[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M756V331K4RFFJA5QYFH3MH9":3,"skill-same:01M756V331K4RFFJA5QYFH3MH9":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},"01M756V331K4RFFJA5QYFH3MH9","authoring-adept-skills",null,"Write a good, portable adept skill: pick the right activation, craft a triggering description, keep it scan-safe and within harness byte budgets. Apply when creating or editing a SKILL.md or running `adept skill add`.","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\u002Fauthoring-adept-skills\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nid: authoring-adept-skills\ndescription: \"Write a good, portable adept skill: pick the right activation, craft a triggering description, keep it scan-safe and within harness byte budgets. Apply when creating or editing a SKILL.md or running `adept skill add`.\"\nactivation: agent\nallowed-tools:\n  - \"Bash\"\n  - \"Read\"\n  - \"Edit\"\n  - \"Write\"\n---\n\n# Authoring a good adept skill\n\nA skill is a directory `\u003Croot>\u002Fskills\u002F\u003Cid>\u002F` with one `SKILL.md` (YAML frontmatter +\nmarkdown body) and optional sidecars. `adept` renders it into every enabled harness, so\nwrite it **once, well, and harness-neutral**.\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 (e.g. [\"**\u002F*.go\"])\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\nValidated against `pkg\u002Fadeptschema\u002Fskill.schema.json` on every load — `adept sync` fails\nloudly on a malformed skill, so let it catch your mistakes.\n\n## Pick activation deliberately — this is the whole game\n\n| activation | Fires when | Use for |\n|---|---|---|\n| `agent`  | The model decides from the **description** | Most skills. Procedures, checklists, how-tos. |\n| `globs`  | A matching file is in context | Language\u002Fpath-specific rules (`**\u002F*.go`, `**\u002F*.tsx`). |\n| `always` | Every request | Rare. Project-wide invariants only — costs budget on every turn. |\n| `manual` | Only when explicitly invoked | Heavy or destructive procedures you don't want auto-firing. |\n\n## The description is the trigger — write it like one\n\nFor `activation: agent`, the description is the **only** thing the model sees when deciding\nwhether to load the skill. Make it earn the load:\n\n- Lead with **when to apply**, not what it is: *\"Use before opening a PR…\"* beats *\"A PR\n  helper.\"*\n- Name concrete nouns the user will say (file types, commands, tools, error strings).\n- One line, ≤ 280 chars. If you can't say when it applies in one line, the skill is too broad\n  — split it.\n\n## Keep it portable and lean\n\n- **Harness-neutral body.** Don't say \"in Cursor, click…\"; describe the behavior, not the UI.\n- **Budget-aware.** Aggregator harnesses (Codex\u002FCopilot) cap total bytes; a bloated skill\n  gets dropped first. Tighten prose; move long reference material into `references\u002F` sidecars.\n- **Scan-safe.** Installs run a safety scan. Avoid anything that reads like prompt injection,\n  exfiltrates secrets, or runs opaque remote code — it will flag (`critical` hard-blocks).\n- **Sidecars** (`scripts\u002F`, `references\u002F`, `assets\u002F`) ride along to harnesses that support\n  them; keep the SKILL.md body self-sufficient for those that don't.\n\n## Loop\n\n```bash\nadept skill add my-skill --edit   # scaffold + open $EDITOR\nadept sync                        # render to every enabled harness\nadept status && adept diff        # confirm it landed clean\n```\n\nRun `adept skill --help` (and `adept skill add --help`) for the current flags and\nsubcommands — prefer it over memory; it never drifts. Edit canonical, `adept sync`, never\nhand-edit rendered files. See [[using-adept]] for the\nfull CLI and [[adept-self-improve]] for turning a one-off lesson into a durable skill.\n","# Authoring a good adept skill\n\nA skill is a directory `\u003Croot>\u002Fskills\u002F\u003Cid>\u002F` with one `SKILL.md` (YAML frontmatter +\nmarkdown body) and optional sidecars. `adept` renders it into every enabled harness, so\nwrite it **once, well, and harness-neutral**.\n\n## Canonical SKILL.md format\n\n```markdown\n---\nid: pr-review                 # ^[a-z0-9](?:[a-z0-9-]{0,48}[a-z0-9])?$ — 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 (e.g. [\"**\u002F*.go\"])\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\nValidated against `pkg\u002Fadeptschema\u002Fskill.schema.json` on every load — `adept sync` fails\nloudly on a malformed skill, so let it catch your mistakes.\n\n## Pick activation deliberately — this is the whole game\n\n| activation | Fires when | Use for |\n|---|---|---|\n| `agent`  | The model decides from the **description** | Most skills. Procedures, checklists, how-tos. |\n| `globs`  | A matching file is in context | Language\u002Fpath-specific rules (`**\u002F*.go`, `**\u002F*.tsx`). |\n| `always` | Every request | Rare. Project-wide invariants only — costs budget on every turn. |\n| `manual` | Only when explicitly invoked | Heavy or destructive procedures you don't want auto-firing. |\n\n## The description is the trigger — write it like one\n\nFor `activation: agent`, the description is the **only** thing the model sees when deciding\nwhether to load the skill. Make it earn the load:\n\n- Lead with **when to apply**, not what it is: *\"Use before opening a PR…\"* beats *\"A PR\n  helper.\"*\n- Name concrete nouns the user will say (file types, commands, tools, error strings).\n- One line, ≤ 280 chars. If you can't say when it applies in one line, the skill is too broad\n  — split it.\n\n## Keep it portable and lean\n\n- **Harness-neutral body.** Don't say \"in Cursor, click…\"; describe the behavior, not the UI.\n- **Budget-aware.** Aggregator harnesses (Codex\u002FCopilot) cap total bytes; a bloated skill\n  gets dropped first. Tighten prose; move long reference material into `references\u002F` sidecars.\n- **Scan-safe.** Installs run a safety scan. Avoid anything that reads like prompt injection,\n  exfiltrates secrets, or runs opaque remote code — it will flag (`critical` hard-blocks).\n- **Sidecars** (`scripts\u002F`, `references\u002F`, `assets\u002F`) ride along to harnesses that support\n  them; keep the SKILL.md body self-sufficient for those that don't.\n\n## Loop\n\n```bash\nadept skill add my-skill --edit   # scaffold + open $EDITOR\nadept sync                        # render to every enabled harness\nadept status && adept diff        # confirm it landed clean\n```\n\nRun `adept skill --help` (and `adept skill add --help`) for the current flags and\nsubcommands — prefer it over memory; it never drifts. Edit canonical, `adept sync`, never\nhand-edit rendered files. See [[using-adept]] for the\nfull CLI and [[adept-self-improve]] for turning a one-off lesson into a durable skill.\n",{"id":5,"activation":24,"description":7,"allowed-tools":25},"agent",[26,27,28,29],"Bash","Read","Edit","Write","main","c5b1b81b2e0ae71bd8afeeade28eaea6f8fd1bf5",".adeptability\u002Fskills\u002Fauthoring-adept-skills",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 authoring-adept-skills",{"tool":46,"command":47},"bunx","bunx skills add itaywol\u002Fadeptability --skill authoring-adept-skills",{"tool":49,"command":50},"pnpm","pnpm dlx skills add itaywol\u002Fadeptability --skill authoring-adept-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability\u002Fblob\u002Fmain\u002F.adeptability\u002Fskills\u002Fauthoring-adept-skills\u002FSKILL.md",true,[],[55,61,67,73,79,85],{"skillNo":56,"name":57,"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":58,"categories":59,"keywords":60,"publishedAt":19},"01M756YHZ76TMVP0KK718K6KN0","using-adept","https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability\u002Fblob\u002Fmain\u002Fskills\u002Fusing-adept\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"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":64,"categories":65,"keywords":66,"publishedAt":19},"01M756YG9YGBG4783SFH8RE5PM","agents","https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability\u002Fblob\u002Fmain\u002Fskills\u002Fagents\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"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":70,"categories":71,"keywords":72,"publishedAt":19},"01M756YD5MDX9ANB4QPVN34YQX","adept-writing-tests","https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability\u002Fblob\u002Fmain\u002Fskills\u002Fadept-writing-tests\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"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":76,"categories":77,"keywords":78,"publishedAt":19},"01M756YB57DN31BKNT4GHM9N2S","adept-contributing","https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability\u002Fblob\u002Fmain\u002Fskills\u002Fadept-contributing\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"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":82,"categories":83,"keywords":84,"publishedAt":19},"01M756Y9VM8W6E2HWMVYH0PH6H","adept-code-style","https:\u002F\u002Fgithub.com\u002Fitaywol\u002Fadeptability\u002Fblob\u002Fmain\u002Fskills\u002Fadept-code-style\u002FSKILL.md",[],[],{"skillNo":86,"name":57,"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},"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",[],[]]