[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79A02VBQWFME6PDE1HQA2NT":3,"skill-same:01M79A02VBQWFME6PDE1HQA2NT":67},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M79A02VBQWFME6PDE1HQA2NT","policy-author",null,"Turn a plain-English governance brief into one validated runx operational policy, or tighten an existing one, with a fail-closed lint pass before it ships.","ZachDreamZ\u002Frunx","ZachDreamZ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F22769595?v=4","01M799NTP9N5VYWB4JY50MC7Y3","NexusCore","01M799NTQ1AYT8TZC0XTSEZXDJ",0,"MIT","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fpolicy-author\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: policy-author\ndescription: Turn a plain-English governance brief into one validated runx operational policy, or tighten an existing one, with a fail-closed lint pass before it ships.\nrunx:\n  category: ops\n---\n\n# Policy Author\n\nAuthor one governed runx operational policy from intent, and prove it lints.\n\nAdopting governed runx means writing an operational policy: which repos may be\ntouched, who owns which surface, which sources are trusted, what confidence is\nrequired before action, and which outcomes need a human. Written by hand that is\na long, error-prone document. This skill turns a plain-English governance brief\ninto one `runx.operational_policy.v1` proposal, or tightens an existing policy,\nand runs a fail-closed lint over it before it ships. It proposes; a human\napproves.\n\n## What this skill does\n\n1. **Read the intent.** Take the governance brief (and an existing policy when\n   tightening) and identify the target surfaces, sources, owners, and the risk\n   posture.\n2. **Draft the policy.** Produce a complete `runx.operational_policy.v1`: target\n   repos, runner binding, allowed actions, trusted sources with confidence\n   floors, owner routes, and outcome rules.\n3. **Lint fail-closed.** Run the policy checks below. Any failing check blocks\n   the proposal with the exact fix, rather than shipping a permissive policy.\n4. **Tighten, never loosen.** When given an existing policy, only propose\n   changes that narrow authority (auto-merge off, human gate on, confidence up).\n   Widening is a separate, explicit human decision.\n\n## Core principles\n\n- **Fail closed.** Unspecified means denied. A missing owner route, source rule,\n  or confidence floor is a lint error, not a permissive default.\n- **Human gate on mutation.** Any policy that allows repository mutation must set\n  `require_human_merge_gate: true` and `auto_merge: false`.\n- **Named owners.** Every target surface routes to a named owner; no orphan\n  surfaces.\n- **Bounded sources.** Each trusted source declares a minimum confidence; no\n  source admits work below its floor.\n- **Verification before close.** A source issue closes only when the outcome is\n  verified.\n\n## When to use this skill\n\n- Bootstrapping a new runx deployment that needs an operational policy.\n- Tightening an existing policy after a near-miss or an audit.\n- Onboarding a new target repo, source, or owner into an existing policy.\n\n## When not to use this skill\n\n- To widen authority (add auto-merge, drop a human gate, lower confidence). That\n  is an explicit human decision, not a generated proposal.\n- To write skill logic or graphs. This authors the governance envelope, not the\n  skills it governs.\n\n## The operational policy model\n\nThe proposal fills `runx.operational_policy.v1`:\n\n- `target_repos`: the repositories the policy may act on.\n- `runner`: the runner binding (id, kind, and required substrate, e.g. GitHub\n  Actions + scafld).\n- `allowed_actions`: the lanes permitted (e.g. `issue-intake`, `issue-to-pr`,\n  `pr-review`).\n- `sources`: trusted inbound sources, each with a `min_confidence` floor.\n- `owner_routes`: surface-to-owner routing; every surface has a named owner.\n- `outcomes`: `verification_required`, `close_source_issue`,\n  `require_human_merge_gate`, `auto_merge`.\n\n## Lint diagnostics\n\nThe fail-closed lint emits these; any error blocks the proposal:\n\n- `policy.owner.unrouted` (error): a target surface has no owner route.\n- `policy.mutation.no_human_gate` (error): mutation allowed without\n  `require_human_merge_gate: true`.\n- `policy.mutation.auto_merge_on` (error): `auto_merge` is true on a mutating\n  policy.\n- `policy.source.no_confidence_floor` (error): a source has no `min_confidence`.\n- `policy.source.floor_too_low` (warning): a confidence floor below 0.7.\n- `policy.close.before_verify` (error): `close_source_issue` set without\n  `verification_required`.\n- `policy.action.unknown` (error): an allowed action is not a known lane.\n\n## Procedure\n\n1. Validate that the brief names the governed work, the target repo or surface,\n   and the intended owner or escalation route.\n2. Extract all repos, sources, actions, owners, confidence floors, and outcome\n   rules from the brief and any existing policy.\n3. If tightening an existing policy, diff proposed changes against the current\n   grant. Flag any widened action, lower confidence floor, removed owner, or\n   removed human gate as a separate human decision.\n4. Draft the smallest complete `runx.operational_policy.v1` that allows the\n   stated work and denies everything else.\n5. Run the lint diagnostics. Any `error` finding prevents `decision: ready`.\n6. Emit the policy, lint result, rationale, blockers, and success checkpoint.\n\n## Edge cases and stop conditions\n\n- **No owner route:** return `needs_input`; an ownerless surface is never\n  governed by default.\n- **Mutation without a human gate:** return `reject` or `needs_input`; do not\n  emit a ready mutating policy without `require_human_merge_gate: true`.\n- **Auto-merge requested:** block the proposal unless the user explicitly\n  performs a separate authority-widening decision outside this skill.\n- **Unknown action lane:** return `needs_input` with the unknown action names.\n- **Source without confidence floor:** return `needs_input`; implicit trust is\n  not a policy.\n- **Conflicting owner routes:** return `needs_input` and cite the conflicting\n  surfaces and owners.\n\n## Output schema (`policy_proposal`)\n\n```yaml\ndecision: ready | needs_input | reject\npolicy:\n  schema: runx.operational_policy.v1\n  target_repos: [string]\n  runner:\n    id: string\n    kind: string\n    requires: [string]\n  allowed_actions: [string]\n  sources:\n    - provider: string\n      min_confidence: number\n  owner_routes:\n    - surface: string\n      owner: string\n  outcomes:\n    verification_required: boolean\n    close_source_issue: never | when_verified | always\n    require_human_merge_gate: boolean\n    auto_merge: boolean\nlint:\n  status: pass | fail\n  findings:\n    - id: string\n      severity: error | warning\n      message: string\nrationale: string\nblockers: [string]\nneeds_input: [string]\nsuccess_checkpoint:\n  milestone: string\n  description: string\n```\n\nA proposal with any `error` finding must have `decision: needs_input` or\n`reject`, never `ready`.\n\n## Worked example\n\nBrief: \"Govern issue intake across our three repos. GitHub issues and Sentry\nalerts. Kam owns the platform, Chong owns product. Never auto-merge; a human\napproves every merge; close the source issue only once the fix is verified.\"\n\nThe proposal binds the three repos to a GitHub-Actions + scafld runner, allows\n`issue-intake`\u002F`issue-to-pr`\u002F`pr-review`, trusts GitHub at 0.72 and Sentry at\n0.82, routes platform to Kam and product to Chong, and sets\n`require_human_merge_gate: true`, `auto_merge: false`,\n`verification_required: true`, `close_source_issue: when_verified`. The lint\npasses, so `decision: ready`.\n\n## Inputs\n\n- `governance_brief` (required): the governance intent in prose.\n- `existing_policy` (optional): a current `runx.operational_policy.v1` to tighten.\n- `target_repos` (optional): explicit repo list when not in the brief.\n- `objective` (optional): operator intent that focuses the pass.\n","# Policy Author\n\nAuthor one governed runx operational policy from intent, and prove it lints.\n\nAdopting governed runx means writing an operational policy: which repos may be\ntouched, who owns which surface, which sources are trusted, what confidence is\nrequired before action, and which outcomes need a human. Written by hand that is\na long, error-prone document. This skill turns a plain-English governance brief\ninto one `runx.operational_policy.v1` proposal, or tightens an existing policy,\nand runs a fail-closed lint over it before it ships. It proposes; a human\napproves.\n\n## What this skill does\n\n1. **Read the intent.** Take the governance brief (and an existing policy when\n   tightening) and identify the target surfaces, sources, owners, and the risk\n   posture.\n2. **Draft the policy.** Produce a complete `runx.operational_policy.v1`: target\n   repos, runner binding, allowed actions, trusted sources with confidence\n   floors, owner routes, and outcome rules.\n3. **Lint fail-closed.** Run the policy checks below. Any failing check blocks\n   the proposal with the exact fix, rather than shipping a permissive policy.\n4. **Tighten, never loosen.** When given an existing policy, only propose\n   changes that narrow authority (auto-merge off, human gate on, confidence up).\n   Widening is a separate, explicit human decision.\n\n## Core principles\n\n- **Fail closed.** Unspecified means denied. A missing owner route, source rule,\n  or confidence floor is a lint error, not a permissive default.\n- **Human gate on mutation.** Any policy that allows repository mutation must set\n  `require_human_merge_gate: true` and `auto_merge: false`.\n- **Named owners.** Every target surface routes to a named owner; no orphan\n  surfaces.\n- **Bounded sources.** Each trusted source declares a minimum confidence; no\n  source admits work below its floor.\n- **Verification before close.** A source issue closes only when the outcome is\n  verified.\n\n## When to use this skill\n\n- Bootstrapping a new runx deployment that needs an operational policy.\n- Tightening an existing policy after a near-miss or an audit.\n- Onboarding a new target repo, source, or owner into an existing policy.\n\n## When not to use this skill\n\n- To widen authority (add auto-merge, drop a human gate, lower confidence). That\n  is an explicit human decision, not a generated proposal.\n- To write skill logic or graphs. This authors the governance envelope, not the\n  skills it governs.\n\n## The operational policy model\n\nThe proposal fills `runx.operational_policy.v1`:\n\n- `target_repos`: the repositories the policy may act on.\n- `runner`: the runner binding (id, kind, and required substrate, e.g. GitHub\n  Actions + scafld).\n- `allowed_actions`: the lanes permitted (e.g. `issue-intake`, `issue-to-pr`,\n  `pr-review`).\n- `sources`: trusted inbound sources, each with a `min_confidence` floor.\n- `owner_routes`: surface-to-owner routing; every surface has a named owner.\n- `outcomes`: `verification_required`, `close_source_issue`,\n  `require_human_merge_gate`, `auto_merge`.\n\n## Lint diagnostics\n\nThe fail-closed lint emits these; any error blocks the proposal:\n\n- `policy.owner.unrouted` (error): a target surface has no owner route.\n- `policy.mutation.no_human_gate` (error): mutation allowed without\n  `require_human_merge_gate: true`.\n- `policy.mutation.auto_merge_on` (error): `auto_merge` is true on a mutating\n  policy.\n- `policy.source.no_confidence_floor` (error): a source has no `min_confidence`.\n- `policy.source.floor_too_low` (warning): a confidence floor below 0.7.\n- `policy.close.before_verify` (error): `close_source_issue` set without\n  `verification_required`.\n- `policy.action.unknown` (error): an allowed action is not a known lane.\n\n## Procedure\n\n1. Validate that the brief names the governed work, the target repo or surface,\n   and the intended owner or escalation route.\n2. Extract all repos, sources, actions, owners, confidence floors, and outcome\n   rules from the brief and any existing policy.\n3. If tightening an existing policy, diff proposed changes against the current\n   grant. Flag any widened action, lower confidence floor, removed owner, or\n   removed human gate as a separate human decision.\n4. Draft the smallest complete `runx.operational_policy.v1` that allows the\n   stated work and denies everything else.\n5. Run the lint diagnostics. Any `error` finding prevents `decision: ready`.\n6. Emit the policy, lint result, rationale, blockers, and success checkpoint.\n\n## Edge cases and stop conditions\n\n- **No owner route:** return `needs_input`; an ownerless surface is never\n  governed by default.\n- **Mutation without a human gate:** return `reject` or `needs_input`; do not\n  emit a ready mutating policy without `require_human_merge_gate: true`.\n- **Auto-merge requested:** block the proposal unless the user explicitly\n  performs a separate authority-widening decision outside this skill.\n- **Unknown action lane:** return `needs_input` with the unknown action names.\n- **Source without confidence floor:** return `needs_input`; implicit trust is\n  not a policy.\n- **Conflicting owner routes:** return `needs_input` and cite the conflicting\n  surfaces and owners.\n\n## Output schema (`policy_proposal`)\n\n```yaml\ndecision: ready | needs_input | reject\npolicy:\n  schema: runx.operational_policy.v1\n  target_repos: [string]\n  runner:\n    id: string\n    kind: string\n    requires: [string]\n  allowed_actions: [string]\n  sources:\n    - provider: string\n      min_confidence: number\n  owner_routes:\n    - surface: string\n      owner: string\n  outcomes:\n    verification_required: boolean\n    close_source_issue: never | when_verified | always\n    require_human_merge_gate: boolean\n    auto_merge: boolean\nlint:\n  status: pass | fail\n  findings:\n    - id: string\n      severity: error | warning\n      message: string\nrationale: string\nblockers: [string]\nneeds_input: [string]\nsuccess_checkpoint:\n  milestone: string\n  description: string\n```\n\nA proposal with any `error` finding must have `decision: needs_input` or\n`reject`, never `ready`.\n\n## Worked example\n\nBrief: \"Govern issue intake across our three repos. GitHub issues and Sentry\nalerts. Kam owns the platform, Chong owns product. Never auto-merge; a human\napproves every merge; close the source issue only once the fix is verified.\"\n\nThe proposal binds the three repos to a GitHub-Actions + scafld runner, allows\n`issue-intake`\u002F`issue-to-pr`\u002F`pr-review`, trusts GitHub at 0.72 and Sentry at\n0.82, routes platform to Kam and product to Chong, and sets\n`require_human_merge_gate: true`, `auto_merge: false`,\n`verification_required: true`, `close_source_issue: when_verified`. The lint\npasses, so `decision: ready`.\n\n## Inputs\n\n- `governance_brief` (required): the governance intent in prose.\n- `existing_policy` (optional): a current `runx.operational_policy.v1` to tighten.\n- `target_repos` (optional): explicit repo list when not in the brief.\n- `objective` (optional): operator intent that focuses the pass.\n",{"name":5,"runx":24,"description":7},{"category":25},"ops","main","fe90232960df6d9653e72e8d024a9d859e1ae524","skills\u002Fpolicy-author","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx","https:\u002F\u002Frunx.ai","https:\u002F\u002Fgithub.com\u002FZachDreamZ","https:\u002F\u002Fagentapigw.dpdns.org","Building Agent API Gateway — structured web data for AI agents. Consistent until I make it.","2026-07-17 04:21:10",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add ZachDreamZ\u002Frunx --skill policy-author",{"tool":41,"command":42},"bunx","bunx skills add ZachDreamZ\u002Frunx --skill policy-author",{"tool":44,"command":45},"pnpm","pnpm dlx skills add ZachDreamZ\u002Frunx --skill policy-author","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fpolicy-author\u002FSKILL.md",true,[49,55,59,63],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"fixtures\u002Fissue-flow-policy-from-brief.yaml","REFERENCE","参考文档",2218,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fpolicy-author\u002Ffixtures\u002Fissue-flow-policy-from-brief.yaml",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"fixtures\u002Ftighten-existing-policy.yaml",2388,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fpolicy-author\u002Ffixtures\u002Ftighten-existing-policy.yaml",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"fixtures\u002Fvague-brief-needs-input.yaml",1948,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fpolicy-author\u002Ffixtures\u002Fvague-brief-needs-input.yaml",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"X.yaml",980,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fpolicy-author\u002FX.yaml",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M79A3PCWPN0YG6XG3X2YWGY4","zapier-handoff","Validate a runx execution context and hand off a governed payload to a Zapier Catch Hook with scoped auth, idempotency, and receipt expectations.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fzapier-handoff\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M79A3JPAJVDGX5AGXKHB6M58","x402-pay","Execute a governed x402 payment by delegating to the canonical spend flow with the x402 runtime path selected.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fx402-pay\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M79A3H7HHAQ5B4QCA0S2PPA3","work-plan","Decompose a build objective into governed runx execution steps.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fwork-plan\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M79A3ESQDZ6AQ3QASKYGYTNB","web-fetch","Fetch and extract one web source within an explicit allowlist, returning the content by digest with full provenance.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fweb-fetch\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M79A3C9NE99P24Q2QGG5236D","weather-forecast","Normalize provider weather evidence into an action-safe forecast packet with provenance, uncertainty, and stop conditions for downstream agents.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fweather-forecast\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M79A38RWEA5NHMYBQZPCVPQP","vuln-triage","Triage dependency or ecosystem vulnerability risk into remediation and advisory packets, grounding on verified CVE evidence when it is supplied.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002FSKILL.md",[],[]]