[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6WX6807ZSSNN56PJV3RAJE1":3,"skill-same:01M6WX6807ZSSNN56PJV3RAJE1":105},{"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":68,"commitSha":69,"skillDirectory":70,"forksCount":14,"repositoryHtmlUrl":71,"repositoryHomepageUrl":72,"ownerHtmlUrl":73,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":74,"install":75,"resources":88},"01M6WX6807ZSSNN56PJV3RAJE1","id-management",null,"Generate unique entity IDs following the project's configured format. The write-side foundation that every entity-creating skill depends on. Use whenever a new entity is being created and needs an ID, or when validating an ID format, or to inspect the project's ID configuration.","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\u002Fv0.10.0\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fid-management\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","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],"id management","management","id","info","when","Existing","v1","inspect","keep","fresh","project","generate","query","foundation","use","write","work","format","sqlite","ids","2026-11-10 10:12:30",false,"---\nname: id-management\ndescription: |\n  Generate unique entity IDs following the project's configured format. The write-side foundation that every entity-creating skill depends on. Use whenever a new entity is being created and needs an ID, or when validating an ID format, or to inspect the project's ID configuration.\nmetadata:\n  processkit:\n    apiVersion: processkit.projectious.work\u002Fv1\n    id: SKILL-id-management\n    version: \"1.0.0\"\n    created: 2026-04-06T00:00:00Z\n    category: processkit\n    layer: 0\n    uses:\n      - skill: index-management\n        purpose: Query existing entities and keep the SQLite index fresh after writes.\n    provides:\n      primitives: []\n      mcp_tools: [generate_id, validate_id, list_used_ids, format_info]\n---\n\n# ID Management\n\n## Intro\n\n`id-management` is the write-side foundation alongside `index-management`.\nWhere `index-management` answers \"what entities exist?\", `id-management`\nanswers \"what should this new entity be called?\". Every skill that\ncreates a new entity calls into this one to allocate a unique ID.\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### What it provides\n\n- **`generate_id(kind, slug_text?)`** — produce a fresh, collision-free ID for the given kind\n- **`validate_id(id)`** — check if a string is a syntactically valid processkit ID and parse out its kind\u002Fbody\n- **`list_used_ids(kind?, limit?)`** — return IDs already in use (useful for diagnostics or bulk operations)\n- **`format_info()`** — return the project's ID configuration so the agent can reason about it\n\n### ID anatomy\n\nEvery processkit entity ID has the shape `\u003CPREFIX>-\u003Cbody>`:\n\n| Part      | Example                     | How it is set                         |\n|-----------|-----------------------------|---------------------------------------|\n| Prefix    | `BACK`                      | Determined by the primitive kind.     |\n| Body      | `20260409_1449-CalmFox-foo` | Generated from configuration below.  |\n\nThe body is composed of up to four axes, all configurable in\n`context\u002Fskills\u002Fid-management\u002Fconfig\u002Fsettings.toml`:\n\n| Setting          | Values           | Effect on body                              |\n|------------------|------------------|---------------------------------------------|\n| `format`         | `word` \u002F `uuid`  | Word pair (adj+noun) or UUID fragment       |\n| `word_style`     | `camel` \u002F `kebab`| `CalmFox` or `calm-fox`                     |\n| `datetime_prefix`| `true` \u002F `false` | Prepend `YYYYMMDD_HHMM` before the pair     |\n| `slug`           | `true` \u002F `false` | Append content-derived slug from title      |\n\nExample combinations:\n\n| format | word_style | datetime_prefix | slug  | Result                              |\n|--------|------------|-----------------|-------|-------------------------------------|\n| word   | camel      | true            | true  | `BACK-20260409_1449-CalmFox-fts5-search` |\n| word   | camel      | false           | true  | `BACK-CalmFox-fts5-search`          |\n| word   | kebab      | false           | false | `BACK-calm-fox`                     |\n| uuid   | —          | false           | false | `BACK-550e8400-e29b-41d4`           |\n\nDefault (no settings.toml): `word` + `kebab` + no datetime + no slug.\n\n### Workflow when creating a new entity\n\nThis is what every entity-creating skill follows internally — the agent\nrarely needs to call `generate_id` directly:\n\n1. Decide the **kind** (`WorkItem`, `LogEntry`, `DecisionRecord`, ...).\n2. Optionally provide **slug text** (e.g. the title of a WorkItem).\n3. Call `generate_id(kind, slug_text)`.\n4. The skill writes the entity file with that ID and updates the index.\n\n### When the agent calls id-management directly\n\nMost of the time, agents create entities via skills like\n`workitem-management.create_workitem` and never see `id-management`.\nDirect calls are useful when:\n\n- You need to reserve an ID before fully writing the entity (e.g. for a\n  multi-step creation flow that references its own ID in the body).\n- You want to validate an ID a human typed in.\n- You want to list all used IDs of a kind for bulk operations or audits.\n- You want to confirm what format the project is configured for.\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Hand-rolling an ID instead of calling `generate_id`.** Even if\n  the ID format looks simple (\"BACK-1234\"), do not synthesize one.\n  Generators handle collisions, prefix configuration, and project-\n  specific format overrides — hand-rolling skips all three and\n  silently produces invalid or colliding IDs.\n- **Reusing an ID from the index without re-checking.** If you\n  cached a \"next available ID\" earlier in the session, it may\n  already be in use by now. Always call `generate_id` fresh at\n  write time.\n- **Using the wrong prefix for an entity kind.** WorkItems are\n  `BACK-`, DecisionRecords are `DEC-`, LogEntries are `LOG-`, etc.\n  Calling `generate_id(kind=\"WorkItem\")` ensures the right prefix;\n  passing `kind=\"workitem\"` (lowercase) or omitting the kind may\n  produce a generic identifier the index can't categorize.\n- **Generating an ID before the entity is fully drafted.** If you\n  call `generate_id` and then abandon the entity (because the user\n  changed their mind), the generated ID is reserved but unused —\n  a \"phantom\" that pollutes the index. Generate at the moment you\n  commit to writing.\n- **Treating `generate_id` as idempotent.** It is not. Each call\n  produces a new fresh ID, even for the same kind. Don't call it\n  twice expecting the same answer.\n- **Not validating user-supplied IDs.** When the user types an ID\n  (\"delete BACK-42\"), call `validate_id` first. Free-text input\n  may have typos, wrong prefix, or be missing entirely.\n- **Skipping `format_info()` for unfamiliar projects.** Different\n  projects can override the ID format (length, separator, prefix\n  case). Before generating IDs in a new project, call\n  `format_info()` to learn the local convention rather than\n  assuming the default.\n\n## Full reference\n\n### Prefix registry\n\n| Primitive       | Prefix   |\n|-----------------|----------|\n| WorkItem        | `BACK`   |\n| LogEntry        | `LOG`    |\n| DecisionRecord  | `DEC`    |\n| Actor           | `ACTOR`  |\n| Role            | `ROLE`   |\n| Binding         | `BIND`   |\n| Scope           | `SCOPE`  |\n| Category        | `CAT`    |\n| Gate            | `GATE`   |\n| Metric          | `METRIC` |\n| Schedule        | `SCHED`  |\n| Constraint      | `CONST`  |\n| Context         | `CTX`    |\n| Discussion      | `DISC`   |\n| Process         | `PROC`   |\n| StateMachine    | `SM`     |\n| Artifact        | `ART`    |\n\nThe registry is hard-coded in `src\u002Flib\u002Fprocesskit\u002F__init__.py` (`KIND_PREFIXES`).\nAdding a new primitive kind requires adding its prefix there.\n\n### Word generation\n\nWord-based IDs are produced from a small built-in dictionary of ~60\nadjectives and ~60 nouns (~3600 base combinations per kind). The\ngenerator picks a random pair, checks for collision against the index,\nand retries up to 50 times. If exhausted, it appends a 4-hex suffix\nto guarantee uniqueness.\n\nThe dictionary lives in `src\u002Flib\u002Fprocesskit\u002Fids.py` — replace it if you\nwant a different vibe (e.g. mythological creatures, geological terms,\nproject-themed words). Custom dictionaries are on the backlog.\n\n### Slug generation\n\nWhen `id_slug = true`, a content-derived slug is appended:\n\n```\nslug_text = \"Add aibox lint command\"\n→ slug = \"add-aibox-lint\" (first 4 tokens, lowercase, kebab-case)\n```\n\nThe slug is informational — uniqueness is still carried by the word or\nUUID portion, not the slug. Two entities can have the same slug as long\nas their word\u002FUUID parts differ.\n\n### Collision avoidance\n\nThe generator queries the index for `existing_ids(kind)` and excludes\nthose before picking a new pair. This is fast (a single SQL query) and\ncorrect as long as the index is fresh. The index is kept fresh by every\nMCP server calling `index.upsert_entity()` immediately after each write.\n\nIf files have been edited outside the MCP path, run `reindex()` first.\nThe Phase 5 `aibox lint` command will detect a stale index and warn.\n\n### Idempotency\n\n`generate_id` is **not** deterministic — calling it twice produces two\ndifferent IDs. This is intentional: multiple agents working in parallel\nshould not collide on the same ID. If you need a deterministic preview\n(e.g. \"what ID would I get for this title?\"), pass a fixed\n`random.Random` to the lib function (`ids.generate_id(..., rng=...)`).\nThe MCP `generate_id` tool does not yet expose a deterministic mode.\n\n### Validation\n\n`validate_id` accepts a string and returns:\n\n```python\n{\n  \"valid\": True,\n  \"kind\": \"WorkItem\",\n  \"prefix\": \"BACK\",\n  \"body\": \"calm-fox\",\n  \"format_guess\": \"word\",\n  \"has_slug\": False,\n}\n```\n\nor:\n\n```python\n{\n  \"valid\": False,\n  \"reason\": \"no known prefix in \u003Cid>\",\n}\n```\n\nIt checks the prefix against the registry and verifies the body shape\nroughly matches a known format. It does NOT check whether the ID is\ncurrently in use — for that, use `list_used_ids` or query the index\ndirectly.\n\n### Relationship to index-management\n\nid-management is a **peer** of index-management at Layer 0, not a\nparent or child. Both are foundational. id-management has a soft\ndependency on index-management (`uses: [index-management]`) because it\nqueries the index for collision avoidance — but conceptually they cover\nopposite halves of the entity lifecycle:\n\n- **id-management** = write side (allocate identity)\n- **index-management** = read side (find what exists)\n\nEvery skill that creates entities depends on both.\n","# ID Management\n\n## Intro\n\n`id-management` is the write-side foundation alongside `index-management`.\nWhere `index-management` answers \"what entities exist?\", `id-management`\nanswers \"what should this new entity be called?\". Every skill that\ncreates a new entity calls into this one to allocate a unique ID.\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### What it provides\n\n- **`generate_id(kind, slug_text?)`** — produce a fresh, collision-free ID for the given kind\n- **`validate_id(id)`** — check if a string is a syntactically valid processkit ID and parse out its kind\u002Fbody\n- **`list_used_ids(kind?, limit?)`** — return IDs already in use (useful for diagnostics or bulk operations)\n- **`format_info()`** — return the project's ID configuration so the agent can reason about it\n\n### ID anatomy\n\nEvery processkit entity ID has the shape `\u003CPREFIX>-\u003Cbody>`:\n\n| Part      | Example                     | How it is set                         |\n|-----------|-----------------------------|---------------------------------------|\n| Prefix    | `BACK`                      | Determined by the primitive kind.     |\n| Body      | `20260409_1449-CalmFox-foo` | Generated from configuration below.  |\n\nThe body is composed of up to four axes, all configurable in\n`context\u002Fskills\u002Fid-management\u002Fconfig\u002Fsettings.toml`:\n\n| Setting          | Values           | Effect on body                              |\n|------------------|------------------|---------------------------------------------|\n| `format`         | `word` \u002F `uuid`  | Word pair (adj+noun) or UUID fragment       |\n| `word_style`     | `camel` \u002F `kebab`| `CalmFox` or `calm-fox`                     |\n| `datetime_prefix`| `true` \u002F `false` | Prepend `YYYYMMDD_HHMM` before the pair     |\n| `slug`           | `true` \u002F `false` | Append content-derived slug from title      |\n\nExample combinations:\n\n| format | word_style | datetime_prefix | slug  | Result                              |\n|--------|------------|-----------------|-------|-------------------------------------|\n| word   | camel      | true            | true  | `BACK-20260409_1449-CalmFox-fts5-search` |\n| word   | camel      | false           | true  | `BACK-CalmFox-fts5-search`          |\n| word   | kebab      | false           | false | `BACK-calm-fox`                     |\n| uuid   | —          | false           | false | `BACK-550e8400-e29b-41d4`           |\n\nDefault (no settings.toml): `word` + `kebab` + no datetime + no slug.\n\n### Workflow when creating a new entity\n\nThis is what every entity-creating skill follows internally — the agent\nrarely needs to call `generate_id` directly:\n\n1. Decide the **kind** (`WorkItem`, `LogEntry`, `DecisionRecord`, ...).\n2. Optionally provide **slug text** (e.g. the title of a WorkItem).\n3. Call `generate_id(kind, slug_text)`.\n4. The skill writes the entity file with that ID and updates the index.\n\n### When the agent calls id-management directly\n\nMost of the time, agents create entities via skills like\n`workitem-management.create_workitem` and never see `id-management`.\nDirect calls are useful when:\n\n- You need to reserve an ID before fully writing the entity (e.g. for a\n  multi-step creation flow that references its own ID in the body).\n- You want to validate an ID a human typed in.\n- You want to list all used IDs of a kind for bulk operations or audits.\n- You want to confirm what format the project is configured for.\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Hand-rolling an ID instead of calling `generate_id`.** Even if\n  the ID format looks simple (\"BACK-1234\"), do not synthesize one.\n  Generators handle collisions, prefix configuration, and project-\n  specific format overrides — hand-rolling skips all three and\n  silently produces invalid or colliding IDs.\n- **Reusing an ID from the index without re-checking.** If you\n  cached a \"next available ID\" earlier in the session, it may\n  already be in use by now. Always call `generate_id` fresh at\n  write time.\n- **Using the wrong prefix for an entity kind.** WorkItems are\n  `BACK-`, DecisionRecords are `DEC-`, LogEntries are `LOG-`, etc.\n  Calling `generate_id(kind=\"WorkItem\")` ensures the right prefix;\n  passing `kind=\"workitem\"` (lowercase) or omitting the kind may\n  produce a generic identifier the index can't categorize.\n- **Generating an ID before the entity is fully drafted.** If you\n  call `generate_id` and then abandon the entity (because the user\n  changed their mind), the generated ID is reserved but unused —\n  a \"phantom\" that pollutes the index. Generate at the moment you\n  commit to writing.\n- **Treating `generate_id` as idempotent.** It is not. Each call\n  produces a new fresh ID, even for the same kind. Don't call it\n  twice expecting the same answer.\n- **Not validating user-supplied IDs.** When the user types an ID\n  (\"delete BACK-42\"), call `validate_id` first. Free-text input\n  may have typos, wrong prefix, or be missing entirely.\n- **Skipping `format_info()` for unfamiliar projects.** Different\n  projects can override the ID format (length, separator, prefix\n  case). Before generating IDs in a new project, call\n  `format_info()` to learn the local convention rather than\n  assuming the default.\n\n## Full reference\n\n### Prefix registry\n\n| Primitive       | Prefix   |\n|-----------------|----------|\n| WorkItem        | `BACK`   |\n| LogEntry        | `LOG`    |\n| DecisionRecord  | `DEC`    |\n| Actor           | `ACTOR`  |\n| Role            | `ROLE`   |\n| Binding         | `BIND`   |\n| Scope           | `SCOPE`  |\n| Category        | `CAT`    |\n| Gate            | `GATE`   |\n| Metric          | `METRIC` |\n| Schedule        | `SCHED`  |\n| Constraint      | `CONST`  |\n| Context         | `CTX`    |\n| Discussion      | `DISC`   |\n| Process         | `PROC`   |\n| StateMachine    | `SM`     |\n| Artifact        | `ART`    |\n\nThe registry is hard-coded in `src\u002Flib\u002Fprocesskit\u002F__init__.py` (`KIND_PREFIXES`).\nAdding a new primitive kind requires adding its prefix there.\n\n### Word generation\n\nWord-based IDs are produced from a small built-in dictionary of ~60\nadjectives and ~60 nouns (~3600 base combinations per kind). The\ngenerator picks a random pair, checks for collision against the index,\nand retries up to 50 times. If exhausted, it appends a 4-hex suffix\nto guarantee uniqueness.\n\nThe dictionary lives in `src\u002Flib\u002Fprocesskit\u002Fids.py` — replace it if you\nwant a different vibe (e.g. mythological creatures, geological terms,\nproject-themed words). Custom dictionaries are on the backlog.\n\n### Slug generation\n\nWhen `id_slug = true`, a content-derived slug is appended:\n\n```\nslug_text = \"Add aibox lint command\"\n→ slug = \"add-aibox-lint\" (first 4 tokens, lowercase, kebab-case)\n```\n\nThe slug is informational — uniqueness is still carried by the word or\nUUID portion, not the slug. Two entities can have the same slug as long\nas their word\u002FUUID parts differ.\n\n### Collision avoidance\n\nThe generator queries the index for `existing_ids(kind)` and excludes\nthose before picking a new pair. This is fast (a single SQL query) and\ncorrect as long as the index is fresh. The index is kept fresh by every\nMCP server calling `index.upsert_entity()` immediately after each write.\n\nIf files have been edited outside the MCP path, run `reindex()` first.\nThe Phase 5 `aibox lint` command will detect a stale index and warn.\n\n### Idempotency\n\n`generate_id` is **not** deterministic — calling it twice produces two\ndifferent IDs. This is intentional: multiple agents working in parallel\nshould not collide on the same ID. If you need a deterministic preview\n(e.g. \"what ID would I get for this title?\"), pass a fixed\n`random.Random` to the lib function (`ids.generate_id(..., rng=...)`).\nThe MCP `generate_id` tool does not yet expose a deterministic mode.\n\n### Validation\n\n`validate_id` accepts a string and returns:\n\n```python\n{\n  \"valid\": True,\n  \"kind\": \"WorkItem\",\n  \"prefix\": \"BACK\",\n  \"body\": \"calm-fox\",\n  \"format_guess\": \"word\",\n  \"has_slug\": False,\n}\n```\n\nor:\n\n```python\n{\n  \"valid\": False,\n  \"reason\": \"no known prefix in \u003Cid>\",\n}\n```\n\nIt checks the prefix against the registry and verifies the body shape\nroughly matches a known format. It does NOT check whether the ID is\ncurrently in use — for that, use `list_used_ids` or query the index\ndirectly.\n\n### Relationship to index-management\n\nid-management is a **peer** of index-management at Layer 0, not a\nparent or child. Both are foundational. id-management has a soft\ndependency on index-management (`uses: [index-management]`) because it\nqueries the index for collision avoidance — but conceptually they cover\nopposite halves of the entity lifecycle:\n\n- **id-management** = write side (allocate identity)\n- **index-management** = read side (find what exists)\n\nEvery skill that creates entities depends on both.\n",{"name":5,"metadata":49,"description":67},{"processkit":50},{"id":51,"uses":52,"layer":14,"created":56,"version":57,"category":58,"provides":59,"apiVersion":66},"SKILL-id-management",[53],{"skill":54,"purpose":55},"index-management","Query existing entities and keep the SQLite index fresh after writes.",1775433600000,"1.0.0","processkit",{"mcp_tools":60,"primitives":65},[61,62,63,64],"generate_id","validate_id","list_used_ids","format_info",[],"processkit.projectious.work\u002Fv1","Generate unique entity IDs following the project's configured format. The write-side foundation that every entity-creating skill depends on. Use whenever a new entity is being created and needs an ID, or when validating an ID format, or to inspect the project's ID configuration.\n","main","4876a92620ee792aac2ac9a1a806322d8a572367","archive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.10.0\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fid-management","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":76,"prompt":86,"zipAvailable":87},[77,80,83],{"tool":78,"command":79},"npx","npx skills add projectious-work\u002Fprocesskit --skill id-management",{"tool":81,"command":82},"bunx","bunx skills add projectious-work\u002Fprocesskit --skill id-management",{"tool":84,"command":85},"pnpm","pnpm dlx skills add projectious-work\u002Fprocesskit --skill id-management","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.10.0\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fid-management\u002FSKILL.md",true,[89,95,99],{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"mcp\u002Fmcp-config.json","REFERENCE","参考文档",198,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.10.0\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fid-management\u002Fmcp\u002Fmcp-config.json",{"path":96,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":97,"sourceHtmlUrl":98},"mcp\u002FSERVER.md",2014,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.10.0\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fid-management\u002Fmcp\u002FSERVER.md",{"path":100,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":103,"sourceHtmlUrl":104},"mcp\u002Fserver.py","SCRIPT","脚本",7163,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.10.0\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fid-management\u002Fmcp\u002Fserver.py",[106,113,120,126,147,167],{"skillNo":107,"name":108,"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":109,"categories":110,"keywords":111,"publishedAt":112},"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":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":119,"publishedAt":112},"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":121,"name":122,"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":123,"categories":124,"keywords":125,"publishedAt":112},"01M76650NN4T8P241021NBR64S","standard-agent-building","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-agent-building\u002FSKILL.md",[],[],{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":133,"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",[132],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[25,134,135,30,136,137,40,138,139,140,141,142,128,143,144,145,146],"skill management","ontology","create","as","transition","get","manage","update","alpha","list","package","skill package","manifests",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":154,"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",[153],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[155,156,25,157,158,159,160,161,162,163,164,165,40,139,140,142,166],"schema","schema management","contract","rebuild","contracts","workflows","wed","generated","MCP","validation","deterministic","mode",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"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",[],[174,25,175,176,136,177,178,179,40,139,180,181,141,182,142,183,184,36,185,186],"proposition management","proposition","interface","claims","record","world","creation","event","WSJF","index","updates","facts","log"]