[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EVPRYAS6R71QNZ8P8B58VY":3,"skill-same:01M7EVPRYAS6R71QNZ8P8B58VY":45},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":28,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7EVPRYAS6R71QNZ8P8B58VY","new-repo-ai-policy",null,"tdupu\u002Fagent-skills-public","tdupu","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F3440403?v=4","01M7EV32X9J0EFE5T4P8TKQTCQ","Taylor Dupuy","01M7EV32XZ1Z4MDBYAFRCJD3BP",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Fnew-repo-ai-policy\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: new-repo-ai-policy\ndescription: Sole write path for a repository's AI-POLICY.md and its AI-POLICY-SHORT.md companion (AI rules) — the AI-usage and software-citation contract. Use on \"add an AI rule\", \"amend AI-POLICY.md\", \"change the disclosure requirements\", \"add a declared tool to the policy\", when latex-ai-statement reports a finding no AI-rule covers, or to instantiate AI-POLICY.md from the pack template into a repo. Every change is proposed, human-approved in conversation, and recorded in the doc's Change Log. Companion checker: latex-ai-statement. NOT for recording what a task actually used (update-ai-usage) or what it cost (update-tokens) — those write the records, not the contract — and NOT for any other repo doc, any .tex, or the pack templates.\n---\n\n# new-repo-ai-policy\n\nOwns the repo's **`AI-POLICY.md`** and its `AI-POLICY-SHORT.md` companion.\nEditing them any other way — \"just adding the model we used\", writing\ndisclosure rules into a manuscript or a skill — is the RED-baseline failure\nthis skill exists to prevent (`baselines-phase1.md`, scenario D; design D3:\nacceptance is a human act).\n\n**Trinity role:** `AI-POLICY.md` (source of truth) + `latex-ai-statement`\n(read-only auditor) + this skill (sole write path).\n\n## Procedure\n\nFollow `subdomains\u002Frepo-docs\u002FAMENDMENT.md` end to end: resolve the repo's\n`AI-POLICY.md` (on miss, instantiate\n`subdomains\u002Frepo-docs\u002Ftemplates\u002FAI-POLICY.md` — the instantiation is itself\nthe proposal) → draft the structured proposal → **human gate, mandatory** →\napply to `AI-POLICY.md` (and its SHORT companion) only, with a Change Log\nrow naming the approver → verify (below) → conservative, pathspec-scoped\ncommit only with explicit authority.\n\n## This skill's specifics\n\n- **Declared-tools rows are the common case.** Adding a tool, model, or\n  skill to the table is a one-row proposal, but it obliges a `.bib` entry\n  and a pinpoint citation wherever the tool is used (AI2, AI3) — name that\n  in Downstream.\n- Placement changes (AI12) ripple into every manuscript in the repo; a\n  journal requirement that overrides placement is recorded as such, not as\n  a weakening of the rule.\n- Pricing conventions live in AI16 and are implemented by `update-tokens`;\n  a proposal changing the rate source or the estimate-labelling convention\n  must say what happens to existing rows (never silently re-priced).\n- **Keep the SHORT companion in step.** Every rule added, reworded, or\n  deprecated updates its indexed line in `AI-POLICY-SHORT.md` in the same\n  amendment. The companion is an index, never a second source of truth.\n\n## Verification (Step 4)\n\n**First run the coverage check** —\n`python3 subdomains\u002Frepo-docs\u002Fscripts\u002Fcheck-ai-coverage.py`. It asserts that\nevery rule marked `[C]`, `[R]`, or `[F]` has an owner that names it: `[C]` a\nrow in `latex-ai-statement`'s table, `[R]` a mention in `update-ai-usage` or\n`update-tokens`, `[F]` a matching line in the SHORT index. Three review\nrounds each shipped a rule whose enforcement point did not mention it; this\nis the check that ends that. A non-zero exit blocks the amendment.\n\nThen the manuscript pass. Run `latex-ai-statement` in\npolicy-verification mode on the amended `AI-POLICY.md`, then on each `.tex`\nin the repo, and report the manuscript count — a repo with no manuscript\nreports \"checked 0 manuscripts\", never a silent pass. AI15\u002FAI16 amendments\ntouch the records, not a `.tex`: verify those against `update-ai-usage` and\n`update-tokens` instead.\n\n## Floors\n\nThe template marks floors `[F]`. Read them there — this skill does not\nrestate the set, because a second copy is how the list drifts. A proposal\nthat weakens or deletes an `[F]` rule is refused, not presented; a repo whose\ninstantiated copy predates a floor is not exempt, and the remedy is an\namendment adding it.\n\n## Refuse and escalate\n\nRoute to the owning **skill**, never to the document — editing another\ndomain's policy in place is the sole-write-path violation this trinity\nexists to prevent.\n\n| Finding belongs to | Route to |\n| --- | --- |\n| LX floor (`subdomains\u002Flatex\u002FPOLICY.md`) | `new-latex-policy` |\n| Repo `STYLE.md` \u002F `LAYOUT.md` \u002F `AGENTS.md` | `new-repo-style-policy` \u002F `new-repo-layout-policy` \u002F `new-repo-agents-policy` |\n| Repo `ADR.md` \u002F `LATEX.md` | `new-repo-adr-policy` \u002F `new-repo-latex-policy` |\n| What a task used or cost (`ai-usage.md`, `tokens.md`) | `update-ai-usage` \u002F `update-tokens` — records, not contract |\n| The pack templates themselves | agents decide (delegated by the repository owner, 2026-09-19), subject to the rule budget in the template header — no skill owns these, so propose durably, tighten the wording, and record the reasoning in the Change Log |\n","# new-repo-ai-policy\n\nOwns the repo's **`AI-POLICY.md`** and its `AI-POLICY-SHORT.md` companion.\nEditing them any other way — \"just adding the model we used\", writing\ndisclosure rules into a manuscript or a skill — is the RED-baseline failure\nthis skill exists to prevent (`baselines-phase1.md`, scenario D; design D3:\nacceptance is a human act).\n\n**Trinity role:** `AI-POLICY.md` (source of truth) + `latex-ai-statement`\n(read-only auditor) + this skill (sole write path).\n\n## Procedure\n\nFollow `subdomains\u002Frepo-docs\u002FAMENDMENT.md` end to end: resolve the repo's\n`AI-POLICY.md` (on miss, instantiate\n`subdomains\u002Frepo-docs\u002Ftemplates\u002FAI-POLICY.md` — the instantiation is itself\nthe proposal) → draft the structured proposal → **human gate, mandatory** →\napply to `AI-POLICY.md` (and its SHORT companion) only, with a Change Log\nrow naming the approver → verify (below) → conservative, pathspec-scoped\ncommit only with explicit authority.\n\n## This skill's specifics\n\n- **Declared-tools rows are the common case.** Adding a tool, model, or\n  skill to the table is a one-row proposal, but it obliges a `.bib` entry\n  and a pinpoint citation wherever the tool is used (AI2, AI3) — name that\n  in Downstream.\n- Placement changes (AI12) ripple into every manuscript in the repo; a\n  journal requirement that overrides placement is recorded as such, not as\n  a weakening of the rule.\n- Pricing conventions live in AI16 and are implemented by `update-tokens`;\n  a proposal changing the rate source or the estimate-labelling convention\n  must say what happens to existing rows (never silently re-priced).\n- **Keep the SHORT companion in step.** Every rule added, reworded, or\n  deprecated updates its indexed line in `AI-POLICY-SHORT.md` in the same\n  amendment. The companion is an index, never a second source of truth.\n\n## Verification (Step 4)\n\n**First run the coverage check** —\n`python3 subdomains\u002Frepo-docs\u002Fscripts\u002Fcheck-ai-coverage.py`. It asserts that\nevery rule marked `[C]`, `[R]`, or `[F]` has an owner that names it: `[C]` a\nrow in `latex-ai-statement`'s table, `[R]` a mention in `update-ai-usage` or\n`update-tokens`, `[F]` a matching line in the SHORT index. Three review\nrounds each shipped a rule whose enforcement point did not mention it; this\nis the check that ends that. A non-zero exit blocks the amendment.\n\nThen the manuscript pass. Run `latex-ai-statement` in\npolicy-verification mode on the amended `AI-POLICY.md`, then on each `.tex`\nin the repo, and report the manuscript count — a repo with no manuscript\nreports \"checked 0 manuscripts\", never a silent pass. AI15\u002FAI16 amendments\ntouch the records, not a `.tex`: verify those against `update-ai-usage` and\n`update-tokens` instead.\n\n## Floors\n\nThe template marks floors `[F]`. Read them there — this skill does not\nrestate the set, because a second copy is how the list drifts. A proposal\nthat weakens or deletes an `[F]` rule is refused, not presented; a repo whose\ninstantiated copy predates a floor is not exempt, and the remedy is an\namendment adding it.\n\n## Refuse and escalate\n\nRoute to the owning **skill**, never to the document — editing another\ndomain's policy in place is the sole-write-path violation this trinity\nexists to prevent.\n\n| Finding belongs to | Route to |\n| --- | --- |\n| LX floor (`subdomains\u002Flatex\u002FPOLICY.md`) | `new-latex-policy` |\n| Repo `STYLE.md` \u002F `LAYOUT.md` \u002F `AGENTS.md` | `new-repo-style-policy` \u002F `new-repo-layout-policy` \u002F `new-repo-agents-policy` |\n| Repo `ADR.md` \u002F `LATEX.md` | `new-repo-adr-policy` \u002F `new-repo-latex-policy` |\n| What a task used or cost (`ai-usage.md`, `tokens.md`) | `update-ai-usage` \u002F `update-tokens` — records, not contract |\n| The pack templates themselves | agents decide (delegated by the repository owner, 2026-09-19), subject to the rule budget in the template header — no skill owns these, so propose durably, tighten the wording, and record the reasoning in the Change Log |\n",{},"main","8d13efb5e66306aeae6e3b948bc463e7e2db1b65","skills\u002Fnew-repo-ai-policy","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public","https:\u002F\u002Fgithub.com\u002Ftdupu","https:\u002F\u002Ftdupu.github.io\u002Findex.html","Associate Professor, Department of Mathematics and Statistics, University of Vermont --- last updated Fall 2019","2026-11-13 09:07:19",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add tdupu\u002Fagent-skills-public --skill new-repo-ai-policy",{"tool":37,"command":38},"bunx","bunx skills add tdupu\u002Fagent-skills-public --skill new-repo-ai-policy",{"tool":40,"command":41},"pnpm","pnpm dlx skills add tdupu\u002Fagent-skills-public --skill new-repo-ai-policy","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Fnew-repo-ai-policy\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M7EW4PT586KKE7VRCAD80Z9K","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M7EW4HV5V74AF3PTV8N4T0PS","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M7EW4DNKGP5CR1RAJP2J9PHA","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7EW4BA2QP88VBFVXDVJM7XQ","using-superpowers","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fusing-superpowers\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M7EW47F2JG5FBESDJNP3PKMV","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fusing-git-worktrees\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M7EW44N8556Y556NX9HJT4KP","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[]]