[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X1D3KQCNNMP02K5V9HSHE4":3,"skill-same:01M6X1D3KQCNNMP02K5V9HSHE4":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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":62,"commitSha":63,"skillDirectory":64,"forksCount":14,"repositoryHtmlUrl":65,"repositoryHomepageUrl":66,"ownerHtmlUrl":67,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":68,"install":69,"resources":82},"01M6X1D3KQCNNMP02K5V9HSHE4","research-with-confidence",null,"Investigates a question systematically before answering — verifying claims through sources, distinguishing known facts from inferences, and calibrating expressed confidence to actual certainty. Use when asked to research a topic, verify a claim, evaluate a technology, or answer a question where accuracy matters more than speed.","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\u002Fv0.22.0\u002Fcontext\u002Fskills\u002Fproduct\u002Fresearch-with-confidence\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"research","research with confidence","with","when","evaluate","accuracy","claims","v1","facts","more","answer","sources","speed","technology","claim","use","question","work","verify","product","2026-11-10 10:12:30",false,"---\nname: research-with-confidence\ndescription: |\n  Investigates a question systematically before answering — verifying claims through sources, distinguishing known facts from inferences, and calibrating expressed confidence to actual certainty. Use when asked to research a topic, verify a claim, evaluate a technology, or answer a question where accuracy matters more than speed.\nmetadata:\n  processkit:\n    apiVersion: processkit.projectious.work\u002Fv1\n    id: SKILL-research-with-confidence\n    version: \"1.0.0\"\n    created: 2026-04-08T00:00:00Z\n    category: product\n    layer: 2\n    commands:\n      - name: pk-research\n        args: \"research question or topic\"\n        description: \"Research a topic with explicit confidence labelling on all claims.\"\n---\n\n# Research with Confidence\n\n## Intro\n\nThe default failure mode for AI agents is overconfidence: stating a\nplausible-sounding answer without checking it. This skill enforces\na discipline: gather before claiming, distinguish facts from\ninferences, and express uncertainty honestly. The goal is not\nhesitancy — it is calibration. Confident where warranted; explicit\nabout gaps where not.\n\n## Overview\n\n### The research protocol\n\nApply this sequence before answering any factual question:\n\n1. **Clarify the question** — What exactly is being asked? What\n   does \"right answer\" look like? What would make the answer useful\n   versus technically correct but not helpful?\n\n2. **Inventory what you already know** — Before searching, write\n   down what you know and how confident you are. Mark uncertain\n   items as hypothesis, not fact.\n\n3. **Identify what you don't know** — List the gaps. Be specific:\n   \"I don't know the current version number\" is better than \"I need\n   to check this.\"\n\n4. **Gather from authoritative sources** — Prioritize: primary\n   sources (official docs, original research, direct measurements)\n   over secondary (articles, summaries, Stack Overflow). For each\n   claim, note the source.\n\n5. **Synthesize with uncertainty labels** — Present findings with\n   explicit confidence levels (see below). State what is confirmed,\n   what is inferred, and what remains unknown.\n\n6. **Surface the residual uncertainty** — End with a clear statement\n   of what you verified, what you couldn't verify, and what the\n   user should validate themselves if the stakes are high.\n\n### Confidence levels\n\nLabel claims explicitly when the stakes matter:\n\n| Label | Meaning | Example |\n|---|---|---|\n| **Confirmed** | Verified against a primary source in this session | \"Confirmed: Python 3.12 was released October 2, 2023 (python.org)\" |\n| **Likely** | Consistent with multiple secondary sources or strong inference from first principles | \"Likely: this API is rate-limited to 100 req\u002Fmin based on the docs\" |\n| **Possible** | One source, or plausible inference, not verified | \"Possible: the library uses lazy evaluation here — I haven't confirmed in source\" |\n| **Unknown** | Not established — do not present as fact | \"Unknown: whether this behavior applies to the v2 API endpoint\" |\n\nNever present a \"Possible\" or \"Unknown\" as \"Confirmed\". Resist the\nurge to fill gaps with confident-sounding guesses.\n\n### Distinguishing types of claims\n\nDifferent claims need different verification approaches:\n\n**Factual \u002F current state** (library version, API behavior, pricing):\n- Must be verified against primary sources\n- Has a shelf life — note when the information was gathered\n- Example: \"As of April 2026, the latest stable release is...\"\n\n**Conceptual \u002F structural** (how a system works, design patterns):\n- Can be reasoned from first principles + verified against docs\n- Less time-sensitive, more stable\n- Example: \"JWT tokens work by encoding a signed payload...\"\n\n**Comparative \u002F evaluative** (A vs B, which is better):\n- Requires defining the evaluation criteria explicitly\n- Different answers for different contexts — state the context\n- Example: \"For read-heavy workloads under 1M requests\u002Fday, Postgres is typically preferred because...\"\n\n**Predictive** (what will happen, what will work):\n- Highest uncertainty category — present as estimate with reasoning\n- Example: \"Based on current trajectory, I'd estimate...\"\n\n### Red flags to pause and verify\n\nStop and check before asserting when:\n\n- The claim involves a specific version number, date, or price\n- The claim is about a library or API that has changed recently\n- The claim contradicts something the user has said\n- The claim is in a domain where you know your training data may be outdated\n- The claim sounds exactly right without any caveats — that's often when it's wrong\n\nThis skill also provides the `\u002Fresearch-with-confidence-investigate` slash command for direct invocation — see `commands\u002Fresearch-with-confidence-investigate.md`.\n\n### Structuring the output\n\n```\n## Findings: [Question]\n\n**Summary:** [1-2 sentence answer at the right confidence level]\n\n**Confirmed:**\n- [Claim] (source: [where you verified])\n- [Claim] (source: [where you verified])\n\n**Likely \u002F inferred:**\n- [Claim] (reasoning: [why you think this])\n\n**Unknown \u002F not verified:**\n- [Gap] — [what the user would need to check to fill it]\n\n**Note:** This research was conducted on [date]. [X] may have changed\nsince then — verify against [source] if currency matters.\n```\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Presenting inferences as confirmed facts.** The most common research failure: stating a plausible-sounding claim without checking it. Before finalizing any factual claim, ask: \"Did I actually verify this in a source, or am I inferring it from general knowledge?\" Label accordingly.\n- **Citing sources without checking whether the source confirms the claim.** Attaching a URL to a claim is not verification — the URL must actually support the specific claim. A document that discusses a topic tangentially does not confirm a specific fact from it. Read the source; don't cite by proximity.\n- **Not dating time-sensitive information.** API behavior, library versions, pricing, and company policies change. Any claim in these categories must be dated: \"As of [month year]...\" If you cannot establish when the information was current, say so.\n- **Treating absence of contradicting information as confirmation.** Not finding evidence against a claim is not the same as finding evidence for it. If you searched and found nothing disconfirming, report it as \"no contradicting evidence found\" — not as \"confirmed.\"\n- **Skipping the residual uncertainty summary.** Research that ends with a conclusion without noting what was not verified gives the user false confidence. Always end with: what was confirmed, what could not be confirmed, and what the user should validate independently if stakes are high.\n- **Stopping research as soon as the first plausible answer appears.** A quick hit on a credible-looking source feels like a complete answer but often isn't. At minimum, check whether a second source agrees, whether the source is primary, and whether the claim is still current.\n- **Expressing calibrated uncertainty in ways that sound like hedging.** \"It's possible that maybe perhaps...\" reads as unhelpful vagueness. Use specific labels (\"Likely\", \"Confirmed\", \"Unknown\") with brief reasoning, not stacked qualifiers. Honesty about uncertainty is valuable; vague waffling is not.\n\n## Full reference\n\n### Research tools and when to use them\n\n| Tool | Best for |\n|---|---|\n| Official documentation | Version-specific facts, API behavior, configuration |\n| Primary research papers | Scientific claims, benchmark data |\n| GitHub repo source code | Actual behavior vs. documented behavior |\n| GitHub issues \u002F PRs | Known bugs, recent changes not yet in docs |\n| Changelog \u002F CHANGELOG.md | What changed in which version |\n| Stack Overflow | Common usage patterns, community-known gotchas |\n| Web search | Current events, recent releases, pricing |\n\n### Cross-referencing checklist\n\nBefore presenting research findings:\n- [ ] Each claim has a source label (or is marked as inference)\n- [ ] Time-sensitive claims are dated\n- [ ] The most important claims are verified against primary sources\n- [ ] Contradictions between sources are noted and reasoned about\n- [ ] What I don't know is explicitly listed\n\n### Handling conflicting sources\n\nWhen two authoritative sources disagree:\n1. Note both sources and their positions\n2. Check publication date — prefer more recent\n3. Check which is closer to primary (official docs > blog post)\n4. If still conflicting, present both and note the conflict\n5. Do not silently pick one — the conflict is itself useful information\n","# Research with Confidence\n\n## Intro\n\nThe default failure mode for AI agents is overconfidence: stating a\nplausible-sounding answer without checking it. This skill enforces\na discipline: gather before claiming, distinguish facts from\ninferences, and express uncertainty honestly. The goal is not\nhesitancy — it is calibration. Confident where warranted; explicit\nabout gaps where not.\n\n## Overview\n\n### The research protocol\n\nApply this sequence before answering any factual question:\n\n1. **Clarify the question** — What exactly is being asked? What\n   does \"right answer\" look like? What would make the answer useful\n   versus technically correct but not helpful?\n\n2. **Inventory what you already know** — Before searching, write\n   down what you know and how confident you are. Mark uncertain\n   items as hypothesis, not fact.\n\n3. **Identify what you don't know** — List the gaps. Be specific:\n   \"I don't know the current version number\" is better than \"I need\n   to check this.\"\n\n4. **Gather from authoritative sources** — Prioritize: primary\n   sources (official docs, original research, direct measurements)\n   over secondary (articles, summaries, Stack Overflow). For each\n   claim, note the source.\n\n5. **Synthesize with uncertainty labels** — Present findings with\n   explicit confidence levels (see below). State what is confirmed,\n   what is inferred, and what remains unknown.\n\n6. **Surface the residual uncertainty** — End with a clear statement\n   of what you verified, what you couldn't verify, and what the\n   user should validate themselves if the stakes are high.\n\n### Confidence levels\n\nLabel claims explicitly when the stakes matter:\n\n| Label | Meaning | Example |\n|---|---|---|\n| **Confirmed** | Verified against a primary source in this session | \"Confirmed: Python 3.12 was released October 2, 2023 (python.org)\" |\n| **Likely** | Consistent with multiple secondary sources or strong inference from first principles | \"Likely: this API is rate-limited to 100 req\u002Fmin based on the docs\" |\n| **Possible** | One source, or plausible inference, not verified | \"Possible: the library uses lazy evaluation here — I haven't confirmed in source\" |\n| **Unknown** | Not established — do not present as fact | \"Unknown: whether this behavior applies to the v2 API endpoint\" |\n\nNever present a \"Possible\" or \"Unknown\" as \"Confirmed\". Resist the\nurge to fill gaps with confident-sounding guesses.\n\n### Distinguishing types of claims\n\nDifferent claims need different verification approaches:\n\n**Factual \u002F current state** (library version, API behavior, pricing):\n- Must be verified against primary sources\n- Has a shelf life — note when the information was gathered\n- Example: \"As of April 2026, the latest stable release is...\"\n\n**Conceptual \u002F structural** (how a system works, design patterns):\n- Can be reasoned from first principles + verified against docs\n- Less time-sensitive, more stable\n- Example: \"JWT tokens work by encoding a signed payload...\"\n\n**Comparative \u002F evaluative** (A vs B, which is better):\n- Requires defining the evaluation criteria explicitly\n- Different answers for different contexts — state the context\n- Example: \"For read-heavy workloads under 1M requests\u002Fday, Postgres is typically preferred because...\"\n\n**Predictive** (what will happen, what will work):\n- Highest uncertainty category — present as estimate with reasoning\n- Example: \"Based on current trajectory, I'd estimate...\"\n\n### Red flags to pause and verify\n\nStop and check before asserting when:\n\n- The claim involves a specific version number, date, or price\n- The claim is about a library or API that has changed recently\n- The claim contradicts something the user has said\n- The claim is in a domain where you know your training data may be outdated\n- The claim sounds exactly right without any caveats — that's often when it's wrong\n\nThis skill also provides the `\u002Fresearch-with-confidence-investigate` slash command for direct invocation — see `commands\u002Fresearch-with-confidence-investigate.md`.\n\n### Structuring the output\n\n```\n## Findings: [Question]\n\n**Summary:** [1-2 sentence answer at the right confidence level]\n\n**Confirmed:**\n- [Claim] (source: [where you verified])\n- [Claim] (source: [where you verified])\n\n**Likely \u002F inferred:**\n- [Claim] (reasoning: [why you think this])\n\n**Unknown \u002F not verified:**\n- [Gap] — [what the user would need to check to fill it]\n\n**Note:** This research was conducted on [date]. [X] may have changed\nsince then — verify against [source] if currency matters.\n```\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Presenting inferences as confirmed facts.** The most common research failure: stating a plausible-sounding claim without checking it. Before finalizing any factual claim, ask: \"Did I actually verify this in a source, or am I inferring it from general knowledge?\" Label accordingly.\n- **Citing sources without checking whether the source confirms the claim.** Attaching a URL to a claim is not verification — the URL must actually support the specific claim. A document that discusses a topic tangentially does not confirm a specific fact from it. Read the source; don't cite by proximity.\n- **Not dating time-sensitive information.** API behavior, library versions, pricing, and company policies change. Any claim in these categories must be dated: \"As of [month year]...\" If you cannot establish when the information was current, say so.\n- **Treating absence of contradicting information as confirmation.** Not finding evidence against a claim is not the same as finding evidence for it. If you searched and found nothing disconfirming, report it as \"no contradicting evidence found\" — not as \"confirmed.\"\n- **Skipping the residual uncertainty summary.** Research that ends with a conclusion without noting what was not verified gives the user false confidence. Always end with: what was confirmed, what could not be confirmed, and what the user should validate independently if stakes are high.\n- **Stopping research as soon as the first plausible answer appears.** A quick hit on a credible-looking source feels like a complete answer but often isn't. At minimum, check whether a second source agrees, whether the source is primary, and whether the claim is still current.\n- **Expressing calibrated uncertainty in ways that sound like hedging.** \"It's possible that maybe perhaps...\" reads as unhelpful vagueness. Use specific labels (\"Likely\", \"Confirmed\", \"Unknown\") with brief reasoning, not stacked qualifiers. Honesty about uncertainty is valuable; vague waffling is not.\n\n## Full reference\n\n### Research tools and when to use them\n\n| Tool | Best for |\n|---|---|\n| Official documentation | Version-specific facts, API behavior, configuration |\n| Primary research papers | Scientific claims, benchmark data |\n| GitHub repo source code | Actual behavior vs. documented behavior |\n| GitHub issues \u002F PRs | Known bugs, recent changes not yet in docs |\n| Changelog \u002F CHANGELOG.md | What changed in which version |\n| Stack Overflow | Common usage patterns, community-known gotchas |\n| Web search | Current events, recent releases, pricing |\n\n### Cross-referencing checklist\n\nBefore presenting research findings:\n- [ ] Each claim has a source label (or is marked as inference)\n- [ ] Time-sensitive claims are dated\n- [ ] The most important claims are verified against primary sources\n- [ ] Contradictions between sources are noted and reasoned about\n- [ ] What I don't know is explicitly listed\n\n### Handling conflicting sources\n\nWhen two authoritative sources disagree:\n1. Note both sources and their positions\n2. Check publication date — prefer more recent\n3. Check which is closer to primary (official docs > blog post)\n4. If still conflicting, present both and note the conflict\n5. Do not silently pick one — the conflict is itself useful information\n",{"name":5,"metadata":49,"description":61},{"processkit":50},{"id":51,"layer":52,"created":53,"version":54,"category":43,"commands":55,"apiVersion":60},"SKILL-research-with-confidence",2,1775606400000,"1.0.0",[56],{"args":57,"name":58,"description":59},"research question or topic","pk-research","Research a topic with explicit confidence labelling on all claims.","processkit.projectious.work\u002Fv1","Investigates a question systematically before answering — verifying claims through sources, distinguishing known facts from inferences, and calibrating expressed confidence to actual certainty. Use when asked to research a topic, verify a claim, evaluate a technology, or answer a question where accuracy matters more than speed.\n","main","4876a92620ee792aac2ac9a1a806322d8a572367","archive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.22.0\u002Fcontext\u002Fskills\u002Fproduct\u002Fresearch-with-confidence","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit","https:\u002F\u002Fprojectious-work.github.io\u002Fprocesskit\u002F","https:\u002F\u002Fgithub.com\u002Fprojectious-work","2026-11-11 23:24:18",{"source":8,"skillName":5,"commands":70,"prompt":80,"zipAvailable":81},[71,74,77],{"tool":72,"command":73},"npx","npx skills add projectious-work\u002Fprocesskit --skill research-with-confidence",{"tool":75,"command":76},"bunx","bunx skills add projectious-work\u002Fprocesskit --skill research-with-confidence",{"tool":78,"command":79},"pnpm","pnpm dlx skills add projectious-work\u002Fprocesskit --skill research-with-confidence","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.22.0\u002Fcontext\u002Fskills\u002Fproduct\u002Fresearch-with-confidence\u002FSKILL.md",true,[83],{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"commands\u002Fpk-research.md","REFERENCE","参考文档",185,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.22.0\u002Fcontext\u002Fskills\u002Fproduct\u002Fresearch-with-confidence\u002Fcommands\u002Fpk-research.md",[90,114,134,153,170,188],{"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":44},"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",[100,101,102,103,104,105,41,106,107,108,92,109,110,111,31,112,113],"management","skill management","create","update","package","alpha","list","manage","ontology","get","as","manifests","skill package","transition",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":121,"publishedAt":44},"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",[120],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},[100,122,123,124,125,126,105,41,127,128,107,129,130,131,109,132,133],"schema","schema management","MCP","workflows","validation","generated","rebuild","contracts","wed","deterministic","contract","mode",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":44},"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",[],[100,141,142,102,103,143,105,41,144,145,146,147,109,148,149,150,151,32,30,152],"proposition","proposition management","index","log","world","record","query","creation","event","interface","updates","WSJF",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":44},"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",[],[100,108,160,102,105,161,162,127,163,144,107,164,165,109,166,167,149,168,31,169],"ontology management","lifecycle","archive","roadmap","do","domain","iteration","keep","measurement","generic",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":44},"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",[],[177,178,179,180,105,181,182,183,41,184,185,186,187],"okf","compatibility","okf compatibility","validate","open","knowledge","format","export","bundles","bundle","import",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":194,"publishedAt":44},"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",[],[100,195,196,102,103,143,105,161,41,106,144,197,107,146,109,167,149,150,198,113],"capability","capability management","queries","changes"]