[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74KJDAGFFA2PDK31455Y493":3,"skill-same:01M74KJDAGFFA2PDK31455Y493":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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M74KJDAGFFA2PDK31455Y493","skael",null,"Use the skael CLI to find, install, pull and publish agent skills from a Skael registry, and to read its exit codes. Use when a task mentions skael, a skill set, a skill registry, or when you need a skill this repo does not have.","skael-dev\u002Fskael","skael-dev","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F288426101?v=4","01M74KGJBVNY8KH0MGCJT9BY1Z","01M74KGJCCXHKGM67DPC1CJTXH",20,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fskael-dev\u002Fskael\u002Fblob\u002Fmain\u002Fskills\u002Fskael\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: skael\ndescription: Use the skael CLI to find, install, pull and publish agent skills from a Skael registry, and to read its exit codes. Use when a task mentions skael, a skill set, a skill registry, or when you need a skill this repo does not have.\n---\n\n# skael\n\n`skael` is the command line for a Skael registry. The registry holds versioned, security-scanned agent skills.\n\n## Before you start\n\nRun `skael doctor`. It reports the config, the server and each agent. `skael version` prints the CLI version.\n\nThe full command reference is at https:\u002F\u002Fskael.dev\u002Fdocs\u002Fcli. Read it for a flag this skill does not list, rather than guessing.\n\nThe CLI reads `SKAEL_URL` and `SKAEL_KEY`. If either is absent, it reads `~\u002F.skael\u002Fconfig.json`, which `skael setup \u003Curl> \u003Capi-key>` writes. Never print a key. Never write a key into a file in the repo.\n\n## Exit codes\n\nBranch on the exit code. Do not parse error text.\n\n| Code | Meaning | What to do |\n|---|---|---|\n| 0 | Success | Continue. |\n| 1 | API, network or local write error. `skael scan` also uses 1 for findings. | Read the error. Retry only if the cause is the network. |\n| 2 | Usage or config error | Fix the command or the config. A retry gives the same result. |\n| 10 | Incomplete set | `skael pull` wrote nothing. Report the excluded entries. Do not remove them from the set by yourself. |\n| 11 | Digest mismatch | `skael pull` wrote nothing. Stop and tell a person. This can mean tampering. Do not retry in a loop. |\n\n## JSON output\n\nAdd `--json` to any command when you parse the output. A read of the API prints the API's own shape. A failure prints this to stdout, and the exit code is non-zero:\n\n```json\n{\"error\": \"what failed\", \"code\": \"machine_code\", \"suggestion\": \"what to try\"}\n```\n\n## Find a skill\n\n```sh\nskael search \"\u003Cwords>\"\nskael list\nskael show \u003Cskill> --versions\n```\n\n## Follow skills on this machine\n\n`skael add` follows a skill, a pattern or a set, and installs what it resolves to. `skael sync` and the auto-sync hook keep everything followed current, so a new skill released under a followed pattern, or added to a followed set, arrives with no command.\n\n```sh\nskael add \u003Cskill>\nskael add 'payments:*'        # every released skill under payments:\nskael add --set \u003Cname>\nskael sync\nskael remove \u003Cskill>          # or 'payments:*', or --set \u003Cname>\n```\n\nQuote a pattern so the shell does not expand it. Skills go to `.agents\u002Fskills`, and also to `.claude\u002Fskills` when Claude Code is detected. `--scope user` writes under your home folder instead of the repo.\n\n`remove` stops following a source. A skill another followed source still wants stays.\n\nWhen two followed sources want different versions of one skill, `add` exits 2 and names both. Remove one of them; do not pin around it.\n\n## Write a set once\n\nA set is a named list of skills. An entry is a skill at its latest version, a skill at one exact version, a pattern such as `payments:*`, `*` for every released skill, or an exclusion such as `!payments:legacy`. Use `pull` when a repo, a CI run or a machine needs a known group of skills written once.\n\n```sh\nskael sets list\nskael sets get \u003Cname>\nskael sets resolve \u003Cname>\nskael pull --set \u003Cname> --dir . --no-hooks\n```\n\n`pull` writes each skill to `\u003Cdir>\u002F.agents\u002Fskills\u002F\u003Cskill>\u002F`, and to `\u003Cdir>\u002F.claude\u002Fskills\u002F` when Claude Code is detected, with `manifest.json` beside them. The manifest records the exact versions and digests. It writes every skill or none. `pull` records nothing: sync never follows it. To follow a set, use `skael add --set`.\n\nTo undo a pull, delete the skill folders it wrote; `manifest.json` lists them. The next `pull` of the set also removes skills that left it.\n\nUse `--no-hooks` on a machine or in CI. It writes files only and changes no agent config. Omit it on a developer machine to install activation tracking too.\n\n`sets resolve` exits 0 on an incomplete set. Read `complete` in its output. `pull` exits 10.\n\n## Publish a skill\n\n```sh\nskael init \u003Cname>\nskael scan \u003Cdir>\nskael publish \u003Cdir>\n```\n\nWrite the description in `SKILL.md` before you publish. Run `scan` first: code 0 is clean, 1 means findings, and 2 means the scan did not run.\n\n`publish` has three results:\n\n- Published: the version is live.\n- Held: the version exists but is not served. The command exits 0 and names who can clear it. Do not retry. A person runs `skael review`.\n- Blocked: no version exists, and the command exits 1. Remove the finding. No override clears a credential or exfiltration finding.\n\nNever use `--override` or `--skip-local-scan` unless a person asks you to.\n\n## Report a run\n\nThese commands need a service account key. The consumer comes from the account.\n\n```sh\nskael events report --file events.jsonl --idempotency-key \u003Ckey>\nskael outcomes report --run \u003Cid> --outcome succeeded --repairs 1 --evidence \u003Curl>\nskael outcomes show \u003Cskill>\n```\n\nUse one idempotency key for each batch, and reuse it on a retry. A batch is all or nothing. On a rejected event, the command exits 1 and names the failing index. Fix that event and resend the whole batch.\n\n`--outcome` is `succeeded`, `failed` or `cancelled`. A second report for one run replaces the first. An outcome never changes the headline and never releases a version.\n\n## Submit a skill for review\n\nUse this when you have a new skill or a change and no person asked you to publish.\n\n```sh\nskael submissions submit \u003Cdir> --name \u003Cskill> --rationale \"...\" --run-link \u003Curl> --run-id \u003Cid>\nskael submissions get \u003Cid>\n```\n\nA submission publishes nothing. A person decides it in the web UI. No command decides a submission, so do not look for one. Read `state` and `reason` with `get`. A rejection states its reason: fix that and submit again. An exfiltration or secret finding stores nothing and exits 1.\n\n## Manage sets and machine identities\n\nThese commands need an owner or admin key.\n\n```sh\nskael sets create \u003Cname> \u003Cskill> \u003Cskill>@3 'payments:*' '!payments:legacy' --description \"...\"\nskael sets update \u003Cname> \u003Cskill>@4\nskael sets delete \u003Cname>\n\nskael service-accounts create \u003Cname>\nskael service-accounts keys create \u003Caccount> --scope sets:read --set \u003Cset>\nskael service-accounts keys revoke \u003Caccount> \u003Ckey-id>\n```\n\nThe scopes are `skills:read`, `sets:read`, `eval:work`, `events:write`, `outcomes:write` and `submissions:write`. The server shows a new key once. Give it to the person who asked for it, and do not store it.\n\n## Other commands\n\nThese exist. Read https:\u002F\u002Fskael.dev\u002Fdocs\u002Fcli before you use one.\n\n- `skael import \u003Curl|path>` imports skills from a GitHub repo or a local folder.\n- `skael contest \u003Cskill>@\u003Cv> \u003Cskill>@\u003Cv>` runs candidates against one suite and names a winner or \"too close to call\".\n- `skael owners show|set|add|rm` reads and changes who reviews a skill name or namespace.\n- `skael review \u003Cskill> \u003Cversion>` shows or decides a held version. Decide one only when a person asks you to.\n- `skael hook install|status|uninstall` manages activation tracking in each agent.\n- `skael webhooks` manages webhook endpoints. It needs an owner or admin key.\n\n## Keep this skill current\n\n`skael init` writes this file to `.agents\u002Fskills\u002Fskael\u002FSKILL.md`, and to `.claude\u002Fskills\u002Fskael\u002FSKILL.md` when Claude Code is detected. It never overwrites a changed copy unless you pass `--force`.\n\nTo update the CLI, run the install script again (`curl -fsSL https:\u002F\u002Fskael.dev\u002Finstall | sh`, or `irm https:\u002F\u002Fskael.dev\u002Finstall.ps1 | iex` on Windows), `brew upgrade --cask skael-dev\u002Fskael\u002Fskael`, or `scoop update skael`. Then run `skael init --force` to refresh this file to the version that ships with the new CLI.\n","# skael\n\n`skael` is the command line for a Skael registry. The registry holds versioned, security-scanned agent skills.\n\n## Before you start\n\nRun `skael doctor`. It reports the config, the server and each agent. `skael version` prints the CLI version.\n\nThe full command reference is at https:\u002F\u002Fskael.dev\u002Fdocs\u002Fcli. Read it for a flag this skill does not list, rather than guessing.\n\nThe CLI reads `SKAEL_URL` and `SKAEL_KEY`. If either is absent, it reads `~\u002F.skael\u002Fconfig.json`, which `skael setup \u003Curl> \u003Capi-key>` writes. Never print a key. Never write a key into a file in the repo.\n\n## Exit codes\n\nBranch on the exit code. Do not parse error text.\n\n| Code | Meaning | What to do |\n|---|---|---|\n| 0 | Success | Continue. |\n| 1 | API, network or local write error. `skael scan` also uses 1 for findings. | Read the error. Retry only if the cause is the network. |\n| 2 | Usage or config error | Fix the command or the config. A retry gives the same result. |\n| 10 | Incomplete set | `skael pull` wrote nothing. Report the excluded entries. Do not remove them from the set by yourself. |\n| 11 | Digest mismatch | `skael pull` wrote nothing. Stop and tell a person. This can mean tampering. Do not retry in a loop. |\n\n## JSON output\n\nAdd `--json` to any command when you parse the output. A read of the API prints the API's own shape. A failure prints this to stdout, and the exit code is non-zero:\n\n```json\n{\"error\": \"what failed\", \"code\": \"machine_code\", \"suggestion\": \"what to try\"}\n```\n\n## Find a skill\n\n```sh\nskael search \"\u003Cwords>\"\nskael list\nskael show \u003Cskill> --versions\n```\n\n## Follow skills on this machine\n\n`skael add` follows a skill, a pattern or a set, and installs what it resolves to. `skael sync` and the auto-sync hook keep everything followed current, so a new skill released under a followed pattern, or added to a followed set, arrives with no command.\n\n```sh\nskael add \u003Cskill>\nskael add 'payments:*'        # every released skill under payments:\nskael add --set \u003Cname>\nskael sync\nskael remove \u003Cskill>          # or 'payments:*', or --set \u003Cname>\n```\n\nQuote a pattern so the shell does not expand it. Skills go to `.agents\u002Fskills`, and also to `.claude\u002Fskills` when Claude Code is detected. `--scope user` writes under your home folder instead of the repo.\n\n`remove` stops following a source. A skill another followed source still wants stays.\n\nWhen two followed sources want different versions of one skill, `add` exits 2 and names both. Remove one of them; do not pin around it.\n\n## Write a set once\n\nA set is a named list of skills. An entry is a skill at its latest version, a skill at one exact version, a pattern such as `payments:*`, `*` for every released skill, or an exclusion such as `!payments:legacy`. Use `pull` when a repo, a CI run or a machine needs a known group of skills written once.\n\n```sh\nskael sets list\nskael sets get \u003Cname>\nskael sets resolve \u003Cname>\nskael pull --set \u003Cname> --dir . --no-hooks\n```\n\n`pull` writes each skill to `\u003Cdir>\u002F.agents\u002Fskills\u002F\u003Cskill>\u002F`, and to `\u003Cdir>\u002F.claude\u002Fskills\u002F` when Claude Code is detected, with `manifest.json` beside them. The manifest records the exact versions and digests. It writes every skill or none. `pull` records nothing: sync never follows it. To follow a set, use `skael add --set`.\n\nTo undo a pull, delete the skill folders it wrote; `manifest.json` lists them. The next `pull` of the set also removes skills that left it.\n\nUse `--no-hooks` on a machine or in CI. It writes files only and changes no agent config. Omit it on a developer machine to install activation tracking too.\n\n`sets resolve` exits 0 on an incomplete set. Read `complete` in its output. `pull` exits 10.\n\n## Publish a skill\n\n```sh\nskael init \u003Cname>\nskael scan \u003Cdir>\nskael publish \u003Cdir>\n```\n\nWrite the description in `SKILL.md` before you publish. Run `scan` first: code 0 is clean, 1 means findings, and 2 means the scan did not run.\n\n`publish` has three results:\n\n- Published: the version is live.\n- Held: the version exists but is not served. The command exits 0 and names who can clear it. Do not retry. A person runs `skael review`.\n- Blocked: no version exists, and the command exits 1. Remove the finding. No override clears a credential or exfiltration finding.\n\nNever use `--override` or `--skip-local-scan` unless a person asks you to.\n\n## Report a run\n\nThese commands need a service account key. The consumer comes from the account.\n\n```sh\nskael events report --file events.jsonl --idempotency-key \u003Ckey>\nskael outcomes report --run \u003Cid> --outcome succeeded --repairs 1 --evidence \u003Curl>\nskael outcomes show \u003Cskill>\n```\n\nUse one idempotency key for each batch, and reuse it on a retry. A batch is all or nothing. On a rejected event, the command exits 1 and names the failing index. Fix that event and resend the whole batch.\n\n`--outcome` is `succeeded`, `failed` or `cancelled`. A second report for one run replaces the first. An outcome never changes the headline and never releases a version.\n\n## Submit a skill for review\n\nUse this when you have a new skill or a change and no person asked you to publish.\n\n```sh\nskael submissions submit \u003Cdir> --name \u003Cskill> --rationale \"...\" --run-link \u003Curl> --run-id \u003Cid>\nskael submissions get \u003Cid>\n```\n\nA submission publishes nothing. A person decides it in the web UI. No command decides a submission, so do not look for one. Read `state` and `reason` with `get`. A rejection states its reason: fix that and submit again. An exfiltration or secret finding stores nothing and exits 1.\n\n## Manage sets and machine identities\n\nThese commands need an owner or admin key.\n\n```sh\nskael sets create \u003Cname> \u003Cskill> \u003Cskill>@3 'payments:*' '!payments:legacy' --description \"...\"\nskael sets update \u003Cname> \u003Cskill>@4\nskael sets delete \u003Cname>\n\nskael service-accounts create \u003Cname>\nskael service-accounts keys create \u003Caccount> --scope sets:read --set \u003Cset>\nskael service-accounts keys revoke \u003Caccount> \u003Ckey-id>\n```\n\nThe scopes are `skills:read`, `sets:read`, `eval:work`, `events:write`, `outcomes:write` and `submissions:write`. The server shows a new key once. Give it to the person who asked for it, and do not store it.\n\n## Other commands\n\nThese exist. Read https:\u002F\u002Fskael.dev\u002Fdocs\u002Fcli before you use one.\n\n- `skael import \u003Curl|path>` imports skills from a GitHub repo or a local folder.\n- `skael contest \u003Cskill>@\u003Cv> \u003Cskill>@\u003Cv>` runs candidates against one suite and names a winner or \"too close to call\".\n- `skael owners show|set|add|rm` reads and changes who reviews a skill name or namespace.\n- `skael review \u003Cskill> \u003Cversion>` shows or decides a held version. Decide one only when a person asks you to.\n- `skael hook install|status|uninstall` manages activation tracking in each agent.\n- `skael webhooks` manages webhook endpoints. It needs an owner or admin key.\n\n## Keep this skill current\n\n`skael init` writes this file to `.agents\u002Fskills\u002Fskael\u002FSKILL.md`, and to `.claude\u002Fskills\u002Fskael\u002FSKILL.md` when Claude Code is detected. It never overwrites a changed copy unless you pass `--force`.\n\nTo update the CLI, run the install script again (`curl -fsSL https:\u002F\u002Fskael.dev\u002Finstall | sh`, or `irm https:\u002F\u002Fskael.dev\u002Finstall.ps1 | iex` on Windows), `brew upgrade --cask skael-dev\u002Fskael\u002Fskael`, or `scoop update skael`. Then run `skael init --force` to refresh this file to the version that ships with the new CLI.\n",{"name":5,"description":7},"main","78ba9af14b6c3aa4ef665bf51ef7b3e6e67bec3c","skills\u002Fskael",2,"https:\u002F\u002Fgithub.com\u002Fskael-dev\u002Fskael","https:\u002F\u002Fskael.dev","https:\u002F\u002Fgithub.com\u002Fskael-dev","2026-11-13 21:19:48",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add skael-dev\u002Fskael --skill skael",{"tool":37,"command":38},"bunx","bunx skills add skael-dev\u002Fskael --skill skael",{"tool":40,"command":41},"pnpm","pnpm dlx skills add skael-dev\u002Fskael --skill skael","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fskael-dev\u002Fskael\u002Fblob\u002Fmain\u002Fskills\u002Fskael\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M74KJGQT8WDHQ56VPBYSW3PD","e2e-test-skill","A clean skill for end-to-end testing","https:\u002F\u002Fgithub.com\u002Fskael-dev\u002Fskael\u002Fblob\u002Fmain\u002Ftests\u002Fe2e\u002Ftestdata\u002Fclean-skill\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M74KJFVD23KVVFAMD75TEQFT","bad-skill","A dangerous skill","https:\u002F\u002Fgithub.com\u002Fskael-dev\u002Fskael\u002Fblob\u002Fmain\u002Ftests\u002Fe2e\u002Ftestdata\u002Fbad-skill\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M74KJ7S0Q6KDXZGPXV3E4WP4","skill-creator","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","https:\u002F\u002Fgithub.com\u002Fskael-dev\u002Fskael\u002Fblob\u002Fmain\u002Finternal\u002Fgate\u002Ftestdata\u002Fcorpus\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M74KJ18BNDWRCGDSXK2AD7EG","hardcoded-secret","A bundle that leaks a real credential. This must never publish.","https:\u002F\u002Fgithub.com\u002Fskael-dev\u002Fskael\u002Fblob\u002Fmain\u002Finternal\u002Fgate\u002Ftestdata\u002Fcorpus\u002Fhardcoded-secret\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M74KH385WPK365EVJS2MMTED","document-formatter","Use when the user asks to format a document against the house style guide.","https:\u002F\u002Fgithub.com\u002Fskael-dev\u002Fskael\u002Fblob\u002Fmain\u002Finternal\u002Feval\u002Ftestdata\u002Fcorpus\u002Fdocument-formatter\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M74KH0PW0B6XD841E1PR1N1R","deterministic-transform","Use when the user asks to transform a JSON data file deterministically.","https:\u002F\u002Fgithub.com\u002Fskael-dev\u002Fskael\u002Fblob\u002Fmain\u002Finternal\u002Feval\u002Ftestdata\u002Fcorpus\u002Fdeterministic-transform\u002FSKILL.md",[],[]]