[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B4BC9KM2EX0TQ3CR05QJR0":3,"skill-same:01M7B4BC9KM2EX0TQ3CR05QJR0":94},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":6,"updatedAt":37,"install":38,"resources":51},"01M7B4BC9KM2EX0TQ3CR05QJR0","accessibility-skills",null,"Static, dependency-free WCAG 2.2 code review for web markup (HTML, JSX, Vue,\nSvelte, Astro) and CSS. Checks source against the a11yproject.com checklist\n(mapped to WCAG 2.2 success criteria) and grades each finding by evidence basis\n(verified \u002F flagged \u002F human-required) and severity (critical\u002Fserious\u002Fmoderate\u002F\nminor). No browser, no npm CLI, no network access — pure Read\u002FGrep over source,\nso it works in any repo immediately. Use for \"review this component for\naccessibility\", \"check this page\u002FPR for a11y issues\", \"is this markup WCAG\ncompliant\", or before merging a UI change. It cannot verify computed contrast,\nactual keyboard\u002Fscreen-reader behavior, or anything needing a rendered page —\nthose get flagged for a real scanner (e.g. axe-core) or human\u002FAT testing, not\nguessed at.","dfadler\u002Fagent-config","dfadler","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F728299?v=4","01M7B4BA8FAJ5P24T90G3PC8TY","Dustin Fadler","01M7B4BA97E5D2066FW0XMDQQY",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Faccessibility-skills\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Faccessibility-skills\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: accessibility-skills\ndescription: |\n  Static, dependency-free WCAG 2.2 code review for web markup (HTML, JSX, Vue,\n  Svelte, Astro) and CSS. Checks source against the a11yproject.com checklist\n  (mapped to WCAG 2.2 success criteria) and grades each finding by evidence basis\n  (verified \u002F flagged \u002F human-required) and severity (critical\u002Fserious\u002Fmoderate\u002F\n  minor). No browser, no npm CLI, no network access — pure Read\u002FGrep over source,\n  so it works in any repo immediately. Use for \"review this component for\n  accessibility\", \"check this page\u002FPR for a11y issues\", \"is this markup WCAG\n  compliant\", or before merging a UI change. It cannot verify computed contrast,\n  actual keyboard\u002Fscreen-reader behavior, or anything needing a rendered page —\n  those get flagged for a real scanner (e.g. axe-core) or human\u002FAT testing, not\n  guessed at.\nargument-hint: \"[file|directory|diff] [--level AA|AAA]\"\nallowed-tools: Read, Grep, Glob, Bash\nlicense: Apache-2.0\nmetadata:\n  version: \"0.1.0\"\n---\n\nAdapted from [The A11Y Project](https:\u002F\u002Fwww.a11yproject.com\u002Fchecklist\u002F) (checklist\ncontent, Apache-2.0) and [AccessLint](https:\u002F\u002Fgithub.com\u002FAccessLint\u002Fskills)\n(evidence-basis\u002Fseverity grading approach, MIT). See `NOTICE.md` for\nprovenance.\n\nThis skill locates and grades; it doesn't fix (hand findings to the user or a\nfollow-up edit) and it doesn't scan a live page (hand that to axe-core or a\nbrowser-based tool). Say which you did and didn't do.\n\n## Reference material\n\n- [`references\u002Fchecklist.md`](references\u002Fchecklist.md) — the WCAG 2.2 checklist\n  items, organized by content area (images, headings, forms, color contrast,\n  etc.), each mapped to its success criterion. Grep it for a keyword rather than\n  reading it end to end.\n- [`references\u002Fgrading.md`](references\u002Fgrading.md) — the evidence-basis (●\u002F◐\u002F○)\n  and severity grading rules, adapted for what static source alone can support.\n  Read it before writing findings; the rules that always apply are summarized\n  below.\n\n## Grading, in brief\n\nEvery finding gets two independent grades:\n\n- **Evidence basis**: ● verified (a deterministic fact from source that's also a\n  real conformance failure: a missing attribute, wrong element, positive\n  `tabindex`) · ◐ flagged (real evidence, but confirming the failure needs\n  computed styles, a rendered page, or a judgment call — a heading-rank skip or\n  `autofocus` is a verifiable *fact* but not an automatic failure, see\n  `references\u002Fchecklist.md`'s Advisory section) · ○ human-required (needs a\n  screen reader or lived experience).\n- **Severity**: critical (blocks a core task) · serious (major barrier) ·\n  moderate (friction, still completable) · minor (polish).\n\nWhen unsure between two evidence grades, use the lower one. Full definitions and\nworked examples are in `references\u002Fgrading.md`.\n\n## Procedure\n\n1. **Scope.** `$ARGUMENTS` is a file, directory, or diff (`git diff`, a PR's\n   changed files) to review, plus an optional `--level AA|AAA` (default AA — AAA\n   items in the checklist are still worth flagging as informational at AA).\n   Given nothing, ask what to review rather than sweeping the whole repo\n   unprompted.\n2. **Read the target.** For a diff, review the changed lines plus enough\n   surrounding markup to judge structure (a changed `\u003Cdiv>` needs its parent to\n   judge heading\u002Flandmark context). For a directory, find markup\u002Ftemplate files\n   via Glob rather than assuming a framework.\n3. **Check against the checklist.** Work through `references\u002Fchecklist.md` by\n   category, but only the categories relevant to what's actually present in the\n   target (no `\u003Ctable>` in the diff → skip the Tables section; note it as N\u002FA,\n   not silently dropped). Grep the source for the syntactic signals each item\n   implies (missing `alt=`, `\u003Cdiv onClick`, un-labeled `\u003Cinput`, skipped heading\n   levels, `autofocus`, positive `tabindex`, literal low-contrast color pairs)\n   rather than reading every line by eye.\n4. **Grade each finding** per `references\u002Fgrading.md`. Cite file:line and the\n   exact snippet for every finding; never fabricate a location.\n   Computed contrast (even a literal color pair like `#999` on white) and\n   `autofocus` always go under Flagged, never Verified; only a missing\n   attribute, wrong element or positive `tabindex` is Verified.\n5. **Report.**\n\n```\n# Accessibility review — \u003Ctarget>\nWCAG 2.2 Level \u003CAA|AAA> · static source review (no browser, no live scan)\n\nSeverity: \u003Cc> critical · \u003Cs> serious · \u003Cm> moderate · \u003Cn> minor\nBasis: ● \u003Cv> verified · ◐ \u003Cf> flagged · ○ \u003Ch> human-required\nChecklist categories reviewed: \u003Clist>   ·   N\u002FA (not present in target): \u003Clist>\n\n## ● Verified\n- [severity] \u003Cwhat> — SC \u003Cx.x.x>\n    where: \u003Cfile>:\u003Cline> — `\u003Csnippet>`\n    fix: \u003Cmechanical change> | TODO(\u003CSC>): needs judgment (\u003Cwhat a human decides>)\n\n## ◐ Flagged\n- [severity] \u003Cwhat> — SC \u003Cx.x.x>\n    where: \u003Cfile>:\u003Cline> — `\u003Csnippet>`\n    confirm with: \u003Cspecific check — e.g. \"axe-core color-contrast rule\", \"render at 200% zoom\">\n\n## ○ Human-required\n- \u003Cwhat only AT or lived experience reveals> — SC \u003Cx.x.x>\n    needs: \u003Cfunctional ability + assistive technology>\n    where: \u003Cfile>:\u003Cline> (context, not proof)\n\n## Not covered by this review\n- Computed contrast, actual keyboard\u002Fscreen-reader behavior, anything needing a\n  rendered page — recommend axe-core\u002FLighthouse and human\u002FAT testing for these.\n```\n\nCopy the `Checklist categories reviewed:` line verbatim, label included; do not\nshorten it to `Categories reviewed:`.\n\nSpend the report's words on findings and handoffs; a clean category is its name\nin \"reviewed,\" not a paragraph. Don't let \"not present in target\" (N\u002FA) or \"not\ncovered by this review\" read as \"passed\" — they're honestly different things.\n\n## Notes\n\n- This skill never edits files. For remediation, hand the ● findings' mechanical\n  fixes to a normal edit, and leave the TODOs for a human.\n- For live-DOM scanning (real contrast, real keyboard traps, real screen-reader\n  output), recommend axe-core (open-source) in CI\u002FPlaywright, or a manual\n  keyboard-and-screen-reader pass — don't simulate what only a browser or a\n  person can confirm.\n","Adapted from [The A11Y Project](https:\u002F\u002Fwww.a11yproject.com\u002Fchecklist\u002F) (checklist\ncontent, Apache-2.0) and [AccessLint](https:\u002F\u002Fgithub.com\u002FAccessLint\u002Fskills)\n(evidence-basis\u002Fseverity grading approach, MIT). See `NOTICE.md` for\nprovenance.\n\nThis skill locates and grades; it doesn't fix (hand findings to the user or a\nfollow-up edit) and it doesn't scan a live page (hand that to axe-core or a\nbrowser-based tool). Say which you did and didn't do.\n\n## Reference material\n\n- [`references\u002Fchecklist.md`](references\u002Fchecklist.md) — the WCAG 2.2 checklist\n  items, organized by content area (images, headings, forms, color contrast,\n  etc.), each mapped to its success criterion. Grep it for a keyword rather than\n  reading it end to end.\n- [`references\u002Fgrading.md`](references\u002Fgrading.md) — the evidence-basis (●\u002F◐\u002F○)\n  and severity grading rules, adapted for what static source alone can support.\n  Read it before writing findings; the rules that always apply are summarized\n  below.\n\n## Grading, in brief\n\nEvery finding gets two independent grades:\n\n- **Evidence basis**: ● verified (a deterministic fact from source that's also a\n  real conformance failure: a missing attribute, wrong element, positive\n  `tabindex`) · ◐ flagged (real evidence, but confirming the failure needs\n  computed styles, a rendered page, or a judgment call — a heading-rank skip or\n  `autofocus` is a verifiable *fact* but not an automatic failure, see\n  `references\u002Fchecklist.md`'s Advisory section) · ○ human-required (needs a\n  screen reader or lived experience).\n- **Severity**: critical (blocks a core task) · serious (major barrier) ·\n  moderate (friction, still completable) · minor (polish).\n\nWhen unsure between two evidence grades, use the lower one. Full definitions and\nworked examples are in `references\u002Fgrading.md`.\n\n## Procedure\n\n1. **Scope.** `$ARGUMENTS` is a file, directory, or diff (`git diff`, a PR's\n   changed files) to review, plus an optional `--level AA|AAA` (default AA — AAA\n   items in the checklist are still worth flagging as informational at AA).\n   Given nothing, ask what to review rather than sweeping the whole repo\n   unprompted.\n2. **Read the target.** For a diff, review the changed lines plus enough\n   surrounding markup to judge structure (a changed `\u003Cdiv>` needs its parent to\n   judge heading\u002Flandmark context). For a directory, find markup\u002Ftemplate files\n   via Glob rather than assuming a framework.\n3. **Check against the checklist.** Work through `references\u002Fchecklist.md` by\n   category, but only the categories relevant to what's actually present in the\n   target (no `\u003Ctable>` in the diff → skip the Tables section; note it as N\u002FA,\n   not silently dropped). Grep the source for the syntactic signals each item\n   implies (missing `alt=`, `\u003Cdiv onClick`, un-labeled `\u003Cinput`, skipped heading\n   levels, `autofocus`, positive `tabindex`, literal low-contrast color pairs)\n   rather than reading every line by eye.\n4. **Grade each finding** per `references\u002Fgrading.md`. Cite file:line and the\n   exact snippet for every finding; never fabricate a location.\n   Computed contrast (even a literal color pair like `#999` on white) and\n   `autofocus` always go under Flagged, never Verified; only a missing\n   attribute, wrong element or positive `tabindex` is Verified.\n5. **Report.**\n\n```\n# Accessibility review — \u003Ctarget>\nWCAG 2.2 Level \u003CAA|AAA> · static source review (no browser, no live scan)\n\nSeverity: \u003Cc> critical · \u003Cs> serious · \u003Cm> moderate · \u003Cn> minor\nBasis: ● \u003Cv> verified · ◐ \u003Cf> flagged · ○ \u003Ch> human-required\nChecklist categories reviewed: \u003Clist>   ·   N\u002FA (not present in target): \u003Clist>\n\n## ● Verified\n- [severity] \u003Cwhat> — SC \u003Cx.x.x>\n    where: \u003Cfile>:\u003Cline> — `\u003Csnippet>`\n    fix: \u003Cmechanical change> | TODO(\u003CSC>): needs judgment (\u003Cwhat a human decides>)\n\n## ◐ Flagged\n- [severity] \u003Cwhat> — SC \u003Cx.x.x>\n    where: \u003Cfile>:\u003Cline> — `\u003Csnippet>`\n    confirm with: \u003Cspecific check — e.g. \"axe-core color-contrast rule\", \"render at 200% zoom\">\n\n## ○ Human-required\n- \u003Cwhat only AT or lived experience reveals> — SC \u003Cx.x.x>\n    needs: \u003Cfunctional ability + assistive technology>\n    where: \u003Cfile>:\u003Cline> (context, not proof)\n\n## Not covered by this review\n- Computed contrast, actual keyboard\u002Fscreen-reader behavior, anything needing a\n  rendered page — recommend axe-core\u002FLighthouse and human\u002FAT testing for these.\n```\n\nCopy the `Checklist categories reviewed:` line verbatim, label included; do not\nshorten it to `Categories reviewed:`.\n\nSpend the report's words on findings and handoffs; a clean category is its name\nin \"reviewed,\" not a paragraph. Don't let \"not present in target\" (N\u002FA) or \"not\ncovered by this review\" read as \"passed\" — they're honestly different things.\n\n## Notes\n\n- This skill never edits files. For remediation, hand the ● findings' mechanical\n  fixes to a normal edit, and leave the TODOs for a human.\n- For live-DOM scanning (real contrast, real keyboard traps, real screen-reader\n  output), recommend axe-core (open-source) in CI\u002FPlaywright, or a manual\n  keyboard-and-screen-reader pass — don't simulate what only a browser or a\n  person can confirm.\n",{"name":5,"license":15,"metadata":25,"description":27,"allowed-tools":28,"argument-hint":29},{"version":26},"0.1.0","Static, dependency-free WCAG 2.2 code review for web markup (HTML, JSX, Vue,\nSvelte, Astro) and CSS. Checks source against the a11yproject.com checklist\n(mapped to WCAG 2.2 success criteria) and grades each finding by evidence basis\n(verified \u002F flagged \u002F human-required) and severity (critical\u002Fserious\u002Fmoderate\u002F\nminor). No browser, no npm CLI, no network access — pure Read\u002FGrep over source,\nso it works in any repo immediately. Use for \"review this component for\naccessibility\", \"check this page\u002FPR for a11y issues\", \"is this markup WCAG\ncompliant\", or before merging a UI change. It cannot verify computed contrast,\nactual keyboard\u002Fscreen-reader behavior, or anything needing a rendered page —\nthose get flagged for a real scanner (e.g. axe-core) or human\u002FAT testing, not\nguessed at.\n","Read, Grep, Glob, Bash","[file|directory|diff] [--level AA|AAA]","main","a924e3abb0a831866902dd0835353e108826e0a3","plugins\u002Faccessibility-skills",0,"https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config","https:\u002F\u002Fgithub.com\u002Fdfadler","http:\u002F\u002Fdfadler.com","2026-11-15 05:22:24",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add dfadler\u002Fagent-config --skill accessibility-skills",{"tool":44,"command":45},"bunx","bunx skills add dfadler\u002Fagent-config --skill accessibility-skills",{"tool":47,"command":48},"pnpm","pnpm dlx skills add dfadler\u002Fagent-config --skill accessibility-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Faccessibility-skills\u002FSKILL.md",true,[52,58,62,66,70,74,78,82,86,90],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},".claude-plugin\u002Fplugin.json","REFERENCE","参考文档",705,"https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Faccessibility-skills\u002F.claude-plugin\u002Fplugin.json",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"evals\u002Faccessibility-skills-does-not-certify-compliance\u002Fcase.yaml",3327,"https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Faccessibility-skills\u002Fevals\u002Faccessibility-skills-does-not-certify-compliance\u002Fcase.yaml",{"path":63,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":64,"sourceHtmlUrl":65},"evals\u002Faccessibility-skills-reviews-component\u002Fcase.yaml",4885,"https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Faccessibility-skills\u002Fevals\u002Faccessibility-skills-reviews-component\u002Fcase.yaml",{"path":67,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":68,"sourceHtmlUrl":69},"evals\u002Faccessibility-skills-reviews-stylesheet\u002Fcase.yaml",3154,"https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Faccessibility-skills\u002Fevals\u002Faccessibility-skills-reviews-stylesheet\u002Fcase.yaml",{"path":71,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":72,"sourceHtmlUrl":73},"evals\u002Faccessibility-skills-stays-quiet-on-aria-question\u002Fcase.yaml",2331,"https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Faccessibility-skills\u002Fevals\u002Faccessibility-skills-stays-quiet-on-aria-question\u002Fcase.yaml",{"path":75,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":76,"sourceHtmlUrl":77},"evals\u002Faccessibility-skills-stays-quiet-on-render-perf\u002Fcase.yaml",2721,"https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Faccessibility-skills\u002Fevals\u002Faccessibility-skills-stays-quiet-on-render-perf\u002Fcase.yaml",{"path":79,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":16},"LICENSE","许可证",11357,{"path":83,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":84,"sourceHtmlUrl":85},"NOTICE.md",3199,"https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Faccessibility-skills\u002FNOTICE.md",{"path":87,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fchecklist.md",12356,"https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Faccessibility-skills\u002Freferences\u002Fchecklist.md",{"path":91,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fgrading.md",5275,"https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Faccessibility-skills\u002Freferences\u002Fgrading.md",[95,103,110,117,124,131],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":99,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":20},"01M7B4V2WXAHE2FC90KSD4GKRV","youtube-transcript","ALWAYS invoke before fetching a transcript, captions or description for a\nYouTube video, even when only asked how you would get them. Given a YouTube\nURL (youtube.com\u002Fwatch, youtu.be, shorts), save the video's English\nauto-captions as plain text and its description to files with `yt-dlp`, and\nprint the title, channel and duration. Use when asked to \"get the transcript\nfor this video\", \"grab the captions\", \"summarize this YouTube video\", \"put\nthese videos' transcripts in an artifact\", or when a YouTube link is pasted\nand its spoken content is needed. Do not drive the browser's transcript panel\nor try `youtube-transcript-api` first: both were tried and are slower or\nempty.","MIT","https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Fyoutube-transcript\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":99,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":20},"01M7B4TNSGRRKJZ9A5B9TSRCC3","git-worktree-usage","Load this before pushing to, or opening a PR from, a branch whose earlier PR\nalready merged (a squash merge leaves its commits off the default branch, so\na new PR from it shows stale history), even when only advising: it defines\nthe fresh-branch and cherry-pick fix.\nCreate worktrees with the `EnterWorktree` tool, never raw `git worktree add`.\nGit worktree and branch mechanics for isolating non-trivial work: locking and\nthe stale-worktree sweep, picking what to parallelize by file surface, the\nrepo-wide `git stash` collision hazard and its `git restore` alternative,\nbranch naming, catching a branch up to a moved `main` via merge (not\nrebase), CI\u002Fcoverage gotchas after a merge, conflict-resolution escalation\nlevels, and PR-splitting sequencing. Also ships two SessionStart hooks that\nself-heal a project's own symlinked-worktree-directory convention and\nauto-prune merged worktrees, and a commit-branch guard hook that asks before\na git commit lands on the default or an unrelated checked-out branch. Use when creating, entering, or cleaning up a\ngit worktree, including before starting work in an existing worktree that\nanother session may be using; deciding how to parallelize agent sessions across a repo;\nhitting a `git stash` collision between sessions; resolving a merge\u002Frebase\nconflict; splitting an already-written diff into multiple PRs; or a stale\nor wrongly-linked worktree directory needs diagnosing. Do not use for a\nplain `git stash` in a single clone with no other worktrees or sessions,\nfor rewriting an unpushed branch's history, or for running commands in a\nworktree the user just created.","https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Fworktree-core\u002Fskills\u002Fgit-worktree-usage\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":99,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":20},"01M7B4SGD3481322E9ZDQAFMTK","url-to-audio","ALWAYS invoke before answering any request to narrate or convert a URL or\narticle to audio, even when only asked what you would do or which backend you\nwould use (including when `OPENAI_API_KEY` is unset and the fallback is `say`).\nTurn a web article into a narrated audio file: fetch the page, extract the\nclean reading text, and synthesize it with macOS `say` by default (free,\nlocal, already installed, no API key) or OpenAI TTS optionally (when\n`OPENAI_API_KEY` is set and a `say` voice isn't good enough). Voice and\nspeed are configurable per call, with env var defaults. Produces a\n`.m4a`\u002F`.mp3` file at a predictable path and prints it. Use when asked to\n\"read this article to me\", \"convert this page\u002FURL to audio\", \"make an\naudio version of this link\", or \"text-to-speech this article\" — including\nwhen asked only for the commands or plan, or when `OPENAI_API_KEY` is unset.","https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Furl-to-audio\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":99,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":20},"01M7B4RKYJQ16XGH8GR1WQ69ZT","subagent-orchestration","Use FIRST, before answering or planning, whenever the user hands over a list of two\nor more separate tasks (\"do A, B and C\", numbered or in no order) that each need real\nexploration, even if they only ask how you would tackle them: it triages which can run\nas parallel sub-agents and which must stay serial. Also use when asked how to\nconfigure a sub-agent already chosen for a large search or exploration (agent type,\nmodel tier), and when about to spawn a sub-agent, fan out with the Workflow tool, or run a task\nthat would put large tool output (more than ~50 lines, or ~3 file reads) into the\nmain context. Routes the work to the main context, a single Agent call, or a\nWorkflow; defines the compact handback a delegated agent should return; and picks\nthe model tier. Use for \"should I delegate this\", \"which agent do I use\", or\n\"keep my context small\".","https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Fsubagent-orchestration\u002FSKILL.md",[],[],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":99,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":20},"01M7B4Q35VB7TKPF3Z3KA4E0YB","config","Internal primitive that reads YAML frontmatter from vault config files via\nmcp__obsidian__* tools, and returns it as merged key-value data. Not a\nuser-facing slash command — this skill is never triggered by a user\nrequest directly; other agent-config skills (screen-capture, and\nsecond-brain's own capture\u002Fquery skills) invoke it to load their own\nsettings. Degrades to an empty config, never a hard failure, when the\nObsidian MCP is disconnected or the config file doesn't exist. Parse\n`$ARGUMENTS` as `\u003Cskill-name> [project-name]`.","https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Fsecond-brain\u002Fskills\u002Fconfig\u002FSKILL.md",[],[],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":99,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":20},"01M7B4PQ6KE886C346DH55GESM","lighthouse","Run a Lighthouse CLI pass (mobile + desktop) against a URL and store the results in the second-brain vault under knowledge\u002Flighthouse\u002F\u003Cproject>\u002F. ALWAYS invoke this skill first when asked to run, repeat or script a Lighthouse pass or performance\u002Faccessibility audit against a URL, before writing any `lighthouse` command, including when the config disables it (it defines the no-op behaviour). Complements, not replaces, a manual responsive resize-and-look pass. Not for advice about fixing a Lighthouse finding. Config-driven: which form factors run, whether the skill runs at all, and where results land are all controlled by lighthouse_enabled, lighthouse_form_factors, and lighthouse_output_dir.","https:\u002F\u002Fgithub.com\u002Fdfadler\u002Fagent-config\u002Fblob\u002Fmain\u002Fplugins\u002Fscreen-capture\u002Fskills\u002Flighthouse\u002FSKILL.md",[],[]]