[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E8ADGDS7CE9JA8427PXD71":3,"skill-same:01M7E8ADGDS7CE9JA8427PXD71":62},{"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":35,"commitSha":36,"skillDirectory":37,"forksCount":14,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":55},"01M7E8ADGDS7CE9JA8427PXD71","update-actions",null,"Use when updating every outdated GitHub Action across one repository or a fleet, one researched change at a time.","tony\u002Fskills","tony","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F26336?v=4","01M72E5RNJ7SQV8F9KBM5RKRMN","Tony Narlock","01M7E7MBN5C6YZ4JJJ5Y82KBJG",0,"MIT","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fgithub-actions\u002Fskills\u002Fupdate-actions\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: update-actions\ndescription: \"Use when updating every outdated GitHub Action across one repository or a fleet, one researched change at a time.\"\nallowed-tools: [\"Bash\", \"Read\", \"Grep\", \"Glob\", \"Edit\", \"Write\", \"Task\", \"AskUserQuestion\"]\nargument-hint: \"[--root \u003Cdir>] [--owner \u003Cname>...] [--repo \u003Cpath|slug>...] [--audit-only] [--pr] [--push]\"\ndisable-model-invocation: true\n---\n\n# Update All GitHub Actions\n\nAudit every `uses:` pin across the repositories in scope, then bring\nthe out-of-date ones current: one commit per repository and action,\neach justified against the vendor's own release notes.\n\nRead `..\u002Fbumping-github-actions\u002FSKILL.md` and run its phases across the\nscope. It owns the phase structure, the references, and the Orchestration\nPlan; `..\u002F..\u002Freferences\u002Foutput-shapes.md` owns the reply. For a single named action, use\n`\u002Fgithub-actions:update-action` instead.\n\nUser arguments: $ARGUMENTS\n\nRead them as the flags `--root`, `--owner` (repeatable), `--repo`\n(repeatable), `--audit-only`, `--pr`, and `--push`. Any text after the flags is\nthe user's request, not an error: act on it. The argument string and any pasted text (PR titles, logs, the\nrequest itself) never go into a Bash command. Only single values you\nextract (action, version, repository path or slug, owner) do, and only\nwhen each holds nothing but letters, digits and `. _ - \u002F @ + ~`;\nstop and name any other value instead of writing it into a command. `..\u002F..\u002Fscripts\u002Ffleet.py`\nand `..\u002F..\u002Fscripts\u002Fpins.py` resolve from this skill's directory; print each\nabsolute path once and write it literally in each command.\n\n## Procedure\n\nThis skill supplies the scope and the fan-out.\n\n### 1. Scope\n\nDefault scope is the current repository. `--root` audits every git\nrepository beneath a directory, found by `fleet.py discover`; `--owner` keeps\nonly those whose remote belongs to the given accounts or organisations;\n`--repo` names individual ones by path or slug. A slug with no clone is audited\nread-only. Under `--root` without `--owner`, list each discovered\nrepository with its owner in the plan before any write. The scope rule and\nthe slug-only read are in\n`..\u002F..\u002Freferences\u002Faction-pinning.md`.\n\n### 2. Inventory and verify\n\nRun the inventory and verification phases across the whole scope before\ntouching anything, one repository at a time by its own path or slug (never\nthe current directory), so a dangling ref is never written fleet-wide. Also\nlist open dependabot pull requests per repository for the close-out,\nwith `pins.py pulls \u003Cslug>` as `..\u002F..\u002Freferences\u002Fdependabot-closeout.md`\nshows. A failed `gh` call means none can be listed; say so.\n\n### 3. Research, one chain per distinct upgrade\n\nGroup the work by upgrade chain rather than by repository: twenty\nrepositories moving `actions\u002Fcheckout` from the same major share one\npiece of research. Dispatch a subagent per chain where the host\nsupports it. Validate every release URL before it reaches a commit\nmessage.\n\n### 4. Orchestration plan\n\nEnter plan mode before the first edit. In Claude Code call `EnterPlanMode`;\nin Cursor, Codex, or Gemini use `\u002Fplan` or `Shift+Tab`.\nWhere plan mode is unavailable, present the plan as text.\n\nPresent the plan the skill defines, including the PRs to close, and wait\nfor approval. With `--audit-only`, stop here and report; nothing is\nwritten. Exit plan mode before committing.\n\n### 5. Commit\n\nOne commit per repository and action, one repository at a time, edited,\nstaged, committed and pushed as `..\u002F..\u002Freferences\u002Fcommit-and-push.md`\ndirects. With `--push`, push as each repository completes so an\ninterrupted run resumes; otherwise report each local branch holding\ncommits and print its push command. With `--pr`, branch, push, and open a pull request per repository, then close\ndependabot pull requests only after those merge. Write commit messages,\npull-request comments, and the report per `..\u002F..\u002Freferences\u002Fprose-rules.md`.\n\n### 6. Verify and close out\n\nWatch every CI run per repository and attribute failures before\nblaming the bumps. Then close the dependabot pull requests per the closing\nprotocol: show the user the exact commands for every PR the protocol maps\nto a commit or to obsolete, and run them only after the user confirms.\n\n## Rules\n\n- No version string is written before its tag is confirmed to exist.\n- Citing dependabot follows `..\u002F..\u002Freferences\u002Fdependabot-closeout.md`.\n- A fleet-wide claim is verified per repository before it enters that\n  repository's commit body.\n- Report unrelated breakage; fix it only when a bump caused it.\n\n## Output\n\nReply in the completed-run shape in `..\u002F..\u002Freferences\u002Foutput-shapes.md`. The\nhero is `✓ N commits across M repos`, or `⚠ Audit only: N pins out of date`\nwith `--audit-only`. A plan-only run and a halted run (no workflows, no\n`gh`, an unverifiable tag, a PR title carrying shell syntax, PRs that\ncannot be listed or mapped) use the shapes in that file; read it before\nreplying. Under a fleet scope, a repository with an incomplete inventory is\nlisted under `## Audit` as excluded, and the run continues.\n","# Update All GitHub Actions\n\nAudit every `uses:` pin across the repositories in scope, then bring\nthe out-of-date ones current: one commit per repository and action,\neach justified against the vendor's own release notes.\n\nRead `..\u002Fbumping-github-actions\u002FSKILL.md` and run its phases across the\nscope. It owns the phase structure, the references, and the Orchestration\nPlan; `..\u002F..\u002Freferences\u002Foutput-shapes.md` owns the reply. For a single named action, use\n`\u002Fgithub-actions:update-action` instead.\n\nUser arguments: $ARGUMENTS\n\nRead them as the flags `--root`, `--owner` (repeatable), `--repo`\n(repeatable), `--audit-only`, `--pr`, and `--push`. Any text after the flags is\nthe user's request, not an error: act on it. The argument string and any pasted text (PR titles, logs, the\nrequest itself) never go into a Bash command. Only single values you\nextract (action, version, repository path or slug, owner) do, and only\nwhen each holds nothing but letters, digits and `. _ - \u002F @ + ~`;\nstop and name any other value instead of writing it into a command. `..\u002F..\u002Fscripts\u002Ffleet.py`\nand `..\u002F..\u002Fscripts\u002Fpins.py` resolve from this skill's directory; print each\nabsolute path once and write it literally in each command.\n\n## Procedure\n\nThis skill supplies the scope and the fan-out.\n\n### 1. Scope\n\nDefault scope is the current repository. `--root` audits every git\nrepository beneath a directory, found by `fleet.py discover`; `--owner` keeps\nonly those whose remote belongs to the given accounts or organisations;\n`--repo` names individual ones by path or slug. A slug with no clone is audited\nread-only. Under `--root` without `--owner`, list each discovered\nrepository with its owner in the plan before any write. The scope rule and\nthe slug-only read are in\n`..\u002F..\u002Freferences\u002Faction-pinning.md`.\n\n### 2. Inventory and verify\n\nRun the inventory and verification phases across the whole scope before\ntouching anything, one repository at a time by its own path or slug (never\nthe current directory), so a dangling ref is never written fleet-wide. Also\nlist open dependabot pull requests per repository for the close-out,\nwith `pins.py pulls \u003Cslug>` as `..\u002F..\u002Freferences\u002Fdependabot-closeout.md`\nshows. A failed `gh` call means none can be listed; say so.\n\n### 3. Research, one chain per distinct upgrade\n\nGroup the work by upgrade chain rather than by repository: twenty\nrepositories moving `actions\u002Fcheckout` from the same major share one\npiece of research. Dispatch a subagent per chain where the host\nsupports it. Validate every release URL before it reaches a commit\nmessage.\n\n### 4. Orchestration plan\n\nEnter plan mode before the first edit. In Claude Code call `EnterPlanMode`;\nin Cursor, Codex, or Gemini use `\u002Fplan` or `Shift+Tab`.\nWhere plan mode is unavailable, present the plan as text.\n\nPresent the plan the skill defines, including the PRs to close, and wait\nfor approval. With `--audit-only`, stop here and report; nothing is\nwritten. Exit plan mode before committing.\n\n### 5. Commit\n\nOne commit per repository and action, one repository at a time, edited,\nstaged, committed and pushed as `..\u002F..\u002Freferences\u002Fcommit-and-push.md`\ndirects. With `--push`, push as each repository completes so an\ninterrupted run resumes; otherwise report each local branch holding\ncommits and print its push command. With `--pr`, branch, push, and open a pull request per repository, then close\ndependabot pull requests only after those merge. Write commit messages,\npull-request comments, and the report per `..\u002F..\u002Freferences\u002Fprose-rules.md`.\n\n### 6. Verify and close out\n\nWatch every CI run per repository and attribute failures before\nblaming the bumps. Then close the dependabot pull requests per the closing\nprotocol: show the user the exact commands for every PR the protocol maps\nto a commit or to obsolete, and run them only after the user confirms.\n\n## Rules\n\n- No version string is written before its tag is confirmed to exist.\n- Citing dependabot follows `..\u002F..\u002Freferences\u002Fdependabot-closeout.md`.\n- A fleet-wide claim is verified per repository before it enters that\n  repository's commit body.\n- Report unrelated breakage; fix it only when a bump caused it.\n\n## Output\n\nReply in the completed-run shape in `..\u002F..\u002Freferences\u002Foutput-shapes.md`. The\nhero is `✓ N commits across M repos`, or `⚠ Audit only: N pins out of date`\nwith `--audit-only`. A plan-only run and a halted run (no workflows, no\n`gh`, an unverifiable tag, a PR title carrying shell syntax, PRs that\ncannot be listed or mapped) use the shapes in that file; read it before\nreplying. Under a fleet scope, a repository with an incomplete inventory is\nlisted under `## Audit` as excluded, and the run continues.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":33,"disable-model-invocation":34},[25,26,27,28,29,30,31,32],"Bash","Read","Grep","Glob","Edit","Write","Task","AskUserQuestion","[--root \u003Cdir>] [--owner \u003Cname>...] [--repo \u003Cpath|slug>...] [--audit-only] [--pr] [--push]",true,"main","5fbeb3b47beedea13813be7b7023f736a8d97a65","plugins\u002Fgithub-actions\u002Fskills\u002Fupdate-actions","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills","https:\u002F\u002Fgithub.com\u002Ftony","https:\u002F\u002Ftony.sh","lighthouse keeper","2026-11-08 17:57:34",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":34},[45,48,51],{"tool":46,"command":47},"npx","npx skills add tony\u002Fskills --skill update-actions",{"tool":49,"command":50},"bunx","bunx skills add tony\u002Fskills --skill update-actions",{"tool":52,"command":53},"pnpm","pnpm dlx skills add tony\u002Fskills --skill update-actions","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fgithub-actions\u002Fskills\u002Fupdate-actions\u002FSKILL.md",[56],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"agents\u002Fopenai.yaml","REFERENCE","参考文档",314,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fgithub-actions\u002Fskills\u002Fupdate-actions\u002Fagents\u002Fopenai.yaml",[63,70,77,84,91,98],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7E8NCSHXV2JPW4J61R0TQS7","serene-bliss","Use when asked to make a CLI --help, docs page, error message, or tooling UX more serene or calmer for developer experience; returns text, no edits.","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fserene-bliss\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7E8N87MAVJD8RRQKQB1ZPS6","review","Weave code review: run independent adversarial reviews in parallel, then synthesize findings","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7E8N402XG4ZBFNACQ413163","refine","Use when asked to refine a draft, iterate on code until cleaner, or polish a README through repeated critique and improvement.","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Frefine\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7E8N01KB86A7136P00GVKJW","prompt","Weave prompt: compare independent adversarial implementations, then adopt the single best one","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fprompt\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7E8MW7YJW2PCMDW3G9RTGNK","plan","Weave planning: compare independent adversarial plans, then synthesize the best one","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fplan\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7E8MSBYXNCV4ZYWDS4PFJXK","fix-review","Fix weave review findings: validate, add test coverage, fix, and commit each as atomic changes","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Ffix-review\u002FSKILL.md",[],[]]