[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NQBECSDFW08C65X0DT5QXG":3,"skill-same:01M6NQBECSDFW08C65X0DT5QXG":138},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":84,"commitSha":85,"skillDirectory":86,"forksCount":14,"repositoryHtmlUrl":87,"repositoryHomepageUrl":88,"ownerHtmlUrl":89,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":90,"install":91,"resources":104},"01M6NQBECSDFW08C65X0DT5QXG","decision-record",null,"Record decisions with rationale, alternatives, and consequences — the ADR pattern as a primitive. Use when a consequential choice is made — architecture, tooling, process, scope, trade-off. Capture WHY, not just WHAT.","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\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fdecision-record\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"decision record","decision","record","log","title","supersede","filter","scope","fresh","pattern","query","architecture","write","work","choice","why","sqlite","ids","audit","product","2026-11-10 10:12:30",false,"---\nname: decision-record\ndescription: |\n  Record decisions with rationale, alternatives, and consequences — the ADR pattern as a primitive. Use when a consequential choice is made — architecture, tooling, process, scope, trade-off. Capture WHY, not just WHAT.\nmetadata:\n  processkit:\n    apiVersion: processkit.projectious.work\u002Fv2\n    id: SKILL-decision-record\n    version: \"1.0.0\"\n    created: 2026-04-06T00:00:00Z\n    category: processkit\n    layer: 2\n    uses:\n      - skill: event-log\n        purpose: Log events to keep the audit trail accurate after every write.\n      - skill: actor-profile\n        purpose: Resolve and validate Actor IDs referenced by this skill's entities.\n      - skill: index-management\n        purpose: Query existing entities and keep the SQLite index fresh after writes.\n      - skill: id-management\n        purpose: Allocate unique entity identifiers via central ID generation.\n    provides:\n      primitives: [DecisionRecord]\n      mcp_tools: [record_decision, query_decisions, link_decision, supersede_decision]\n      templates: [decisionrecord]\n    commands:\n      - name: pk-dec\n        args: \"decision-title\"\n        description: \"Record a new architectural or product decision with the given title\"\n      - name: pk-dec-find\n        args: \"filter\"\n        description: \"Query existing decisions by keyword, status, or topic\"\n---\n\n# Decision Record\n\n## Intro\n\nA DecisionRecord captures a single consequential choice: what was decided,\nwhy, what alternatives were rejected, and what consequences are expected.\nThis is the classic **Architecture Decision Record (ADR)** pattern, promoted\nto a first-class primitive in processkit.\n\n> **MCP server.** This skill ships a self-contained MCP server at\n> `mcp\u002Fserver.py` (PEP 723 script — requires `uv` and Python ≥ 3.10 on\n> PATH). Agent harnesses reach its tools by reading a single MCP config\n> file at startup, so the contents of `mcp\u002Fmcp-config.json` must be merged\n> into the harness's MCP config and placed at the harness-specific path\n> before this skill is usable. If processkit was installed by an installer,\n> that wiring is the installer's responsibility; if processkit was\n> installed manually, the project owner must do it by hand.\n\n## Overview\n\n### When to record a decision\n\nRecord a decision when the choice:\n\n- Has consequences someone will ask about in six months (\"why are we using X?\").\n- Rules out real alternatives that took thought to reject.\n- Affects more than one file, component, or person.\n- Is the kind of thing that \"we decided in a meeting\" but nobody wrote down.\n\nDon't record: trivial choices made inside a single function, preference calls\nwith no downside, decisions already documented somewhere authoritative.\n\n### Shape\n\n```yaml\n---\napiVersion: processkit.projectious.work\u002Fv2\nkind: DecisionRecord\nmetadata:\n  id: DEC-steady-river\n  created: 2026-04-06T00:00:00Z\nspec:\n  title: \"Use official Python MCP SDK with uv PEP 723 inline dependencies\"\n  state: accepted\n  context: \"Skill MCP servers need a runtime. Options vary from zero-dep stdlib to full SDK.\"\n  decision: \"Use the official mcp Python SDK, distributed as standalone scripts with PEP 723 inline deps, launched via uv.\"\n  rationale: |\n    - The SDK is the standard; rolling our own JSON-RPC means maintaining protocol code.\n    - PEP 723 + uv eliminates per-skill env setup; uv caching amortizes first-run cost.\n    - Container already has Python ≥3.10 and uv — no base image change.\n  alternatives:\n    - option: \"Raw JSON-RPC with zero dependencies\"\n      rejected_because: \"Reimplements the protocol, fragile for complex servers.\"\n    - option: \"Pydantic-only minimal server\"\n      rejected_because: \"Kept as escape hatch if container size becomes critical; not default.\"\n  consequences: |\n    - +300-400 MB image size per skill with MCP server.\n    - First-run 5-10s for uv resolution; cached thereafter.\n    - Escape hatch documented if size becomes an issue.\n  deciders: [ACTOR-owner, ACTOR-claude]\n  decided_at: 2026-04-05T00:00:00Z\n---\n\nOptional body: longer narrative, links to the discussion, related research.\n```\n\n### Workflow\n\n1. Pick an ID: `DEC-\u003Cgenerated-id>`.\n2. Write a declarative `title` — state the decision itself, not a question.\n3. Fill in `context` (what prompted this), `decision` (the chosen option),\n   `rationale` (why).\n4. List `alternatives` with explicit `rejected_because` — this is the part\n   future-you will thank present-you for.\n5. Write `consequences` — what follows from this decision, positive and\n   negative.\n6. Set `state: proposed` if still under discussion, `accepted` if finalized.\n7. Save to `context\u002Fdecisions\u002F`.\n8. Log `decision.created`; later state changes use\n   `decision.transitioned`.\n\n### Superseding\n\nWhen a decision is replaced by a later one:\n\n1. In the **new** DecisionRecord, set `spec.supersedes: DEC-\u003Cold-id>`.\n2. In the **old** DecisionRecord, set `spec.state: superseded` and\n   `spec.superseded_by: DEC-\u003Cnew-id>`.\n3. Log `decision.superseded` referencing both IDs.\n\n**Never delete or edit the old record.** Its existence is why we can trace\nthe evolution of the decision.\n\nThis skill also provides the `\u002Fpk-dec` and `\u002Fpk-dec-find` commands for\ndirect invocation — see `commands\u002Fpk-dec.md` and\n`commands\u002Fpk-dec-find.md`.\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Recording a decision before it has actually been made.** A\n  proposal in a discussion is not a DecisionRecord. Open a Discussion\n  if reasoning is still in flight; only record when the choice is\n  settled. Recording too early creates a fictional history.\n- **Capturing WHAT but not WHY.** A DecisionRecord without rationale\n  is just a workitem in the wrong directory. The whole value of the\n  ADR pattern is the reasoning trail — what was considered, why this\n  was picked, what was rejected.\n- **Omitting the rejected alternatives.** \"We decided X\" is half a\n  decision; \"We picked X over Y and Z because …\" is a decision.\n  Future-you needs the alternatives to know whether the call still\n  holds when context changes.\n- **Editing an old DecisionRecord instead of superseding it.**\n  Decisions are immutable history. If the call needs to change, write\n  a NEW DecisionRecord with `supersedes:` pointing at the old one\n  and set the old one's state to `superseded`. Never overwrite — the\n  old reasoning is part of the audit trail.\n- **Recording trivial choices as DecisionRecords.** A DecisionRecord\n  is overhead; reserve it for choices a future agent or human will\n  ask about in six months. Variable naming inside one function is\n  not a DecisionRecord.\n- **Putting the rationale in the Discussion body instead of the\n  DecisionRecord.** Discussions are pre-decisional reasoning;\n  DecisionRecords are post-decisional summary. The rationale must\n  be copied (not linked) into the DecisionRecord so the latter is\n  self-contained when read in isolation.\n- **Hallucinating decision history when the user asks \"what did we\n  decide about X\".** Run `query_decisions` and `search_entities`\n  against the actual store before answering. Do not synthesize an\n  answer from memory; it will be wrong.\n\n## Full reference\n\n### State machine\n\nSee `src\u002Fprimitives\u002Fstate-machines\u002Fdecisionrecord.yaml`:\n\n```\nproposed → accepted → superseded (terminal)\n    ↓\n  rejected (terminal)\n```\n\n`rejected` is for decisions considered and declined — kept for history.\n`superseded` is for decisions replaced by a later one.\n\n### Full field list\n\nSee `src\u002Fprimitives\u002Fschemas\u002Fdecisionrecord.yaml`. Notable fields:\n\n- `deciders`: list of Actor IDs. Who agreed.\n- `supersedes` \u002F `superseded_by`: DEC IDs. Replacement chain.\n- `related_workitems`: BACK IDs. Work that prompted or implements the decision.\n- `decided_at`: when the decision was finalized. Distinct from\n  `metadata.created` (when the file was written).\n\n### Distinguishing decisions from discussions\n\nA **Discussion** (separate primitive) is a multi-turn conversation exploring\na question. A **DecisionRecord** is the crisp outcome. Workflow:\n\n1. Open a Discussion when a question arises.\n2. Explore, debate, research.\n3. When the group converges on an answer, write a DecisionRecord.\n4. Link the Discussion via `spec.related_discussions` (cross-reference).\n\nNot every discussion produces a decision; not every decision is preceded by\na discussion.\n\n### Writing good titles\n\nGood titles are declarative, active, and concrete:\n\n- ✓ \"Use official Python MCP SDK with uv PEP 723 inline dependencies\"\n- ✓ \"Two-repo split: aibox + processkit\"\n- ✗ \"Which MCP library to use?\" (question, not decision)\n- ✗ \"Tooling update\" (too vague)\n- ✗ \"Alice's proposal\" (credits the person, not the decision)\n\n### Consequences that are honest\n\nFuture readers trust the decision record more when you write the real\nconsequences, including the uncomfortable ones. \"Costs 300-400 MB image\nsize\" builds more credibility than \"some increase in container size.\"\n\n### Linking to workitems\n\nWhen a decision prompts work to happen, link via `spec.related_workitems`:\n\n```yaml\nspec:\n  related_workitems: [BACK-calm-fox, BACK-swift-oak]\n```\n\nThis lets queries find \"all work that implements DEC-foo\" and \"all\ndecisions that motivated BACK-bar.\"\n","# Decision Record\n\n## Intro\n\nA DecisionRecord captures a single consequential choice: what was decided,\nwhy, what alternatives were rejected, and what consequences are expected.\nThis is the classic **Architecture Decision Record (ADR)** pattern, promoted\nto a first-class primitive in processkit.\n\n> **MCP server.** This skill ships a self-contained MCP server at\n> `mcp\u002Fserver.py` (PEP 723 script — requires `uv` and Python ≥ 3.10 on\n> PATH). Agent harnesses reach its tools by reading a single MCP config\n> file at startup, so the contents of `mcp\u002Fmcp-config.json` must be merged\n> into the harness's MCP config and placed at the harness-specific path\n> before this skill is usable. If processkit was installed by an installer,\n> that wiring is the installer's responsibility; if processkit was\n> installed manually, the project owner must do it by hand.\n\n## Overview\n\n### When to record a decision\n\nRecord a decision when the choice:\n\n- Has consequences someone will ask about in six months (\"why are we using X?\").\n- Rules out real alternatives that took thought to reject.\n- Affects more than one file, component, or person.\n- Is the kind of thing that \"we decided in a meeting\" but nobody wrote down.\n\nDon't record: trivial choices made inside a single function, preference calls\nwith no downside, decisions already documented somewhere authoritative.\n\n### Shape\n\n```yaml\n---\napiVersion: processkit.projectious.work\u002Fv2\nkind: DecisionRecord\nmetadata:\n  id: DEC-steady-river\n  created: 2026-04-06T00:00:00Z\nspec:\n  title: \"Use official Python MCP SDK with uv PEP 723 inline dependencies\"\n  state: accepted\n  context: \"Skill MCP servers need a runtime. Options vary from zero-dep stdlib to full SDK.\"\n  decision: \"Use the official mcp Python SDK, distributed as standalone scripts with PEP 723 inline deps, launched via uv.\"\n  rationale: |\n    - The SDK is the standard; rolling our own JSON-RPC means maintaining protocol code.\n    - PEP 723 + uv eliminates per-skill env setup; uv caching amortizes first-run cost.\n    - Container already has Python ≥3.10 and uv — no base image change.\n  alternatives:\n    - option: \"Raw JSON-RPC with zero dependencies\"\n      rejected_because: \"Reimplements the protocol, fragile for complex servers.\"\n    - option: \"Pydantic-only minimal server\"\n      rejected_because: \"Kept as escape hatch if container size becomes critical; not default.\"\n  consequences: |\n    - +300-400 MB image size per skill with MCP server.\n    - First-run 5-10s for uv resolution; cached thereafter.\n    - Escape hatch documented if size becomes an issue.\n  deciders: [ACTOR-owner, ACTOR-claude]\n  decided_at: 2026-04-05T00:00:00Z\n---\n\nOptional body: longer narrative, links to the discussion, related research.\n```\n\n### Workflow\n\n1. Pick an ID: `DEC-\u003Cgenerated-id>`.\n2. Write a declarative `title` — state the decision itself, not a question.\n3. Fill in `context` (what prompted this), `decision` (the chosen option),\n   `rationale` (why).\n4. List `alternatives` with explicit `rejected_because` — this is the part\n   future-you will thank present-you for.\n5. Write `consequences` — what follows from this decision, positive and\n   negative.\n6. Set `state: proposed` if still under discussion, `accepted` if finalized.\n7. Save to `context\u002Fdecisions\u002F`.\n8. Log `decision.created`; later state changes use\n   `decision.transitioned`.\n\n### Superseding\n\nWhen a decision is replaced by a later one:\n\n1. In the **new** DecisionRecord, set `spec.supersedes: DEC-\u003Cold-id>`.\n2. In the **old** DecisionRecord, set `spec.state: superseded` and\n   `spec.superseded_by: DEC-\u003Cnew-id>`.\n3. Log `decision.superseded` referencing both IDs.\n\n**Never delete or edit the old record.** Its existence is why we can trace\nthe evolution of the decision.\n\nThis skill also provides the `\u002Fpk-dec` and `\u002Fpk-dec-find` commands for\ndirect invocation — see `commands\u002Fpk-dec.md` and\n`commands\u002Fpk-dec-find.md`.\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Recording a decision before it has actually been made.** A\n  proposal in a discussion is not a DecisionRecord. Open a Discussion\n  if reasoning is still in flight; only record when the choice is\n  settled. Recording too early creates a fictional history.\n- **Capturing WHAT but not WHY.** A DecisionRecord without rationale\n  is just a workitem in the wrong directory. The whole value of the\n  ADR pattern is the reasoning trail — what was considered, why this\n  was picked, what was rejected.\n- **Omitting the rejected alternatives.** \"We decided X\" is half a\n  decision; \"We picked X over Y and Z because …\" is a decision.\n  Future-you needs the alternatives to know whether the call still\n  holds when context changes.\n- **Editing an old DecisionRecord instead of superseding it.**\n  Decisions are immutable history. If the call needs to change, write\n  a NEW DecisionRecord with `supersedes:` pointing at the old one\n  and set the old one's state to `superseded`. Never overwrite — the\n  old reasoning is part of the audit trail.\n- **Recording trivial choices as DecisionRecords.** A DecisionRecord\n  is overhead; reserve it for choices a future agent or human will\n  ask about in six months. Variable naming inside one function is\n  not a DecisionRecord.\n- **Putting the rationale in the Discussion body instead of the\n  DecisionRecord.** Discussions are pre-decisional reasoning;\n  DecisionRecords are post-decisional summary. The rationale must\n  be copied (not linked) into the DecisionRecord so the latter is\n  self-contained when read in isolation.\n- **Hallucinating decision history when the user asks \"what did we\n  decide about X\".** Run `query_decisions` and `search_entities`\n  against the actual store before answering. Do not synthesize an\n  answer from memory; it will be wrong.\n\n## Full reference\n\n### State machine\n\nSee `src\u002Fprimitives\u002Fstate-machines\u002Fdecisionrecord.yaml`:\n\n```\nproposed → accepted → superseded (terminal)\n    ↓\n  rejected (terminal)\n```\n\n`rejected` is for decisions considered and declined — kept for history.\n`superseded` is for decisions replaced by a later one.\n\n### Full field list\n\nSee `src\u002Fprimitives\u002Fschemas\u002Fdecisionrecord.yaml`. Notable fields:\n\n- `deciders`: list of Actor IDs. Who agreed.\n- `supersedes` \u002F `superseded_by`: DEC IDs. Replacement chain.\n- `related_workitems`: BACK IDs. Work that prompted or implements the decision.\n- `decided_at`: when the decision was finalized. Distinct from\n  `metadata.created` (when the file was written).\n\n### Distinguishing decisions from discussions\n\nA **Discussion** (separate primitive) is a multi-turn conversation exploring\na question. A **DecisionRecord** is the crisp outcome. Workflow:\n\n1. Open a Discussion when a question arises.\n2. Explore, debate, research.\n3. When the group converges on an answer, write a DecisionRecord.\n4. Link the Discussion via `spec.related_discussions` (cross-reference).\n\nNot every discussion produces a decision; not every decision is preceded by\na discussion.\n\n### Writing good titles\n\nGood titles are declarative, active, and concrete:\n\n- ✓ \"Use official Python MCP SDK with uv PEP 723 inline dependencies\"\n- ✓ \"Two-repo split: aibox + processkit\"\n- ✗ \"Which MCP library to use?\" (question, not decision)\n- ✗ \"Tooling update\" (too vague)\n- ✗ \"Alice's proposal\" (credits the person, not the decision)\n\n### Consequences that are honest\n\nFuture readers trust the decision record more when you write the real\nconsequences, including the uncomfortable ones. \"Costs 300-400 MB image\nsize\" builds more credibility than \"some increase in container size.\"\n\n### Linking to workitems\n\nWhen a decision prompts work to happen, link via `spec.related_workitems`:\n\n```yaml\nspec:\n  related_workitems: [BACK-calm-fox, BACK-swift-oak]\n```\n\nThis lets queries find \"all work that implements DEC-foo\" and \"all\ndecisions that motivated BACK-bar.\"\n",{"name":5,"metadata":44,"description":83},{"processkit":45},{"id":46,"uses":47,"layer":60,"created":61,"version":62,"category":63,"commands":64,"provides":72,"apiVersion":82},"SKILL-decision-record",[48,51,54,57],{"skill":49,"purpose":50},"event-log","Log events to keep the audit trail accurate after every write.",{"skill":52,"purpose":53},"actor-profile","Resolve and validate Actor IDs referenced by this skill's entities.",{"skill":55,"purpose":56},"index-management","Query existing entities and keep the SQLite index fresh after writes.",{"skill":58,"purpose":59},"id-management","Allocate unique entity identifiers via central ID generation.",2,1775433600000,"1.0.0","processkit",[65,69],{"args":66,"name":67,"description":68},"decision-title","pk-dec","Record a new architectural or product decision with the given title",{"args":25,"name":70,"description":71},"pk-dec-find","Query existing decisions by keyword, status, or topic",{"mcp_tools":73,"templates":78,"primitives":80},[74,75,76,77],"record_decision","query_decisions","link_decision","supersede_decision",[79],"decisionrecord",[81],"DecisionRecord","processkit.projectious.work\u002Fv2","Record decisions with rationale, alternatives, and consequences — the ADR pattern as a primitive. Use when a consequential choice is made — architecture, tooling, process, scope, trade-off. Capture WHY, not just WHAT.\n","main","7231f100e266e30d2c1699ecde5c00602471dc3c","src\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fdecision-record","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":92,"prompt":102,"zipAvailable":103},[93,96,99],{"tool":94,"command":95},"npx","npx skills add projectious-work\u002Fprocesskit --skill decision-record",{"tool":97,"command":98},"bunx","bunx skills add projectious-work\u002Fprocesskit --skill decision-record",{"tool":100,"command":101},"pnpm","pnpm dlx skills add projectious-work\u002Fprocesskit --skill decision-record","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fdecision-record\u002FSKILL.md",true,[105,111,117,121,125,129,135],{"path":106,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":109,"sourceHtmlUrl":110},"assets\u002Fdecisionrecord.yaml","ASSET","资产文件",341,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fdecision-record\u002Fassets\u002Fdecisionrecord.yaml",{"path":112,"resourceType":113,"resourceTypeDesc":114,"sizeBytes":115,"sourceHtmlUrl":116},"commands\u002Fpk-dec-find.md","REFERENCE","参考文档",130,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fdecision-record\u002Fcommands\u002Fpk-dec-find.md",{"path":118,"resourceType":113,"resourceTypeDesc":114,"sizeBytes":119,"sourceHtmlUrl":120},"commands\u002Fpk-dec.md",133,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fdecision-record\u002Fcommands\u002Fpk-dec.md",{"path":122,"resourceType":113,"resourceTypeDesc":114,"sizeBytes":123,"sourceHtmlUrl":124},"mcp\u002Fmcp-config.json",213,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fdecision-record\u002Fmcp\u002Fmcp-config.json",{"path":126,"resourceType":113,"resourceTypeDesc":114,"sizeBytes":127,"sourceHtmlUrl":128},"mcp\u002FSERVER.md",2757,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fdecision-record\u002Fmcp\u002FSERVER.md",{"path":130,"resourceType":131,"resourceTypeDesc":132,"sizeBytes":133,"sourceHtmlUrl":134},"mcp\u002Fserver.py","SCRIPT","脚本",11663,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fdecision-record\u002Fmcp\u002Fserver.py",{"path":136,"resourceType":131,"resourceTypeDesc":132,"sizeBytes":14,"sourceHtmlUrl":137},"scripts\u002F.gitkeep","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fdecision-record\u002Fscripts\u002F.gitkeep",[139,146,153,159,186,206],{"skillNo":140,"name":141,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":145},"01M7665G2ED3624R3X93304265","standard-ui-design","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-ui-design\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":145},"01M76651QTC6W0HJ4AFW2MMR3V","standard-agent-use","Company standard for working with AI agents. Use when deciding what to delegate to agents, capturing open work, keeping agent memory or knowledge notes, improving an agent workflow, or introducing agent work in a team or for a client.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-agent-use\u002FSKILL.md",[],[],{"skillNo":154,"name":155,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":145},"01M76650NN4T8P241021NBR64S","standard-agent-building","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-agent-building\u002FSKILL.md",[],[],{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":170,"publishedAt":39},"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",[165],{"categoryNo":166,"categoryName":167,"taxonomyType":168,"taxonomyTypeDesc":169},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[171,172,173,174,175,176,32,177,178,179,180,181,161,182,183,184,185],"management","skill management","ontology","v1","create","as","transition","get","manage","update","alpha","list","package","skill package","manifests",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":193,"publishedAt":39},"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",[192],{"categoryNo":166,"categoryName":167,"taxonomyType":168,"taxonomyTypeDesc":169},[194,195,171,196,197,198,199,200,201,202,203,204,32,178,179,181,205],"schema","schema management","contract","rebuild","contracts","workflows","wed","generated","MCP","validation","deterministic","mode",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":212,"publishedAt":39},"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",[],[213,171,214,215,175,216,21,217,32,178,218,219,180,220,181,221,222,29,223,22],"proposition management","proposition","interface","claims","world","creation","event","WSJF","index","updates","facts"]