[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M756VCF5ZERWBMARAMGYCRVP":3,"skill-same:01M756VCF5ZERWBMARAMGYCRVP":54},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":35,"ownerHtmlUrl":36,"ownerBlogUrl":37,"ownerDescription":38,"updatedAt":39,"install":40,"resources":53},"01M756VCF5ZERWBMARAMGYCRVP","using-adept",null,"Use the `adept` CLI to author AI skills once and render them into Claude Code, Cursor, Codex, Copilot, and OpenCode. Apply when installing\u002Fsyncing skills, editing skill.yaml\u002FSKILL.md, or touching .adeptability\u002F.","itaywol\u002Fadeptability","itaywol","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6410154?v=4","01M756SKJABTDMYHWVMHBA0M6E","Itay Wolfish","01M756SKKJFSV073PS3KYR896D",9,"MIT","https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability\u002Fblob\u002Fmain\u002F.adeptability\u002Fskills\u002Fusing-adept\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nid: using-adept\ndescription: \"Use the `adept` CLI to author AI skills once and render them into Claude Code, Cursor, Codex, Copilot, and OpenCode. Apply when installing\u002Fsyncing skills, editing skill.yaml\u002FSKILL.md, or touching .adeptability\u002F.\"\nactivation: agent\nallowed-tools:\n  - \"Bash\"\n  - \"Read\"\n  - \"Edit\"\n  - \"Write\"\n---\n\n# Using the `adept` CLI\n\n`adept` makes one AI skill portable across every coding harness. You **author once** in a\ncanonical format; `adept` **renders accurately** into each harness's native layout and keeps\nboth sides in sync.\n\n## Mental model\n\n```\ncanonical skill  ──render──▶  .claude\u002Fskills\u002F…   (per-skill)\n(.adeptability\u002F  ──render──▶  .cursor\u002Frules\u002F….mdc (single-file)\n skills\u002F\u003Cid>\u002F    ──render──▶  AGENTS.md            (Codex aggregate)\n SKILL.md)       ──render──▶  .github\u002Finstructions (Copilot aggregate)\n                 ◀─sync-from─  (adopt edits made directly in a harness file)\n```\n\n- **Identity is `(id, content-hash)`** — there are no version numbers. The hash decides\n  whether something changed.\n- A skill is a directory `\u003Croot>\u002Fskills\u002F\u003Cid>\u002F` with one `SKILL.md` (YAML frontmatter +\n  markdown body) and optional sidecars (`scripts\u002F`, `references\u002F`, `assets\u002F`).\n- The **filesystem is the source of truth.** `config.json` only records which harnesses are\n  enabled, the materialization mode, and library remotes.\n\n## Canonical SKILL.md format\n\n```markdown\n---\nid: pr-review                 # ^[a-z0-9](?:[a-z0-9-]{0,48}[a-z0-9])?$ — matches the directory name\ndescription: Use before opening a PR. Tests, security, performance.   # \u003C= 280 chars\nactivation: agent             # always | globs | agent | manual\nglobs: []                     # REQUIRED when activation: globs\nallowed-tools: [Read, Grep]   # carried into Claude Code\ntargets: []                   # empty = all enabled harnesses\ntags: [review, quality]\n---\n# PR Review Checklist\n- [ ] Tests added or updated\n- [ ] No secrets in the diff\n```\n\n## The commands you'll use most\n\n```bash\nadept init                       # scaffold .adeptability\u002F in the current project\nadept init --from \u003Cgit-url>      # …and clone a remote skill library to pull skills from\nadept harness add \u003Cid>           # enable a harness (claude-code | cursor | codex | copilot | opencode)\nadept sync                       # render canonical skills → every enabled harness\nadept status                     # init state, libraries, harnesses, and drift at a glance\nadept diff                       # show exactly what differs between canonical and rendered\nadept sync-from                  # adopt edits made directly in a harness file back to canonical\nadept skill add \u003Cid> --edit      # scaffold a new skill and open $EDITOR\nadept skill install \u003Cowner>\u002F\u003Crepo>\u002F\u003Cskill>   # install one skill from GitHub\u002Fskills.sh (pinned to a SHA)\n```\n\n**`adept --help` is the source of truth for the command surface** — it's always current, so\nprefer it over memory. `adept --help` lists every verb; `adept \u003Ccommand> --help` (e.g.\n`adept skill --help`, `adept sync --help`) shows that command's subcommands and flags. Global\nflags on every command: `--json`, `--log-level debug|info|warn|error`, `--project \u003Cpath>`,\n`--library \u003Cpath>`.\n\n## Typical tasks\n\n**Start fresh, author your own skills**\n```bash\nadept init\nadept skill add lint-style --edit\nadept harness add claude-code\nadept harness add cursor\nadept sync\n```\n\n**Adopt a project that already has harness files** (`.claude\u002F`, `.cursor\u002F`, `AGENTS.md`, …)\n```bash\nadept init        # auto-detects and adopts existing harness skills into canonical\nadept status      # confirm what got adopted\nadept diff        # confirm the round-trip is clean\n```\n\n**Pull skills from a shared library**\n```bash\nadept init --from git@github.com:my-org\u002Fskills.git\nadept harness add claude-code\nadept sync\n```\n\n**Install one vetted skill from the ecosystem**\n```bash\nadept skill search find-skills\nadept skill info  vercel-labs\u002Fskills\u002Ffind-skills    # repo, stars, license, SHA, installs\nadept skill install vercel-labs\u002Fskills\u002Ffind-skills  # preview + safety scan + y\u002FN\n```\n\n## Rules of thumb (so you don't surprise the user)\n\n- **Edit canonical, then `adept sync`.** Don't hand-edit rendered files like\n  `.cursor\u002Frules\u002F*.mdc` — they're regenerated. If you must edit a harness file directly, run\n  `adept sync-from` to pull the change back into canonical.\n- **Run `adept status` \u002F `adept diff` before and after** a sync so you can report what changed.\n- **Installs are gated.** `adept skill install` runs a safety scan and shows a preview; a\n  `critical` finding blocks the install unless the user passes `--allow-unsafe`. Never pass\n  `--allow-unsafe` or `--yes` on the user's behalf without explicit confirmation.\n- **Exit codes are meaningful:** `0` clean, `1` error, `2` drift\u002Fdirty or merge conflict.\n  Scan severities map the same way (`high` → 1, `critical` → 2).\n- **Secrets stay in the environment.** Provider API keys are read from the environment at\n  call time; adept never writes them to `config.json`.\n- Aggregator harnesses (Codex\u002FCopilot) have a **byte budget** — if skills overflow it,\n  the lowest-priority ones are dropped and a truncation note is written. Check `adept status`.\n","# Using the `adept` CLI\n\n`adept` makes one AI skill portable across every coding harness. You **author once** in a\ncanonical format; `adept` **renders accurately** into each harness's native layout and keeps\nboth sides in sync.\n\n## Mental model\n\n```\ncanonical skill  ──render──▶  .claude\u002Fskills\u002F…   (per-skill)\n(.adeptability\u002F  ──render──▶  .cursor\u002Frules\u002F….mdc (single-file)\n skills\u002F\u003Cid>\u002F    ──render──▶  AGENTS.md            (Codex aggregate)\n SKILL.md)       ──render──▶  .github\u002Finstructions (Copilot aggregate)\n                 ◀─sync-from─  (adopt edits made directly in a harness file)\n```\n\n- **Identity is `(id, content-hash)`** — there are no version numbers. The hash decides\n  whether something changed.\n- A skill is a directory `\u003Croot>\u002Fskills\u002F\u003Cid>\u002F` with one `SKILL.md` (YAML frontmatter +\n  markdown body) and optional sidecars (`scripts\u002F`, `references\u002F`, `assets\u002F`).\n- The **filesystem is the source of truth.** `config.json` only records which harnesses are\n  enabled, the materialization mode, and library remotes.\n\n## Canonical SKILL.md format\n\n```markdown\n---\nid: pr-review                 # ^[a-z0-9](?:[a-z0-9-]{0,48}[a-z0-9])?$ — matches the directory name\ndescription: Use before opening a PR. Tests, security, performance.   # \u003C= 280 chars\nactivation: agent             # always | globs | agent | manual\nglobs: []                     # REQUIRED when activation: globs\nallowed-tools: [Read, Grep]   # carried into Claude Code\ntargets: []                   # empty = all enabled harnesses\ntags: [review, quality]\n---\n# PR Review Checklist\n- [ ] Tests added or updated\n- [ ] No secrets in the diff\n```\n\n## The commands you'll use most\n\n```bash\nadept init                       # scaffold .adeptability\u002F in the current project\nadept init --from \u003Cgit-url>      # …and clone a remote skill library to pull skills from\nadept harness add \u003Cid>           # enable a harness (claude-code | cursor | codex | copilot | opencode)\nadept sync                       # render canonical skills → every enabled harness\nadept status                     # init state, libraries, harnesses, and drift at a glance\nadept diff                       # show exactly what differs between canonical and rendered\nadept sync-from                  # adopt edits made directly in a harness file back to canonical\nadept skill add \u003Cid> --edit      # scaffold a new skill and open $EDITOR\nadept skill install \u003Cowner>\u002F\u003Crepo>\u002F\u003Cskill>   # install one skill from GitHub\u002Fskills.sh (pinned to a SHA)\n```\n\n**`adept --help` is the source of truth for the command surface** — it's always current, so\nprefer it over memory. `adept --help` lists every verb; `adept \u003Ccommand> --help` (e.g.\n`adept skill --help`, `adept sync --help`) shows that command's subcommands and flags. Global\nflags on every command: `--json`, `--log-level debug|info|warn|error`, `--project \u003Cpath>`,\n`--library \u003Cpath>`.\n\n## Typical tasks\n\n**Start fresh, author your own skills**\n```bash\nadept init\nadept skill add lint-style --edit\nadept harness add claude-code\nadept harness add cursor\nadept sync\n```\n\n**Adopt a project that already has harness files** (`.claude\u002F`, `.cursor\u002F`, `AGENTS.md`, …)\n```bash\nadept init        # auto-detects and adopts existing harness skills into canonical\nadept status      # confirm what got adopted\nadept diff        # confirm the round-trip is clean\n```\n\n**Pull skills from a shared library**\n```bash\nadept init --from git@github.com:my-org\u002Fskills.git\nadept harness add claude-code\nadept sync\n```\n\n**Install one vetted skill from the ecosystem**\n```bash\nadept skill search find-skills\nadept skill info  vercel-labs\u002Fskills\u002Ffind-skills    # repo, stars, license, SHA, installs\nadept skill install vercel-labs\u002Fskills\u002Ffind-skills  # preview + safety scan + y\u002FN\n```\n\n## Rules of thumb (so you don't surprise the user)\n\n- **Edit canonical, then `adept sync`.** Don't hand-edit rendered files like\n  `.cursor\u002Frules\u002F*.mdc` — they're regenerated. If you must edit a harness file directly, run\n  `adept sync-from` to pull the change back into canonical.\n- **Run `adept status` \u002F `adept diff` before and after** a sync so you can report what changed.\n- **Installs are gated.** `adept skill install` runs a safety scan and shows a preview; a\n  `critical` finding blocks the install unless the user passes `--allow-unsafe`. Never pass\n  `--allow-unsafe` or `--yes` on the user's behalf without explicit confirmation.\n- **Exit codes are meaningful:** `0` clean, `1` error, `2` drift\u002Fdirty or merge conflict.\n  Scan severities map the same way (`high` → 1, `critical` → 2).\n- **Secrets stay in the environment.** Provider API keys are read from the environment at\n  call time; adept never writes them to `config.json`.\n- Aggregator harnesses (Codex\u002FCopilot) have a **byte budget** — if skills overflow it,\n  the lowest-priority ones are dropped and a truncation note is written. Check `adept status`.\n",{"id":5,"activation":24,"description":7,"allowed-tools":25},"agent",[26,27,28,29],"Bash","Read","Edit","Write","main","c5b1b81b2e0ae71bd8afeeade28eaea6f8fd1bf5",".adeptability\u002Fskills\u002Fusing-adept",0,"https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability","https:\u002F\u002Fpkg.go.dev\u002Fgithub.com\u002Fitaywol\u002Fadeptability","https:\u002F\u002Fgithub.com\u002Fitaywol","https:\u002F\u002Fitaywol.com","Founding Engineer @ Echo","2026-07-25 15:28:37",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add itaywol\u002Fadeptability --skill using-adept",{"tool":46,"command":47},"bunx","bunx skills add itaywol\u002Fadeptability --skill using-adept",{"tool":49,"command":50},"pnpm","pnpm dlx skills add itaywol\u002Fadeptability --skill using-adept","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability\u002Fblob\u002Fmain\u002F.adeptability\u002Fskills\u002Fusing-adept\u002FSKILL.md",true,[],[55,60,66,72,78,84],{"skillNo":56,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M756YHZ76TMVP0KK718K6KN0","https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability\u002Fblob\u002Fmain\u002Fskills\u002Fusing-adept\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M756YG9YGBG4783SFH8RE5PM","agents","https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability\u002Fblob\u002Fmain\u002Fskills\u002Fagents\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M756YD5MDX9ANB4QPVN34YQX","adept-writing-tests","https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability\u002Fblob\u002Fmain\u002Fskills\u002Fadept-writing-tests\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M756YB57DN31BKNT4GHM9N2S","adept-contributing","https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability\u002Fblob\u002Fmain\u002Fskills\u002Fadept-contributing\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":6,"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},"01M756Y9VM8W6E2HWMVYH0PH6H","adept-code-style","https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability\u002Fblob\u002Fmain\u002Fskills\u002Fadept-code-style\u002FSKILL.md",[],[],{"skillNo":85,"name":5,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M756Y76FNSH8VWP77TX1A8Z1","Use the `adept` CLI to author an AI skill once and render it into Claude Code, Cursor, Codex, Copilot, OpenCode, and 45+ agents. Apply when installing\u002Fsyncing skills, editing SKILL.md, or touching .adeptability\u002F.","https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability\u002Fblob\u002Fmain\u002Finternal\u002Fdefaultskills\u002Fassets\u002Fusing-adept\u002FSKILL.md",[],[]]