retain better does not prove that feature X causes retention. Correlation is common; causation is hard to establish. Distinguish \"users who do X have 20% higher retention\" from \"X drives retention.\" Use causal language only when the analysis actually establishes it.\n- **Overloading a single slide or page with multiple findings.** A slide with three charts and six bullets gives the audience nothing to focus on. One finding per slide, one key number called out, one implication. If more findings need to be presented, use more slides — not more density per slide.\n\n## Full reference\n\n### Annotation patterns for charts\n\n- **Highlight the key data point** with a contrasting color or bold label\n- **Add a reference line** for targets, averages, or prior periods\n- **Annotate inflection points** with what happened: \"Price increase announced\"\n- **Call out the key number** in large text near the most important data point\n- Keep all other chart elements muted (light gray grid, thin axes)\n\n### Handling missing data\n\nWhen data is incomplete:\n1. State what is missing explicitly\n2. Explain the impact on the finding (minor \u002F may affect conclusion \u002F invalidates analysis)\n3. Recommend what data collection would fill the gap\n\nNever silently exclude data that would change the conclusion.\n\n### Statistical significance in business contexts\n\nBusiness audiences rarely need p-values. Translate:\n- \"This is statistically significant at p \u003C 0.05 with n=10,000\" →\n  \"We're highly confident this is a real effect, not random noise, given the large sample\"\n- \"Confidence interval: 18-26%\" →\n  \"We estimate the true value is between 18% and 26% — our best point estimate is 22%\"\n\n### Linking to processkit context\n\nSave data stories in `context\u002Fartifacts\u002F`:\n- `context\u002Fartifacts\u002Fanalysis-[topic]-[date].md`\n\nLink to the WorkItem or Decision that this analysis informed. If the\nanalysis produced a recommendation, create a WorkItem for the action\nand link the analysis as a reference.\n","# Data Storytelling\n\n## Intro\n\nData storytelling is the discipline of turning analysis into\ndecisions. Numbers alone rarely change behavior — context, narrative,\nand a clear recommendation do. A data story answers: what happened,\nwhy it matters, and what to do next. The analyst's job is not to\npresent data; it is to reduce the decision cost for the audience.\n\n## Overview\n\n### The data story structure\n\nEvery data communication follows this arc:\n\n```\nSituation → Complication → Insight → Recommendation → Action\n```\n\n- **Situation** — what the world looks like (baseline, context)\n- **Complication** — what changed or what problem emerged\n- **Insight** — what the data reveals about why, or what it implies\n- **Recommendation** — what should happen as a result\n- **Action** — who does what by when\n\nThis is the Minto Pyramid adapted for data: answer first, support\nsecond. The most common mistake is reversing the order — building\nto the conclusion instead of leading with it.\n\n### Lead with the finding, not the method\n\n**Bad (method-first):**\n> \"I pulled the last 90 days of session data from the analytics\n> platform, joined it with the conversion events table, and\n> filtered for users in the onboarding cohort. After controlling\n> for device type, I found...\"\n\n**Good (finding-first):**\n> \"Mobile onboarding conversions dropped 23% in Q1. The root cause\n> is a single screen — the account verification step — where 61%\n> of mobile users abandon. Here's what we should do.\"\n\nThe method belongs in an appendix, not in the lede. Executives\nand stakeholders need the finding; analysts need the method.\n\n### Choosing the right visual\n\n| Data relationship | Best chart | Avoid |\n|---|---|---|\n| Trend over time | Line chart | Bar chart for many points |\n| Category comparison | Bar chart (horizontal for long labels) | Pie chart |\n| Part-to-whole | Stacked bar, treemap | Pie with >4 slices |\n| Distribution | Histogram, box plot | Line chart |\n| Correlation | Scatter plot | Line chart (implies causation) |\n| Single big number | Bold number + context | Chart (overly complex) |\n\n**The \"so what\" test:** every chart should have a title that states\nthe finding, not the topic. \"Revenue by Region\" is a topic;\n\"APAC Revenue Is Growing 3× Faster Than Other Regions\" is a finding.\n\n### Writing the narrative\n\n**Executive summary format:**\n```\n**Bottom line:** [One sentence — the most important finding]\n\n**Evidence:**\n- [Finding 1] — [significance\u002Fmagnitude]\n- [Finding 2] — [significance\u002Fmagnitude]\n\n**Recommendation:**\n- [Specific action] — **owner:** [name], **by:** [date]\n\n**Context:** [1-2 sentences on methodology and data source, for\ncredibility — not detail]\n```\n\n**Slide narrative format** (one insight per slide):\n- Title: the finding (claim, not topic)\n- Chart: the evidence\n- Annotation: the key number called out directly on the chart\n- Caption: the implication (\"This suggests we should...\")\n- Footer: data source and date range\n\n**Report format** (for longer analysis):\n```markdown\n# [Report Title] — [Date Range] — [Prepared by]\n\n## Summary (read this first)\n[3-5 bullets, each a finding + implication]\n\n## Key findings\n\n### Finding 1: [Title — a claim]\n[Chart or table]\n[2-3 sentences interpreting the chart]\n[Implication]\n\n### Finding 2: [Title]\n...\n\n## Recommendations\n| Recommendation | Expected impact | Owner | Timeline |\n|---|---|---|---|\n| [Action] | [Metric change] | [Name] | [Date] |\n\n## Methodology\n[Source, date range, definitions, caveats]\n```\n\n### Making numbers meaningful\n\nContext transforms numbers:\n\n**Raw number:** \"Users completed 4,200 tasks last month.\"  \n**With comparison:** \"Users completed 4,200 tasks last month, up 18% from the prior month.\"  \n**With benchmark:** \"Users completed 4,200 tasks — roughly 3.5 tasks per active user, vs. our target of 5.\"  \n**With implication:** \"At the current completion rate, we'll hit our Q2 target of 20K tasks if growth holds.\"\n\nAlways answer: compared to what? Is this good or bad? What does\nthis mean for the decision at hand?\n\n### Handling uncertainty\n\nData stories must acknowledge their limits:\n- Name the confidence level for projections: \"Based on the last 3 months, we estimate...\"\n- Surface data quality issues: \"This metric excludes mobile app events, which represent ~15% of sessions\"\n- Distinguish correlation from causation: \"This is associated with higher retention — we have not established causation\"\n\nAcknowledging uncertainty builds credibility; hiding it destroys it\nwhen discovered.\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Building to the conclusion instead of leading with it.** Audiences who have not yet heard the finding cannot follow a long setup. Lead with the recommendation or the most important finding, then provide the supporting evidence. \"Revenue is at risk if we don't fix onboarding — here's why\" beats three paragraphs of context before the punchline.\n- **Using chart titles that describe the chart instead of stating the finding.** \"Revenue by Quarter\" tells the reader what to look at; \"Revenue Growth Stalled in Q3 for the First Time in Two Years\" tells them what to conclude. Every chart title should be a complete sentence that states the finding — not a label.\n- **Presenting percentages without the base.** \"Conversion improved by 50%\" means nothing without the base — going from 2% to 3% and from 20% to 30% are very different outcomes. Always include the denominator: \"from 2% to 3% (N=12,000 sessions).\"\n- **Using precision to signal confidence that isn't there.** Reporting \"23.47% conversion rate\" instead of \"~23%\" implies a precision the data probably does not warrant. Match significant figures to the actual certainty of the measurement; over-precision undermines credibility with sophisticated audiences.\n- **Presenting data without a recommendation.** A report that describes what happened but doesn't say what to do leaves all the decision work to the audience. The analyst who understands the data is better positioned to recommend the next action than the executive who just received it. Always end with a specific recommendation and owner.\n- **Treating association as causation.** Showing that users who use feature X retain better does not prove that feature X causes retention. Correlation is common; causation is hard to establish. Distinguish \"users who do X have 20% higher retention\" from \"X drives retention.\" Use causal language only when the analysis actually establishes it.\n- **Overloading a single slide or page with multiple findings.** A slide with three charts and six bullets gives the audience nothing to focus on. One finding per slide, one key number called out, one implication. If more findings need to be presented, use more slides — not more density per slide.\n\n## Full reference\n\n### Annotation patterns for charts\n\n- **Highlight the key data point** with a contrasting color or bold label\n- **Add a reference line** for targets, averages, or prior periods\n- **Annotate inflection points** with what happened: \"Price increase announced\"\n- **Call out the key number** in large text near the most important data point\n- Keep all other chart elements muted (light gray grid, thin axes)\n\n### Handling missing data\n\nWhen data is incomplete:\n1. State what is missing explicitly\n2. Explain the impact on the finding (minor \u002F may affect conclusion \u002F invalidates analysis)\n3. Recommend what data collection would fill the gap\n\nNever silently exclude data that would change the conclusion.\n\n### Statistical significance in business contexts\n\nBusiness audiences rarely need p-values. Translate:\n- \"This is statistically significant at p \u003C 0.05 with n=10,000\" →\n  \"We're highly confident this is a real effect, not random noise, given the large sample\"\n- \"Confidence interval: 18-26%\" →\n  \"We estimate the true value is between 18% and 26% — our best point estimate is 22%\"\n\n### Linking to processkit context\n\nSave data stories in `context\u002Fartifacts\u002F`:\n- `context\u002Fartifacts\u002Fanalysis-[topic]-[date].md`\n\nLink to the WorkItem or Decision that this analysis informed. If the\nanalysis produced a recommendation, create a WorkItem for the action\nand link the analysis as a reference.\n",{"name":5,"metadata":60,"description":67},{"processkit":61},{"id":62,"layer":63,"created":64,"version":65,"category":53,"apiVersion":66},"SKILL-data-storytelling",2,1775606400000,"1.0.0","processkit.projectious.work\u002Fv1","Translates data analysis into clear narratives and recommendations that non-technical audiences can act on. Use when presenting analysis results, writing data-driven reports, creating executive summaries from dashboards, or when data needs to be communicated as a decision rather than as numbers.\n","main","4876a92620ee792aac2ac9a1a806322d8a572367","archive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.23.1\u002Fcontext\u002Fskills\u002Fdocuments\u002Fdata-storytelling","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit","https:\u002F\u002Fprojectious-work.github.io\u002Fprocesskit\u002F","https:\u002F\u002Fgithub.com\u002Fprojectious-work","2026-11-09 00:53:29",{"source":8,"skillName":5,"commands":76,"prompt":86,"zipAvailable":87},[77,80,83],{"tool":78,"command":79},"npx","npx skills add projectious-work\u002Fprocesskit --skill data-storytelling",{"tool":81,"command":82},"bunx","bunx skills add projectious-work\u002Fprocesskit --skill data-storytelling",{"tool":84,"command":85},"pnpm","pnpm dlx skills add projectious-work\u002Fprocesskit --skill data-storytelling","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.23.1\u002Fcontext\u002Fskills\u002Fdocuments\u002Fdata-storytelling\u002FSKILL.md",true,[],[90,113,133,154,171,189],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":99,"publishedAt":55},"01M6X5MTC89B4ZGXW3JVSQCPF8","skill-management","Manage Skill package manifests as v1 ontology entities.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fskill-management\u002FSKILL.md",[96],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[100,101,102,103,104,105,50,106,107,108,92,109,45,110,42,111,112],"management","skill management","create","update","package","alpha","list","manage","ontology","get","manifests","skill package","transition",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":120,"publishedAt":55},"01M6X5MCV74NHW5MEDNHZRF2C8","schema-management","Manage generated processkit schema contracts through deterministic MCP rebuild and inspection workflows.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fschema-management\u002FSKILL.md",[119],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},[100,121,122,123,124,125,105,50,126,127,107,128,129,130,109,131,132],"schema","schema management","MCP","workflows","validation","generated","rebuild","contracts","wed","deterministic","contract","mode",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":55},"01M6X5M5G6YJ96AMZGSCZJ1D13","proposition-management","Record claims, risks, beliefs, world facts, WSJF estimates, and assumptions through the Proposition interface.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fproposition-management\u002FSKILL.md",[],[100,140,141,102,103,142,105,50,143,144,145,146,109,147,148,149,150,151,152,153],"proposition","proposition management","index","log","world","record","query","creation","event","interface","updates","facts","claims","WSJF",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":55},"01M6X5KMQ83QN9M6MPWZM7344F","ontology-management","Manage generated v1 ontology entities that do not require a dedicated domain server.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fontology-management\u002FSKILL.md",[],[100,108,161,102,105,162,163,126,164,143,107,165,166,109,167,168,148,169,42,170],"ontology management","lifecycle","archive","roadmap","do","domain","iteration","keep","measurement","generic",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":55},"01M6X5KCY2DN3SM21RERSFNEBT","okf-compatibility","Import, export, and validate conformant Open Knowledge Format bundles.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fokf-compatibility\u002FSKILL.md",[],[178,179,180,181,105,182,183,184,50,185,186,187,188],"okf","compatibility","okf compatibility","validate","open","knowledge","format","export","bundles","bundle","import",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":195,"publishedAt":55},"01M6X5JA8S5PNGJVFW4EQY8T83","capability-management","Manage versioned Capability entities and their governed lifecycle.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fcapability-management\u002FSKILL.md",[],[100,196,197,102,103,142,105,162,50,106,143,198,107,145,109,168,148,149,199,112],"capability","capability management","queries","changes"]