[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75Y1YPJS3MHKX3X91FFM2AB":3,"skill-same:01M75Y1YPJS3MHKX3X91FFM2AB":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":44},"01M75Y1YPJS3MHKX3X91FFM2AB","ci",null,"Set up or normalize one project Verify command and matching GitHub Actions checks while preserving existing CI. Use for \u002Fci, GitHub Actions setup, pull-request checks, automatic checks, or aligning typecheck, test, and build verification.","aiblueprinthq\u002Fai-blueprint","aiblueprinthq","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F317905365?v=4","01M75XZGKSB8GPVXQ69BA57VA7","01M75XZGME4HNZG9CDB8K3TQ8X",510,"MIT","https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fci\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: ci\ndescription: Set up or normalize one project Verify command and matching GitHub Actions checks while preserving existing CI. Use for \u002Fci, GitHub Actions setup, pull-request checks, automatic checks, or aligning typecheck, test, and build verification.\ndisable-model-invocation: true\n---\n\n# ci - set up automatic GitHub checks\n\n**Context reuse:** Reuse any required file already loaded in project instructions or the current session. Read it again only if absent, changed, or exact current bytes or line references are needed.\n\n**First action:** Before project inspection, preflight, or any other tool call,\npublish `running` to `blueprint\u002F.state\u002Frun.json` when `blueprint\u002F.state\u002F`\nexists. From the project root, run the first helper that exists,\n`node .agents\u002Fskills\u002Fblueprint-doctor\u002Fscripts\u002Frun-state.mjs` or\n`node .claude\u002Fskills\u002Fblueprint-doctor\u002Fscripts\u002Frun-state.mjs`, with `start --command\n\u003Cskill> --summary \"\u003Ctruthful summary>\" --boundary\n\u003Cread-only|reviewed|local-only>`. Use `update` at milestones, with `--status\nblocked --resume \u003Ccommand>` for a blocker, and `finish --status ready|completed`\nat the end; `--help` lists every option and `blueprint\u002Fworkflow.md` has the full\nactivity contract. A missing or failing helper is a warning, not a blocker.\n\nWhere this sits in the workflow:\n\n    \u002Fonboard or \u002Fadopt  ->  [ci]  ->  Verify locally  ->  GitHub runs Verify\n    (project commands)     (setup)    (same recipe)      (pull requests)\n\nThis skill gives local work and GitHub one shared automated command. It is an\noptional setup task, not a requirement for using the Blueprint.\n\nKeep the beginner explanation simple:\n\n- **Verify is the recipe.** It runs checks the project already has.\n- **GitHub Actions is the worker.** It runs the same recipe automatically.\n- **A GitHub ruleset is the lock.** That optional remote setting can require the\n  worker to report green before merge.\n\nThis skill configures the recipe and worker. It never changes the remote\nruleset, pushes, publishes, or deploys.\n\n## Input\n\nNo argument is required. A named provider or workflow preference is a request to\nreview, not permission to replace existing CI. This skill's default provider is\nGitHub Actions because it creates GitHub pull-request checks.\n\n## Step 1 - inspect without changing files\n\nRead enough to identify the real project setup:\n\n- `AGENTS.md`, especially Commands and any documented `Verify` command\n- package or language manifests and task-runner files\n- lockfiles and the package manager they imply\n- existing typecheck, test, build, lint, and other quality commands\n- test configuration and actual test files\n- runtime version files such as `.nvmrc`, `.node-version`, `.python-version`,\n  `go.mod`, or `rust-toolchain.toml`\n- `.github\u002Fworkflows\u002F` and any documented external CI\n- git's current branch, configured default branch, and remotes when available\n\nDo not assume npm, Node.js, `main`, or GitHub from the Blueprint template. Do not\nrun installs or edit files during inspection.\n\nIf an existing workflow already provides equivalent pull-request checks, explain\nwhat it runs. If it is healthy and aligned with a documented Verify command,\nreport that no setup is needed. If normalization would change existing CI, show\nthe proposed change and get explicit approval before editing it.\n\n## Step 2 - define one Verify command\n\nBuild one command from meaningful checks that actually exist, in this order:\n\n1. typecheck\n2. tests, only when a runner and real test command are configured\n3. build\n\nOmit missing checks. Do not install a test runner, invent an empty test suite, or\nadd a placeholder command. Lint, formatting, coverage, browser tests, security\nscans, dependency audits, and version matrices are not part of the beginner\ndefault. Preserve them when existing CI already requires them, and discuss any\nnormalization before changing that behavior.\n\nFor JavaScript and TypeScript, add or reuse a package script named `verify` and\ninvoke it with the detected package manager. For other stacks, use the existing\nnative task runner or the smallest clear combined command. Document the exact\ninvocation as `Verify` in the Commands section of `AGENTS.md`.\n\nExamples are explanatory only. Never copy them without detecting the project:\n\n```text\nVerify: npm run verify\nVerify: make verify\nVerify: cargo test && cargo build --locked\n```\n\nIf no meaningful check exists, stop and explain what is missing. Do not create a\nworkflow that always passes.\n\n## Step 3 - create or align the workflow\n\nCreate `.github\u002Fworkflows\u002Fverify.yml` only when that path is free. If it already\nexists, never overwrite it silently. Show the exact proposed diff and ask before\nchanging it.\n\nThe workflow should contain only what the detected project needs:\n\n- a clear workflow name such as `Verify`\n- `pull_request`\n- pushes to the detected default branch\n- `permissions: contents: read`\n- the real runtime version\n- checkout and the appropriate runtime setup action\n- the lockfile-safe dependency install command\n- one final step that runs the exact `Verify` command from `AGENTS.md`\n\nIf the default branch cannot be identified from git or project context, ask\nbefore writing the push trigger instead of guessing. Preserve all other workflow\nfiles. When another workflow overlaps, report the overlap and ask whether to\nreuse, align, or leave it alone.\n\n## Step 4 - prove the setup locally\n\nRun the exact documented `Verify` command locally. The individual build, test,\nor typecheck commands may still be run separately for diagnosis, but the final\nproof must use Verify because that is what GitHub will run.\n\nA passing local run proves the recipe against the current working copy. It does\nnot prove dependency installation or command behavior from a fresh checkout.\nUntil the workflow is pushed and reports green on GitHub, describe the setup as\nprepared locally, not CI verified. The first successful GitHub run is the\nauthoritative clean-checkout proof.\n\nIf Verify fails, report the failing subcommand and stop. Do not weaken the\ncommand, remove a legitimate check, or describe CI as ready.\n\nDo not push the workflow. A local workflow file does nothing on GitHub until the\nuser later approves a push.\n\n## Step 5 - report\n\nFinish with a concise setup report:\n\n- existing CI found and whether it was preserved or changed\n- exact `Verify` command\n- checks included and checks omitted\n- test gate status\n- workflow path and triggers\n- local Verify result and whether CI is only prepared locally or confirmed by a\n  successful GitHub run\n- files changed\n- any overlap, uncertainty, or follow-up\n\nExplain that making the GitHub check required is a separate remote ruleset choice\nafter the workflow is pushed. Do not change repository settings or treat that as\npart of this skill.\n\n## Interaction with other skills\n\n- `\u002Ftests` adds the real test command to an existing Verify command, but never\n  creates CI by itself.\n- `\u002Fimplement`, `\u002Fcomplete`, and `\u002Fautopilot` run Verify when it is documented,\n  with their existing fallback behavior when it is absent.\n- `\u002Fblueprint-doctor` diagnoses drift between `AGENTS.md`, the project command, and the\n  workflow. Missing CI remains informational.\n\n## Rules\n\n- Preserve existing CI and custom checks.\n- Never invent tests or install a runner as part of CI setup.\n- Never add coverage, browser tests, security scans, or matrices by default.\n- Never push or change a remote ruleset without separate explicit approval.\n- Keep one exact Verify command shared by local work and GitHub.\n\n## Formatting\n\nFormat the output to match the project's conventions in\n`blueprint\u002Fcontext\u002Fai-interaction.md`: concise, scannable markdown, with lists for\nenumerations and tables for matrices rather than dense paragraphs.\n","# ci - set up automatic GitHub checks\n\n**Context reuse:** Reuse any required file already loaded in project instructions or the current session. Read it again only if absent, changed, or exact current bytes or line references are needed.\n\n**First action:** Before project inspection, preflight, or any other tool call,\npublish `running` to `blueprint\u002F.state\u002Frun.json` when `blueprint\u002F.state\u002F`\nexists. From the project root, run the first helper that exists,\n`node .agents\u002Fskills\u002Fblueprint-doctor\u002Fscripts\u002Frun-state.mjs` or\n`node .claude\u002Fskills\u002Fblueprint-doctor\u002Fscripts\u002Frun-state.mjs`, with `start --command\n\u003Cskill> --summary \"\u003Ctruthful summary>\" --boundary\n\u003Cread-only|reviewed|local-only>`. Use `update` at milestones, with `--status\nblocked --resume \u003Ccommand>` for a blocker, and `finish --status ready|completed`\nat the end; `--help` lists every option and `blueprint\u002Fworkflow.md` has the full\nactivity contract. A missing or failing helper is a warning, not a blocker.\n\nWhere this sits in the workflow:\n\n    \u002Fonboard or \u002Fadopt  ->  [ci]  ->  Verify locally  ->  GitHub runs Verify\n    (project commands)     (setup)    (same recipe)      (pull requests)\n\nThis skill gives local work and GitHub one shared automated command. It is an\noptional setup task, not a requirement for using the Blueprint.\n\nKeep the beginner explanation simple:\n\n- **Verify is the recipe.** It runs checks the project already has.\n- **GitHub Actions is the worker.** It runs the same recipe automatically.\n- **A GitHub ruleset is the lock.** That optional remote setting can require the\n  worker to report green before merge.\n\nThis skill configures the recipe and worker. It never changes the remote\nruleset, pushes, publishes, or deploys.\n\n## Input\n\nNo argument is required. A named provider or workflow preference is a request to\nreview, not permission to replace existing CI. This skill's default provider is\nGitHub Actions because it creates GitHub pull-request checks.\n\n## Step 1 - inspect without changing files\n\nRead enough to identify the real project setup:\n\n- `AGENTS.md`, especially Commands and any documented `Verify` command\n- package or language manifests and task-runner files\n- lockfiles and the package manager they imply\n- existing typecheck, test, build, lint, and other quality commands\n- test configuration and actual test files\n- runtime version files such as `.nvmrc`, `.node-version`, `.python-version`,\n  `go.mod`, or `rust-toolchain.toml`\n- `.github\u002Fworkflows\u002F` and any documented external CI\n- git's current branch, configured default branch, and remotes when available\n\nDo not assume npm, Node.js, `main`, or GitHub from the Blueprint template. Do not\nrun installs or edit files during inspection.\n\nIf an existing workflow already provides equivalent pull-request checks, explain\nwhat it runs. If it is healthy and aligned with a documented Verify command,\nreport that no setup is needed. If normalization would change existing CI, show\nthe proposed change and get explicit approval before editing it.\n\n## Step 2 - define one Verify command\n\nBuild one command from meaningful checks that actually exist, in this order:\n\n1. typecheck\n2. tests, only when a runner and real test command are configured\n3. build\n\nOmit missing checks. Do not install a test runner, invent an empty test suite, or\nadd a placeholder command. Lint, formatting, coverage, browser tests, security\nscans, dependency audits, and version matrices are not part of the beginner\ndefault. Preserve them when existing CI already requires them, and discuss any\nnormalization before changing that behavior.\n\nFor JavaScript and TypeScript, add or reuse a package script named `verify` and\ninvoke it with the detected package manager. For other stacks, use the existing\nnative task runner or the smallest clear combined command. Document the exact\ninvocation as `Verify` in the Commands section of `AGENTS.md`.\n\nExamples are explanatory only. Never copy them without detecting the project:\n\n```text\nVerify: npm run verify\nVerify: make verify\nVerify: cargo test && cargo build --locked\n```\n\nIf no meaningful check exists, stop and explain what is missing. Do not create a\nworkflow that always passes.\n\n## Step 3 - create or align the workflow\n\nCreate `.github\u002Fworkflows\u002Fverify.yml` only when that path is free. If it already\nexists, never overwrite it silently. Show the exact proposed diff and ask before\nchanging it.\n\nThe workflow should contain only what the detected project needs:\n\n- a clear workflow name such as `Verify`\n- `pull_request`\n- pushes to the detected default branch\n- `permissions: contents: read`\n- the real runtime version\n- checkout and the appropriate runtime setup action\n- the lockfile-safe dependency install command\n- one final step that runs the exact `Verify` command from `AGENTS.md`\n\nIf the default branch cannot be identified from git or project context, ask\nbefore writing the push trigger instead of guessing. Preserve all other workflow\nfiles. When another workflow overlaps, report the overlap and ask whether to\nreuse, align, or leave it alone.\n\n## Step 4 - prove the setup locally\n\nRun the exact documented `Verify` command locally. The individual build, test,\nor typecheck commands may still be run separately for diagnosis, but the final\nproof must use Verify because that is what GitHub will run.\n\nA passing local run proves the recipe against the current working copy. It does\nnot prove dependency installation or command behavior from a fresh checkout.\nUntil the workflow is pushed and reports green on GitHub, describe the setup as\nprepared locally, not CI verified. The first successful GitHub run is the\nauthoritative clean-checkout proof.\n\nIf Verify fails, report the failing subcommand and stop. Do not weaken the\ncommand, remove a legitimate check, or describe CI as ready.\n\nDo not push the workflow. A local workflow file does nothing on GitHub until the\nuser later approves a push.\n\n## Step 5 - report\n\nFinish with a concise setup report:\n\n- existing CI found and whether it was preserved or changed\n- exact `Verify` command\n- checks included and checks omitted\n- test gate status\n- workflow path and triggers\n- local Verify result and whether CI is only prepared locally or confirmed by a\n  successful GitHub run\n- files changed\n- any overlap, uncertainty, or follow-up\n\nExplain that making the GitHub check required is a separate remote ruleset choice\nafter the workflow is pushed. Do not change repository settings or treat that as\npart of this skill.\n\n## Interaction with other skills\n\n- `\u002Ftests` adds the real test command to an existing Verify command, but never\n  creates CI by itself.\n- `\u002Fimplement`, `\u002Fcomplete`, and `\u002Fautopilot` run Verify when it is documented,\n  with their existing fallback behavior when it is absent.\n- `\u002Fblueprint-doctor` diagnoses drift between `AGENTS.md`, the project command, and the\n  workflow. Missing CI remains informational.\n\n## Rules\n\n- Preserve existing CI and custom checks.\n- Never invent tests or install a runner as part of CI setup.\n- Never add coverage, browser tests, security scans, or matrices by default.\n- Never push or change a remote ruleset without separate explicit approval.\n- Keep one exact Verify command shared by local work and GitHub.\n\n## Formatting\n\nFormat the output to match the project's conventions in\n`blueprint\u002Fcontext\u002Fai-interaction.md`: concise, scannable markdown, with lists for\nenumerations and tables for matrices rather than dense paragraphs.\n",{"name":5,"description":7,"disable-model-invocation":23},true,"main","483eb73dbc58a4b82a5642f864ea7569af947e39",".claude\u002Fskills\u002Fci",132,"https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint","https:\u002F\u002Fai-blueprint.dev","https:\u002F\u002Fgithub.com\u002Faiblueprinthq","2026-11-14 19:46:05",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":23},[34,37,40],{"tool":35,"command":36},"npx","npx skills add aiblueprinthq\u002Fai-blueprint --skill ci",{"tool":38,"command":39},"bunx","bunx skills add aiblueprinthq\u002Fai-blueprint --skill ci",{"tool":41,"command":42},"pnpm","pnpm dlx skills add aiblueprinthq\u002Fai-blueprint --skill ci","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fci\u002FSKILL.md",[],[46,52,57,64,71,78],{"skillNo":47,"name":48,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M75Y34X26C74A66RYE49W8JY","status","https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002Fpackages\u002Fcreate-ai-blueprint\u002Ftest\u002Ffixtures\u002Fhealthy-blueprint\u002F.claude\u002Fskills\u002Fstatus\u002FSKILL.md",[],[],{"skillNo":53,"name":48,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":18},"01M75Y3456H4WZZ25634QY9KRA","https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002Fpackages\u002Fcreate-ai-blueprint\u002Ftest\u002Ffixtures\u002Fhealthy-blueprint\u002F.agents\u002Fskills\u002Fstatus\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":18},"01M75Y31WCYVFM5M4NH7D9MRMW","tests","Set up unit testing with \u002Ftests or \u002Ftests unit, or explicitly set up browser and end-to-end testing with \u002Ftests browser. Reuse or install a suitable test runner, add one example or smoke test, document commands, and verify. Use check for one-time live verification.","https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftests\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M75Y2ZETQZEHN2V19HWZBB1R","prototype","Plan and create throwaway static HTML and CSS mockups with shared design tokens before feature implementation. Use for \u002Fprototype, screen mockups, layout exploration, themes, or deciding a project's look and feel.","https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fprototype\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M75Y2WY81F9N40G2RADX2FKH","overview","Validate and normalize project-plan.md and build-plan.md, then generate the durable project-overview.md used by agents. Use for \u002Foverview, plan cleanup, generating the first overview, or refreshing context after either plan changes.","https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Foverview\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M75Y2SNF3FZJP3NHRT0B5MQE","onboard","Onboard a fresh or early scaffold after Blueprint is overlaid by tuning commands, standards, adapters, visibility, and context loading. Use for \u002Fonboard, fresh installation setup, or what to do after installing Blueprint. Use adopt for an established app.","https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fonboard\u002FSKILL.md",[],[]]