[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6WWMTKBG2VRHY5SGRDWC55V":3,"skill-same:01M6WWMTKBG2VRHY5SGRDWC55V":117},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":72,"commitSha":73,"skillDirectory":74,"forksCount":14,"repositoryHtmlUrl":75,"repositoryHomepageUrl":76,"ownerHtmlUrl":77,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":78,"install":79,"resources":92},"01M6WWMTKBG2VRHY5SGRDWC55V","release-audit",null,"Detect-only pre-release validation sweep over the processkit content tree.\nWalks entity files, SKILL.md definitions, MCP server tools, and\ncross-references, then emits a single human-readable report with\nERROR \u002F WARN \u002F INFO counts. Use when the user invokes `\u002Fpk-release-audit`,\nbefore tagging a release, or any time you need a comprehensive structural\nhealth check beyond what pk-doctor covers. Detect-only; never modifies any\nfile under `context\u002F`.","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\u002Fskills\u002Fprocesskit\u002Frelease-audit\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"release","audit","release audit","drift","when","you","error","structural","human","time","structure","info","MCP","references","files","only","never","work","server","mcp server","2026-11-10 10:12:30",false,"---\nname: release-audit\ndescription: |\n  Detect-only pre-release validation sweep over the processkit content tree.\n  Walks entity files, SKILL.md definitions, MCP server tools, and\n  cross-references, then emits a single human-readable report with\n  ERROR \u002F WARN \u002F INFO counts. Use when the user invokes `\u002Fpk-release-audit`,\n  before tagging a release, or any time you need a comprehensive structural\n  health check beyond what pk-doctor covers. Detect-only; never modifies any\n  file under `context\u002F`.\nmetadata:\n  processkit:\n    apiVersion: processkit.projectious.work\u002Fv2\n    id: SKILL-release-audit\n    version: \"1.0.0\"\n    created: 2026-04-26T00:00:00Z\n    category: processkit\n    layer: 3\n    uses:\n      - skill: pk-doctor\n        purpose: Complementary health check — pk-doctor covers schema\u002Fdrift\u002Fmigration checks; release-audit covers entity frontmatter, skill structure, MCP tool annotations, and cross-references.\n    commands:\n      - name: pk-release-audit\n        args: \"[--repo-root=\u003Cpath>] [--tree=context|src-context|both]\"\n        description: \"Run the pre-release validation sweep and print a single report.\"\n---\n\n# release-audit\n\n## Intro\n\n`\u002Fpk-release-audit` is the structural correctness sweep you run before\ntagging a processkit release. It answers: \"are all entity files, skill\ndefinitions, MCP server tools, and cross-references internally consistent?\"\nwithout modifying any file.\n\nThe skill complements `pk-doctor`: doctor covers schema validation, drift\nbetween `context\u002F` and `src\u002Fcontext\u002F`, and pending migrations; release-audit\ncovers entity frontmatter correctness, SKILL.md structural requirements, MCP\ntool annotation completeness, and `uses:` cross-reference resolution.\n\nExit code is `0` if there are no ERRORs (WARNs are permitted), `1` if any\nERROR is found. This makes it suitable as a blocking CI gate before `git tag`.\n\n## Overview\n\n### Invocation\n\n```\n\u002Fpk-release-audit                       # detect-only; all four checks; report to stdout\nuv run --script context\u002Fskills\u002Fprocesskit\u002Frelease-audit\u002Fscripts\u002Frelease_audit.py\nuv run --script ...\u002Frelease_audit.py --repo-root=\u002Fpath\u002Fto\u002Frepo\nuv run --script ...\u002Frelease_audit.py --tree=src-context\nuv run --script ...\u002Frelease_audit.py --tree=both\n```\n\nExit code `0` = clean (0 ERRORs). Exit code `1` = at least one ERROR found.\nThe default `context` tree is the live dogfood\u002Fproject tree. `src-context`\naudits the shipped release deliverable tree under `src\u002Fcontext\u002F` and does\nnot warn when dogfood-only entity directories such as `workitems\u002F` or\n`decisions\u002F` are absent.\n\n### The four checks\n\n1. **`entity_files`** — walks every selected tree's `\u003Cdir>\u002F*.md` for the registered\n   entity directories (`workitems`, `decisions`, `logs`, `artifacts`, `actors`,\n   `bindings`, `scopes`, `gates`, `roles`, `migrations`, `team`, `team-members`,\n   `notes`, `discussions`). For each file verifies:\n   - YAML frontmatter is present and parseable (between `---` markers).\n   - `apiVersion: processkit.projectious.work\u002Fv2` is present.\n   - `kind:` is present and is one of the 13 registered kinds.\n   - `metadata.id` is present and matches the filename stem.\n\n2. **`skill_structure`** — walks every selected tree's `skills\u002F**\u002FSKILL.md`. For each\n   file verifies:\n   - Frontmatter has `name`, `description`,\n     `metadata.processkit.apiVersion`, `metadata.processkit.id`,\n     `metadata.processkit.version`, `metadata.processkit.category`, and\n     `metadata.processkit.layer` for processkit-category skills.\n   - Body contains the four required sections: `## Intro`, `## Overview`,\n     `## Gotchas`, `## Full reference`.\n\n3. **`mcp_annotations`** — walks every selected tree's `skills\u002F**\u002Fmcp\u002Fserver.py`.\n   For each file verifies that every `@server.tool(...)` decoration includes\n   an `annotations=ToolAnnotations(...)` argument containing all four required\n   hint keys: `readOnlyHint`, `destructiveHint`, `idempotentHint`,\n   `openWorldHint`.\n\n4. **`cross_references`** — walks every selected tree's `skills\u002F**\u002FSKILL.md` and reads\n   `metadata.processkit.uses[*].skill`. For each named skill, checks that a\n   corresponding `SKILL.md` exists at `context\u002Fskills\u002F\u003Ccategory>\u002F\u003Cname>\u002FSKILL.md`\n   (searches all category directories, not just `processkit\u002F`). ERROR per\n   unresolvable reference.\n\n### What release-audit will NEVER do\n\n- Modify any file under `context\u002F` or `src\u002Fcontext\u002F`.\n- Validate YAML schemas against `src\u002Fcontext\u002Fschemas\u002F` — that is pk-doctor's\n  `schema_filename` check.\n- Write to `context\u002Flogs\u002F` — this tool is a CLI script, not an MCP server.\n- Block on missing `context\u002Ftemplates\u002F` — the template mirror is not consulted.\n\n### Report shape\n\n```\n# pk-release-audit v1.0.0\nrepo_root: \u002Fpath\u002Fto\u002Frepo\n\n## entity_files — 0 ERROR \u002F 0 WARN \u002F 47 INFO\n  [i] BACK-20260409_1449-BoldVale-fts5-full-text-search (workitems) — OK\n\n## skill_structure — 1 ERROR \u002F 0 WARN \u002F 36 INFO\n  [E] skill.missing-section — context\u002Fskills\u002Ffoo\u002Fbar\u002FSKILL.md missing section: ## Gotchas\n\n## mcp_annotations — 0 ERROR \u002F 0 WARN \u002F 12 INFO\n  [i] skill-gate:acknowledge_contract — annotations present\n\n## cross_references — 0 ERROR \u002F 0 WARN \u002F 14 INFO\n  [i] pk-doctor → event-log — resolved\n\n## totals — 1 ERROR \u002F 0 WARN \u002F 109 INFO\n```\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Running release-audit as a replacement for pk-doctor.** The two tools\n  complement each other. Release-audit does NOT check schema conformance,\n  drift, or pending migrations. Always run both before tagging.\n- **Treating cross-reference ERRORs as false positives.** The `uses:` resolver\n  searches all `context\u002Fskills\u002F\u003Ccategory>\u002F\u003Cname>\u002FSKILL.md` paths. If a skill\n  truly exists but is in an unexpected location, the fix is to correct the\n  `uses:` entry, not to suppress the check.\n- **Fixing ERRORs by editing files directly without understanding the cause.**\n  A `metadata.id` mismatch ERROR means either the file was renamed without\n  updating the frontmatter, or the frontmatter was edited without renaming the\n  file. The correct fix depends on which copy is canonical — check git history.\n- **Running release-audit against a partial tree.** The script walks the live\n  `context\u002F` tree from the detected repo root. Running it in a worktree or\n  checkout missing some files will produce false ERRORs for every absent entity\n  directory. Use `--tree=src-context` when auditing only the shipped\n  release deliverable.\n- **Ignoring WARNs before a release.** WARNs indicate structural drift that\n  does not prevent the release but will accumulate into ERRORs in future\n  versions. Address all WARNs before a minor or major release.\n\n## Full reference\n\n### CLI contract\n\n```\nrelease_audit.py [--repo-root=PATH] [--tree=context|src-context|both]\n```\n\n| Flag | Meaning |\n|------|---------|\n| `--repo-root` | Explicit repo root path. Defaults to `git rev-parse --show-toplevel`. |\n| `--tree` | `context` audits the live tree, `src-context` audits the release deliverable tree, and `both` audits both. |\n\n### Registered entity kinds\n\n| kind | directory |\n|------|-----------|\n| `WorkItem` | `workitems\u002F` |\n| `DecisionRecord` | `decisions\u002F` |\n| `LogEntry` | `logs\u002F` |\n| `Artifact` | `artifacts\u002F` |\n| `Actor` | `actors\u002F` |\n| `Binding` | `bindings\u002F` |\n| `Scope` | `scopes\u002F` |\n| `Gate` | `gates\u002F` |\n| `Role` | `roles\u002F` |\n| `Migration` | `migrations\u002F` |\n| `TeamMember` | `team-members\u002F` |\n| `Note` | `notes\u002F` |\n| `Discussion` | `discussions\u002F` |\n\n### Required SKILL.md frontmatter fields\n\n- `name` (string)\n- `description` (string)\n- `metadata.processkit.apiVersion` (string)\n- `metadata.processkit.id` (string, must start with `SKILL-`)\n- `metadata.processkit.version` (string)\n- `metadata.processkit.category` (string)\n- `metadata.processkit.layer` (integer or null)\n\n### Required SKILL.md body sections\n\n- `## Intro`\n- `## Overview`\n- `## Gotchas`\n- `## Full reference`\n\n### Required MCP tool annotation keys\n\n- `readOnlyHint`\n- `destructiveHint`\n- `idempotentHint`\n- `openWorldHint`\n\n### Adding a check in future versions\n\n1. Add a new check function in `release_audit.py` following the\n   `run_\u003Cname>(repo_root) -> list[Finding]` pattern.\n2. Register it in `CHECKS` at the bottom of the file.\n3. Add a gotcha for that check in this SKILL.md.\n4. Mirror the updated script to `src\u002Fcontext\u002Fskills\u002Fprocesskit\u002Frelease-audit\u002Fscripts\u002F`.\n","# release-audit\n\n## Intro\n\n`\u002Fpk-release-audit` is the structural correctness sweep you run before\ntagging a processkit release. It answers: \"are all entity files, skill\ndefinitions, MCP server tools, and cross-references internally consistent?\"\nwithout modifying any file.\n\nThe skill complements `pk-doctor`: doctor covers schema validation, drift\nbetween `context\u002F` and `src\u002Fcontext\u002F`, and pending migrations; release-audit\ncovers entity frontmatter correctness, SKILL.md structural requirements, MCP\ntool annotation completeness, and `uses:` cross-reference resolution.\n\nExit code is `0` if there are no ERRORs (WARNs are permitted), `1` if any\nERROR is found. This makes it suitable as a blocking CI gate before `git tag`.\n\n## Overview\n\n### Invocation\n\n```\n\u002Fpk-release-audit                       # detect-only; all four checks; report to stdout\nuv run --script context\u002Fskills\u002Fprocesskit\u002Frelease-audit\u002Fscripts\u002Frelease_audit.py\nuv run --script ...\u002Frelease_audit.py --repo-root=\u002Fpath\u002Fto\u002Frepo\nuv run --script ...\u002Frelease_audit.py --tree=src-context\nuv run --script ...\u002Frelease_audit.py --tree=both\n```\n\nExit code `0` = clean (0 ERRORs). Exit code `1` = at least one ERROR found.\nThe default `context` tree is the live dogfood\u002Fproject tree. `src-context`\naudits the shipped release deliverable tree under `src\u002Fcontext\u002F` and does\nnot warn when dogfood-only entity directories such as `workitems\u002F` or\n`decisions\u002F` are absent.\n\n### The four checks\n\n1. **`entity_files`** — walks every selected tree's `\u003Cdir>\u002F*.md` for the registered\n   entity directories (`workitems`, `decisions`, `logs`, `artifacts`, `actors`,\n   `bindings`, `scopes`, `gates`, `roles`, `migrations`, `team`, `team-members`,\n   `notes`, `discussions`). For each file verifies:\n   - YAML frontmatter is present and parseable (between `---` markers).\n   - `apiVersion: processkit.projectious.work\u002Fv2` is present.\n   - `kind:` is present and is one of the 13 registered kinds.\n   - `metadata.id` is present and matches the filename stem.\n\n2. **`skill_structure`** — walks every selected tree's `skills\u002F**\u002FSKILL.md`. For each\n   file verifies:\n   - Frontmatter has `name`, `description`,\n     `metadata.processkit.apiVersion`, `metadata.processkit.id`,\n     `metadata.processkit.version`, `metadata.processkit.category`, and\n     `metadata.processkit.layer` for processkit-category skills.\n   - Body contains the four required sections: `## Intro`, `## Overview`,\n     `## Gotchas`, `## Full reference`.\n\n3. **`mcp_annotations`** — walks every selected tree's `skills\u002F**\u002Fmcp\u002Fserver.py`.\n   For each file verifies that every `@server.tool(...)` decoration includes\n   an `annotations=ToolAnnotations(...)` argument containing all four required\n   hint keys: `readOnlyHint`, `destructiveHint`, `idempotentHint`,\n   `openWorldHint`.\n\n4. **`cross_references`** — walks every selected tree's `skills\u002F**\u002FSKILL.md` and reads\n   `metadata.processkit.uses[*].skill`. For each named skill, checks that a\n   corresponding `SKILL.md` exists at `context\u002Fskills\u002F\u003Ccategory>\u002F\u003Cname>\u002FSKILL.md`\n   (searches all category directories, not just `processkit\u002F`). ERROR per\n   unresolvable reference.\n\n### What release-audit will NEVER do\n\n- Modify any file under `context\u002F` or `src\u002Fcontext\u002F`.\n- Validate YAML schemas against `src\u002Fcontext\u002Fschemas\u002F` — that is pk-doctor's\n  `schema_filename` check.\n- Write to `context\u002Flogs\u002F` — this tool is a CLI script, not an MCP server.\n- Block on missing `context\u002Ftemplates\u002F` — the template mirror is not consulted.\n\n### Report shape\n\n```\n# pk-release-audit v1.0.0\nrepo_root: \u002Fpath\u002Fto\u002Frepo\n\n## entity_files — 0 ERROR \u002F 0 WARN \u002F 47 INFO\n  [i] BACK-20260409_1449-BoldVale-fts5-full-text-search (workitems) — OK\n\n## skill_structure — 1 ERROR \u002F 0 WARN \u002F 36 INFO\n  [E] skill.missing-section — context\u002Fskills\u002Ffoo\u002Fbar\u002FSKILL.md missing section: ## Gotchas\n\n## mcp_annotations — 0 ERROR \u002F 0 WARN \u002F 12 INFO\n  [i] skill-gate:acknowledge_contract — annotations present\n\n## cross_references — 0 ERROR \u002F 0 WARN \u002F 14 INFO\n  [i] pk-doctor → event-log — resolved\n\n## totals — 1 ERROR \u002F 0 WARN \u002F 109 INFO\n```\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Running release-audit as a replacement for pk-doctor.** The two tools\n  complement each other. Release-audit does NOT check schema conformance,\n  drift, or pending migrations. Always run both before tagging.\n- **Treating cross-reference ERRORs as false positives.** The `uses:` resolver\n  searches all `context\u002Fskills\u002F\u003Ccategory>\u002F\u003Cname>\u002FSKILL.md` paths. If a skill\n  truly exists but is in an unexpected location, the fix is to correct the\n  `uses:` entry, not to suppress the check.\n- **Fixing ERRORs by editing files directly without understanding the cause.**\n  A `metadata.id` mismatch ERROR means either the file was renamed without\n  updating the frontmatter, or the frontmatter was edited without renaming the\n  file. The correct fix depends on which copy is canonical — check git history.\n- **Running release-audit against a partial tree.** The script walks the live\n  `context\u002F` tree from the detected repo root. Running it in a worktree or\n  checkout missing some files will produce false ERRORs for every absent entity\n  directory. Use `--tree=src-context` when auditing only the shipped\n  release deliverable.\n- **Ignoring WARNs before a release.** WARNs indicate structural drift that\n  does not prevent the release but will accumulate into ERRORs in future\n  versions. Address all WARNs before a minor or major release.\n\n## Full reference\n\n### CLI contract\n\n```\nrelease_audit.py [--repo-root=PATH] [--tree=context|src-context|both]\n```\n\n| Flag | Meaning |\n|------|---------|\n| `--repo-root` | Explicit repo root path. Defaults to `git rev-parse --show-toplevel`. |\n| `--tree` | `context` audits the live tree, `src-context` audits the release deliverable tree, and `both` audits both. |\n\n### Registered entity kinds\n\n| kind | directory |\n|------|-----------|\n| `WorkItem` | `workitems\u002F` |\n| `DecisionRecord` | `decisions\u002F` |\n| `LogEntry` | `logs\u002F` |\n| `Artifact` | `artifacts\u002F` |\n| `Actor` | `actors\u002F` |\n| `Binding` | `bindings\u002F` |\n| `Scope` | `scopes\u002F` |\n| `Gate` | `gates\u002F` |\n| `Role` | `roles\u002F` |\n| `Migration` | `migrations\u002F` |\n| `TeamMember` | `team-members\u002F` |\n| `Note` | `notes\u002F` |\n| `Discussion` | `discussions\u002F` |\n\n### Required SKILL.md frontmatter fields\n\n- `name` (string)\n- `description` (string)\n- `metadata.processkit.apiVersion` (string)\n- `metadata.processkit.id` (string, must start with `SKILL-`)\n- `metadata.processkit.version` (string)\n- `metadata.processkit.category` (string)\n- `metadata.processkit.layer` (integer or null)\n\n### Required SKILL.md body sections\n\n- `## Intro`\n- `## Overview`\n- `## Gotchas`\n- `## Full reference`\n\n### Required MCP tool annotation keys\n\n- `readOnlyHint`\n- `destructiveHint`\n- `idempotentHint`\n- `openWorldHint`\n\n### Adding a check in future versions\n\n1. Add a new check function in `release_audit.py` following the\n   `run_\u003Cname>(repo_root) -> list[Finding]` pattern.\n2. Register it in `CHECKS` at the bottom of the file.\n3. Add a gotcha for that check in this SKILL.md.\n4. Mirror the updated script to `src\u002Fcontext\u002Fskills\u002Fprocesskit\u002Frelease-audit\u002Fscripts\u002F`.\n",{"name":5,"metadata":54,"description":71},{"processkit":55},{"id":56,"uses":57,"layer":61,"created":62,"version":63,"category":64,"commands":65,"apiVersion":70},"SKILL-release-audit",[58],{"skill":59,"purpose":60},"pk-doctor","Complementary health check — pk-doctor covers schema\u002Fdrift\u002Fmigration checks; release-audit covers entity frontmatter, skill structure, MCP tool annotations, and cross-references.",3,1777161600000,"1.0.0","processkit",[66],{"args":67,"name":68,"description":69},"[--repo-root=\u003Cpath>] [--tree=context|src-context|both]","pk-release-audit","Run the pre-release validation sweep and print a single report.","processkit.projectious.work\u002Fv2","Detect-only pre-release validation sweep over the processkit content tree.\nWalks entity files, SKILL.md definitions, MCP server tools, and\ncross-references, then emits a single human-readable report with\nERROR \u002F WARN \u002F INFO counts. Use when the user invokes `\u002Fpk-release-audit`,\nbefore tagging a release, or any time you need a comprehensive structural\nhealth check beyond what pk-doctor covers. Detect-only; never modifies any\nfile under `context\u002F`.\n","main","4876a92620ee792aac2ac9a1a806322d8a572367","archive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Frelease-audit","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":80,"prompt":90,"zipAvailable":91},[81,84,87],{"tool":82,"command":83},"npx","npx skills add projectious-work\u002Fprocesskit --skill release-audit",{"tool":85,"command":86},"bunx","bunx skills add projectious-work\u002Fprocesskit --skill release-audit",{"tool":88,"command":89},"pnpm","pnpm dlx skills add projectious-work\u002Fprocesskit --skill release-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Frelease-audit\u002FSKILL.md",true,[93,99,105,109,113],{"path":94,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":97,"sourceHtmlUrl":98},"commands\u002Fpk-release-audit.md","REFERENCE","参考文档",277,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Frelease-audit\u002Fcommands\u002Fpk-release-audit.md",{"path":100,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":103,"sourceHtmlUrl":104},"mcp\u002Fserver.py","SCRIPT","脚本",3685,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Frelease-audit\u002Fmcp\u002Fserver.py",{"path":106,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":107,"sourceHtmlUrl":108},"scripts\u002Frelease_audit.py",33085,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Frelease-audit\u002Fscripts\u002Frelease_audit.py",{"path":110,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":111,"sourceHtmlUrl":112},"scripts\u002Ftest_release_audit_json.py",4934,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Frelease-audit\u002Fscripts\u002Ftest_release_audit_json.py",{"path":114,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":115,"sourceHtmlUrl":116},"scripts\u002Ftest_release_audit.py",24445,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Frelease-audit\u002Fscripts\u002Ftest_release_audit.py",[118,125,132,138,161,180],{"skillNo":119,"name":120,"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":121,"categories":122,"keywords":123,"publishedAt":124},"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":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":124},"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":133,"name":134,"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":135,"categories":136,"keywords":137,"publishedAt":124},"01M76650NN4T8P241021NBR64S","standard-agent-building","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-agent-building\u002FSKILL.md",[],[],{"skillNo":139,"name":140,"nameZh":6,"description":141,"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":145,"publishedAt":49},"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",[144],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[146,147,148,149,150,151,46,152,153,154,155,156,140,157,158,159,160],"management","skill management","ontology","v1","create","as","transition","get","manage","update","alpha","list","package","skill package","manifests",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":168,"publishedAt":49},"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",[167],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[169,170,146,171,172,173,174,175,176,41,177,178,46,153,154,156,179],"schema","schema management","contract","rebuild","contracts","workflows","wed","generated","validation","deterministic","mode",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":49},"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",[],[187,146,188,189,150,190,191,192,46,153,193,194,155,195,156,196,197,198,199,200],"proposition management","proposition","interface","claims","record","world","creation","event","WSJF","index","updates","query","facts","log"]