[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DBRST29F8J729DHGCM55WJ":3,"skill-same:01M7DBRST29F8J729DHGCM55WJ":46},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7DBRST29F8J729DHGCM55WJ","intent-records",null,"Draft or approve an intent record when a person asks for a change, or describe existing behaviour before retrofitting compiled intent. Use before turning intent into a pi-work workspec.","CenterForAgenticAI\u002Ftools","CenterForAgenticAI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F250424195?v=4","01M7DBNBBRNZ6NT6WYSEPYK811","CAAIR","01M7DBNBCBH3B7HHWP0ACQW3F7",0,"MIT","https:\u002F\u002Fgithub.com\u002FCenterForAgenticAI\u002Ftools\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-intent\u002Fskills\u002Fintent-records\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: intent-records\ndescription: Draft or approve an intent record when a person asks for a change, or describe existing behaviour before retrofitting compiled intent. Use before turning intent into a pi-work workspec.\n---\n\nAdopter records, models, receipts, conformance manifests, oracles and vendored scripts live under `.intent\u002F` (`.intent\u002Ftools\u002F` for scripts). Commands run from the repo root. ripgrep and fd skip hidden directories by default; search `.intent` explicitly or use `rg --hidden` \u002F `fd --hidden`.\n\n# Intent records\n\nThe person has the requirement; the adopting project's agent reads this skill. Finish with a record whose rules and approval state are explicit, not inferred from a green test.\n\n1. Read the adopting repository's CONTEXT.md and relevant code\u002Fexamples. For a new adopter, run `pi-intent init \u003Crepo-dir>`; otherwise preserve existing records. Read the installed package's SPEC.md for the schema and lifecycle.\n2. Choose a new four-digit id and slug. Write `.intent\u002Frecords\u002FNNNN-slug.md` using the installed `templates\u002Frecords\u002F0001-change.md`. For a retrofit, start `descriptive` and distinguish observed behaviour from proposed rules. For greenfield work, start `draft`.\n3. Cite existing terms in CONTEXT.md. Define only terms the record introduces. Give contiguous R1, R2… clauses, concrete input\u002Foutput examples, freedoms, non-goals and open questions. Done: every clause can be interpreted without guessing and every unresolved decision is visible.\n4. Ask the person to review the complete record and resolve or explicitly defer questions. Record their explicit approval with `approved-by: \u003Chuman>` and `status: approved`; agents draft and capture human decisions rather than approve themselves. An edited approved meaning returns to draft. Done: approval names the exact reviewed text.\n5. Load `compiled-intent-model` when the change has a finite decision worth modeling. Emergent effects, timing or concurrency instead need ordinary tests that name the record's rule.\n6. Feed the approved record into pi-work's marked draft, preserve its clause text as criteria, promote with `work_promote`, and decompose with pi-work's authoring\u002Fdecomposition skills. Follow the ADR-0009 pattern: a model-change node owns changed allowable states; affected implementation nodes depend on it. The link is evidence commands, not a pi-work package dependency or a new schema field.\n\n## pi-work handoff\n\nUse the README's worked workspec fragment as the evidence pattern: the model-change node requires `node .intent\u002Ftools\u002Fintent-check.mjs` and `node .intent\u002Ftools\u002Fintent-gate.mjs`; implementation depends on it and requires `node .intent\u002Ftools\u002Fintent-conform.mjs`. Those are `kind: command` criteria with exit 0 and a nonempty expected success string. Run pi-work's fail-closed `work_verify` at the explicit worktree and commit; missing, timed-out or stale evidence leaves work unverified. Add `--require-coverage` if all laws must be exercised.\n\nDone: the record path is a workspec reference, the model dependency is explicit, and each selected check is a criterion whose evidence runs the real command. pi-work does not depend on pi-intent.\n","Adopter records, models, receipts, conformance manifests, oracles and vendored scripts live under `.intent\u002F` (`.intent\u002Ftools\u002F` for scripts). Commands run from the repo root. ripgrep and fd skip hidden directories by default; search `.intent` explicitly or use `rg --hidden` \u002F `fd --hidden`.\n\n# Intent records\n\nThe person has the requirement; the adopting project's agent reads this skill. Finish with a record whose rules and approval state are explicit, not inferred from a green test.\n\n1. Read the adopting repository's CONTEXT.md and relevant code\u002Fexamples. For a new adopter, run `pi-intent init \u003Crepo-dir>`; otherwise preserve existing records. Read the installed package's SPEC.md for the schema and lifecycle.\n2. Choose a new four-digit id and slug. Write `.intent\u002Frecords\u002FNNNN-slug.md` using the installed `templates\u002Frecords\u002F0001-change.md`. For a retrofit, start `descriptive` and distinguish observed behaviour from proposed rules. For greenfield work, start `draft`.\n3. Cite existing terms in CONTEXT.md. Define only terms the record introduces. Give contiguous R1, R2… clauses, concrete input\u002Foutput examples, freedoms, non-goals and open questions. Done: every clause can be interpreted without guessing and every unresolved decision is visible.\n4. Ask the person to review the complete record and resolve or explicitly defer questions. Record their explicit approval with `approved-by: \u003Chuman>` and `status: approved`; agents draft and capture human decisions rather than approve themselves. An edited approved meaning returns to draft. Done: approval names the exact reviewed text.\n5. Load `compiled-intent-model` when the change has a finite decision worth modeling. Emergent effects, timing or concurrency instead need ordinary tests that name the record's rule.\n6. Feed the approved record into pi-work's marked draft, preserve its clause text as criteria, promote with `work_promote`, and decompose with pi-work's authoring\u002Fdecomposition skills. Follow the ADR-0009 pattern: a model-change node owns changed allowable states; affected implementation nodes depend on it. The link is evidence commands, not a pi-work package dependency or a new schema field.\n\n## pi-work handoff\n\nUse the README's worked workspec fragment as the evidence pattern: the model-change node requires `node .intent\u002Ftools\u002Fintent-check.mjs` and `node .intent\u002Ftools\u002Fintent-gate.mjs`; implementation depends on it and requires `node .intent\u002Ftools\u002Fintent-conform.mjs`. Those are `kind: command` criteria with exit 0 and a nonempty expected success string. Run pi-work's fail-closed `work_verify` at the explicit worktree and commit; missing, timed-out or stale evidence leaves work unverified. Add `--require-coverage` if all laws must be exercised.\n\nDone: the record path is a workspec reference, the model dependency is explicit, and each selected check is a criterion whose evidence runs the real command. pi-work does not depend on pi-intent.\n",{"name":5,"description":7},"main","a341ec69437d028e71ea1de51b7f6d9c1238048b","packages\u002Fpi-intent\u002Fskills\u002Fintent-records","https:\u002F\u002Fgithub.com\u002FCenterForAgenticAI\u002Ftools","https:\u002F\u002Fgithub.com\u002FCenterForAgenticAI","https:\u002F\u002Fwww.centerforairesearch.org\u002F","CAAIR develops applied AI systems that support civil society, public accountability, and democratic infrastructure.","2026-11-12 02:15:25",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add CenterForAgenticAI\u002Ftools --skill intent-records",{"tool":38,"command":39},"bunx","bunx skills add CenterForAgenticAI\u002Ftools --skill intent-records",{"tool":41,"command":42},"pnpm","pnpm dlx skills add CenterForAgenticAI\u002Ftools --skill intent-records","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCenterForAgenticAI\u002Ftools\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-intent\u002Fskills\u002Fintent-records\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7DBS96C51VE1KHCM1N0SR47","work-execution","Execute a validated pi-work node or wave when you need the ready-set, by-reference work_plan brief, Fabric default, pi-delegate fallback, explicit tree-bound verification, remediation, scope amendments, or a post-integration refactor pass. Use after decomposition and before claiming any node is done.","https:\u002F\u002Fgithub.com\u002FCenterForAgenticAI\u002Ftools\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-work\u002Fskills\u002Fwork-execution\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7DBS2SJ4ZND4SG77JX66BWK","work-decomposition","Turn a validated pi-work intent into a strict workspec work graph when the work is too large for one bounded worker. Use when assigning criterion homes, dependencies, honest write scopes, open decisions, or optional model-change nodes before planning execution.","https:\u002F\u002Fgithub.com\u002FCenterForAgenticAI\u002Ftools\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-work\u002Fskills\u002Fwork-decomposition\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7DBRXT98J0Q84K38FCFQ9VT","work-authoring","Draft a pi-work workspec when an outcome, scope, or proof obligation is still unclear. Use this before turning a conversation, issue, or design into a markdown draft, especially when acceptance criteria need to survive lossless promotion into strict YAML.","https:\u002F\u002Fgithub.com\u002FCenterForAgenticAI\u002Ftools\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-work\u002Fskills\u002Fwork-authoring\u002FSKILL.md",[],[],{"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},"01M7DBRNVNYBW7K25Y7W7CYVEA","intent-conformance","Connect an approved finite Bend model to actual application code with a language-neutral conformance manifest, app-language oracles and a broken-model control. Load when proving implementation parity or diagnosing decision drift.","https:\u002F\u002Fgithub.com\u002FCenterForAgenticAI\u002Ftools\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-intent\u002Fskills\u002Fintent-conformance\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},"01M7DBRH9KT2DMXVT16P1JCHQK","compiled-intent-model","Author or change a finite Bend model from an approved intent record, review its meaning, obtain human law approval, and produce an offline-verifiable Jev receipt. Load for model-change nodes, not for emergent runtime behaviour.","https:\u002F\u002Fgithub.com\u002FCenterForAgenticAI\u002Ftools\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-intent\u002Fskills\u002Fcompiled-intent-model\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},"01M7DBRBGVD06GXTFWR7GXA67Y","developing-pi-extension-repos","Keep tests, dependencies, CI reproduction, and coverage reliable across Pi extension repositories. Load when editing, testing, or setting up a worktree in a pi extension repository, when tests pass from source but fail from compiled output (or vice versa), before running `npm install` in a checkout other sessions may be using. For writing extension code itself, load `authoring-pi-extensions`.","https:\u002F\u002Fgithub.com\u002FCenterForAgenticAI\u002Ftools\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-dev\u002Fskills\u002Fdeveloping-pi-extension-repos\u002FSKILL.md",[],[]]