[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JJ4QH96NNMTKEM3ZMP50J":3,"skill-same:01M71JJ4QH96NNMTKEM3ZMP50J":72},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":5,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M71JJ4QH96NNMTKEM3ZMP50J","install-skill",null,"Install a freshly authored skill into ~\u002Fskills\u002F (the source-of-truth repo), record its provenance, validate it, and symlink it into active agent directories. Use after creating a SKILL.md, when finishing an anthropic-skill-creator session, or when the user says \"install this skill\", \"wire it up\", \"register the skill\", or \"add it to my repo\".","caezium\u002Fskills","caezium","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113233555?v=4","01M71JB77ZPBAWEK009Y2W8BP7","Henry Zhang","01M71JB792NVXCWSYD27HQ0964",3,"MIT","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Finstall-skill\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"install","install skill","it","creator","source","my","symlink","a skill","validate","active","record","provenance","when","use","up","session","repo","register","directories","skill-creator","2026-11-10 10:12:30",false,"---\nname: install-skill\ndescription: Install a freshly authored skill into ~\u002Fskills\u002F (the source-of-truth repo), record its provenance, validate it, and symlink it into active agent directories. Use after creating a SKILL.md, when finishing an anthropic-skill-creator session, or when the user says \"install this skill\", \"wire it up\", \"register the skill\", or \"add it to my repo\".\n---\n\n# Install Skill\n\nWires a newly authored skill into the user's personal skills repo at `~\u002Fskills\u002F`, links it into Claude Code, Cursor, and shared-agent discovery for Codex, and prepares it for review in [caezium\u002Fskills](https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills).\n\nThe user's setup uses **`~\u002Fskills\u002F` as the single source of truth**. Agent directories (`~\u002F.claude\u002Fskills\u002F`, `~\u002F.cursor\u002Fskills\u002F`, and `~\u002F.agents\u002Fskills\u002F`) hold only symlinks pointing back here. Never copy a canonical skill into the agent directories — always symlink.\n\n## Where things live\n\n| Location | Role |\n|---|---|\n| `~\u002Fskills\u002F\u003Cname>\u002FSKILL.md` | Source of truth — git-tracked, pushed to caezium\u002Fskills |\n| `~\u002Fskills\u002Fcommands\u002F\u003Cname>.md` | Source of truth for single-file slash commands |\n| `~\u002Fskills\u002Fskills.lock.json` | Source pin, content digest, update policy, and reviewed local overlays |\n| `~\u002Fskills\u002Fbin\u002Fsync.sh` | Symlinks `~\u002Fskills\u002F*` into Claude, Cursor, and shared-agent discovery paths |\n| `~\u002F.claude\u002Fskills\u002F\u003Cname>` | Symlink → `~\u002Fskills\u002F\u003Cname>\u002F` |\n| `~\u002F.cursor\u002Fskills\u002F\u003Cname>` | Symlink → `~\u002Fskills\u002F\u003Cname>\u002F` |\n| `~\u002F.agents\u002Fskills\u002F\u003Cname>` | Symlink → `~\u002Fskills\u002F\u003Cname>\u002F` for Codex and other shared agents |\n\n## Install workflow\n\n### Step 1 — Validate\n\nBefore placing anything, confirm:\n\n- [ ] Name is lowercase, hyphens-only, ≤ 64 chars (e.g. `code-review`, not `Code_Review`)\n- [ ] Directory name and the `name:` field in frontmatter match exactly\n- [ ] `SKILL.md` has frontmatter with both `name:` and `description:`\n- [ ] Description is in third person, includes WHAT + WHEN trigger terms\n- [ ] No naming collision:\n\n```sh\nls ~\u002Fskills\u002F | grep -i \u003Cskill-name>\n```\n\nIf collision: rename, merge, or stop and ask.\n\n### Step 2 — Place in `~\u002Fskills\u002F`\n\nIf authored in a temp\u002Fworking directory:\n\n```sh\nmv \u003Csource-path> ~\u002Fskills\u002F\u003Cskill-name>\u002F\n```\n\nIf authored directly at `~\u002Fskills\u002F\u003Cskill-name>\u002F`, skip this.\n\n**Single-file slash commands** (no SKILL.md, just one `.md` with frontmatter) go under `~\u002Fskills\u002Fcommands\u002F` instead:\n\n```sh\nmv \u003Cname>.md ~\u002Fskills\u002Fcommands\u002F\n```\n\n### Step 3 — Sync to active agents\n\n```sh\n~\u002Fskills\u002Fbin\u002Fsync.sh all\n```\n\nSubcommands: `claude`, `cursor`, `agents`, or `all`. Idempotent — replaces existing symlinks and treats a real-directory collision as a hard error that must be preserved and reconciled first.\n\nAfter sync, verify:\n\n```sh\nls -la ~\u002F.claude\u002Fskills\u002F\u003Cskill-name>   # should show -> \u002FUsers\u002Fhenry\u002Fskills\u002F\u003Cskill-name>\u002F\nls -la ~\u002F.cursor\u002Fskills\u002F\u003Cskill-name>\nls -la ~\u002F.agents\u002Fskills\u002F\u003Cskill-name>\n```\n\n### Step 4 — Update and validate provenance\n\nAdd or update the skill's record in `skills.lock.json`. For a personal skill,\nuse the helper so the content digest and record shape cannot drift:\n\n```sh\npython3 ~\u002Fskills\u002Fbin\u002Frecord-skill-state.py record \\\n  --name \u003Cskill-name> \\\n  --kind custom \\\n  --update-policy personal-repo \\\n  --notes \"\u003Cpurpose and ownership>\"\n```\n\nFor a vendored package, also pass `--source-id`, `--source-root`, and\n`--source-path`; use `--overlay` once per intentional local change. Pin the\nreviewed source with the helper's `pin-source` command, then validate both the\nlock and every package before committing:\n\n```sh\npython3 ~\u002Fskills\u002Fbin\u002Fvalidate-skills-lock.py \\\n  ~\u002Fskills\u002Fskills.lock.json \\\n  --schema ~\u002Fskills\u002Fschema\u002Fskills-lock.schema.json\npython3 ~\u002Fskills\u002Fbin\u002Fvalidate-skill-tree.py --root ~\u002Fskills\npython3 ~\u002Fskills\u002Fbin\u002Fhash-skill-tree.py \\\n  --verify-lock ~\u002Fskills\u002Fskills.lock.json \\\n  --root ~\u002Fskills\n```\n\nDo not change a source pin merely to silence drift: inspect the upstream diff,\nrefresh the complete package, reapply reviewed overlays, and update the pin and\ncontent digest together.\n\n### Step 5 — Refresh the published skills map\n\nRefresh the full-machine inventory before committing. The script deduplicates\npersonal, shared-agent, Codex, and plugin skills, then builds and validates the\nHTML site locally:\n\n```sh\n~\u002Fskills\u002Fbin\u002Fupdate-skills-map.sh\n```\n\nInclude `site\u002Finstalled-skills.json` in the same commit when it changed. The\nsite deployment workflow rebuilds the repository catalog and the installed\nskills map after the push.\n\n### Step 6 — Commit for review\n\n```sh\ncd ~\u002Fskills\ngit add \u003Cskill-name>\u002F skills.lock.json site\u002Finstalled-skills.json\ngit commit -m \"Add \u003Cskill-name>: \u003Cone-line purpose>\"\n```\n\nCommit message conventions:\n- **New skill:** `Add \u003Cskill-name>: \u003Cone-line purpose>`\n- **Edit existing:** `Update \u003Cskill-name>: \u003Cwhat changed>`\n- **Remove:** `Remove \u003Cskill-name>: \u003Cwhy>`\n- **Slash command:** `Add \u002F\u003Cname> command` or `Update \u002F\u003Cname> command`\n\nShow the staged diff before committing. Push or merge only when the user\nexplicitly asks for that external action. Use a short-lived branch and a PR for\nvendored upstream updates so the package diff, overlay rebase, source pin, and\ncontent hash can be reviewed together; a scheduled freshness issue is never\nauthority to merge an update.\n\n### Step 7 — Confirm pickup\n\nIn a **fresh** Claude Code, Codex\u002FT3, or Cursor session, the skill should appear in the available-skills list. Skills load at session start; runtime additions don't auto-register. Tell the user to restart their session if it is not showing.\n\n## Common gotchas\n\n- **Symlink already points to `~\u002F.agents\u002Fskills\u002F\u003Cname>`.** That's the legacy npx-install path. `sync.sh` will replace it — `~\u002Fskills\u002F` is now the canonical home. Confirm with the user before clobbering if the existing version differs meaningfully.\n- **Real directory at the target.** `sync.sh` refuses to overwrite a real directory in any discovery path. Inspect and compare it, preserve it outside discovery, then choose exactly one owner for the global name before syncing. Never delete an unknown real directory just to make the warning disappear.\n- **Embedded `.git\u002F` in the skill folder.** If the skill came from a cloned or npx-installed source, it may have its own `.git\u002F`. Build the reviewed package from a separate source checkout while excluding `.git`; never delete unresolved source metadata merely to make Git accept the package. For example:\n\n  ```sh\n  rsync -a --exclude=.git\u002F \u003Creviewed-source>\u002F ~\u002Fskills\u002F\u003Cskill-name>\u002F\n  ```\n\n- **Frontmatter typos.** A missing or malformed `---` block makes the skill invisible to the agent. Quick check:\n\n  ```sh\n  head -5 ~\u002Fskills\u002F\u003Cskill-name>\u002FSKILL.md\n  ```\n\n- **Skill not picked up after restart.** Confirm the symlink resolves (`readlink ~\u002F.claude\u002Fskills\u002F\u003Cname>`), confirm frontmatter parses, and check `~\u002F.claude\u002Fsettings.json` doesn't disable skill loading.\n\n## When NOT to install here\n\nSkip `~\u002Fskills\u002F` (and use a project-local location instead) when:\n\n- The skill is one-off for a single project → put it in that project's `.claude\u002Fskills\u002F` or `.cursor\u002Fskills\u002F`\n- The skill contains secrets, API keys, or private paths — caezium\u002Fskills is **public**\n- The skill duplicates existing functionality — search `~\u002Fskills\u002F` first; consider editing the existing one\n\n## Quick reference\n\nFor an already-validated skill folder at `~\u002Fskills\u002F\u003Cname>\u002F`:\n\n```sh\npython3 ~\u002Fskills\u002Fbin\u002Frecord-skill-state.py record --name \u003Cname> \\\n  --kind custom --update-policy personal-repo --notes \"\u003Cpurpose>\"\npython3 ~\u002Fskills\u002Fbin\u002Fvalidate-skill-tree.py --root ~\u002Fskills\n~\u002Fskills\u002Fbin\u002Fupdate-skills-map.sh\n~\u002Fskills\u002Fbin\u002Fsync.sh all\ncd ~\u002Fskills && git add \u003Cname>\u002F skills.lock.json site\u002Finstalled-skills.json && git commit -m \"Add \u003Cname>: \u003Cpurpose>\"\n```\n","# Install Skill\n\nWires a newly authored skill into the user's personal skills repo at `~\u002Fskills\u002F`, links it into Claude Code, Cursor, and shared-agent discovery for Codex, and prepares it for review in [caezium\u002Fskills](https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills).\n\nThe user's setup uses **`~\u002Fskills\u002F` as the single source of truth**. Agent directories (`~\u002F.claude\u002Fskills\u002F`, `~\u002F.cursor\u002Fskills\u002F`, and `~\u002F.agents\u002Fskills\u002F`) hold only symlinks pointing back here. Never copy a canonical skill into the agent directories — always symlink.\n\n## Where things live\n\n| Location | Role |\n|---|---|\n| `~\u002Fskills\u002F\u003Cname>\u002FSKILL.md` | Source of truth — git-tracked, pushed to caezium\u002Fskills |\n| `~\u002Fskills\u002Fcommands\u002F\u003Cname>.md` | Source of truth for single-file slash commands |\n| `~\u002Fskills\u002Fskills.lock.json` | Source pin, content digest, update policy, and reviewed local overlays |\n| `~\u002Fskills\u002Fbin\u002Fsync.sh` | Symlinks `~\u002Fskills\u002F*` into Claude, Cursor, and shared-agent discovery paths |\n| `~\u002F.claude\u002Fskills\u002F\u003Cname>` | Symlink → `~\u002Fskills\u002F\u003Cname>\u002F` |\n| `~\u002F.cursor\u002Fskills\u002F\u003Cname>` | Symlink → `~\u002Fskills\u002F\u003Cname>\u002F` |\n| `~\u002F.agents\u002Fskills\u002F\u003Cname>` | Symlink → `~\u002Fskills\u002F\u003Cname>\u002F` for Codex and other shared agents |\n\n## Install workflow\n\n### Step 1 — Validate\n\nBefore placing anything, confirm:\n\n- [ ] Name is lowercase, hyphens-only, ≤ 64 chars (e.g. `code-review`, not `Code_Review`)\n- [ ] Directory name and the `name:` field in frontmatter match exactly\n- [ ] `SKILL.md` has frontmatter with both `name:` and `description:`\n- [ ] Description is in third person, includes WHAT + WHEN trigger terms\n- [ ] No naming collision:\n\n```sh\nls ~\u002Fskills\u002F | grep -i \u003Cskill-name>\n```\n\nIf collision: rename, merge, or stop and ask.\n\n### Step 2 — Place in `~\u002Fskills\u002F`\n\nIf authored in a temp\u002Fworking directory:\n\n```sh\nmv \u003Csource-path> ~\u002Fskills\u002F\u003Cskill-name>\u002F\n```\n\nIf authored directly at `~\u002Fskills\u002F\u003Cskill-name>\u002F`, skip this.\n\n**Single-file slash commands** (no SKILL.md, just one `.md` with frontmatter) go under `~\u002Fskills\u002Fcommands\u002F` instead:\n\n```sh\nmv \u003Cname>.md ~\u002Fskills\u002Fcommands\u002F\n```\n\n### Step 3 — Sync to active agents\n\n```sh\n~\u002Fskills\u002Fbin\u002Fsync.sh all\n```\n\nSubcommands: `claude`, `cursor`, `agents`, or `all`. Idempotent — replaces existing symlinks and treats a real-directory collision as a hard error that must be preserved and reconciled first.\n\nAfter sync, verify:\n\n```sh\nls -la ~\u002F.claude\u002Fskills\u002F\u003Cskill-name>   # should show -> \u002FUsers\u002Fhenry\u002Fskills\u002F\u003Cskill-name>\u002F\nls -la ~\u002F.cursor\u002Fskills\u002F\u003Cskill-name>\nls -la ~\u002F.agents\u002Fskills\u002F\u003Cskill-name>\n```\n\n### Step 4 — Update and validate provenance\n\nAdd or update the skill's record in `skills.lock.json`. For a personal skill,\nuse the helper so the content digest and record shape cannot drift:\n\n```sh\npython3 ~\u002Fskills\u002Fbin\u002Frecord-skill-state.py record \\\n  --name \u003Cskill-name> \\\n  --kind custom \\\n  --update-policy personal-repo \\\n  --notes \"\u003Cpurpose and ownership>\"\n```\n\nFor a vendored package, also pass `--source-id`, `--source-root`, and\n`--source-path`; use `--overlay` once per intentional local change. Pin the\nreviewed source with the helper's `pin-source` command, then validate both the\nlock and every package before committing:\n\n```sh\npython3 ~\u002Fskills\u002Fbin\u002Fvalidate-skills-lock.py \\\n  ~\u002Fskills\u002Fskills.lock.json \\\n  --schema ~\u002Fskills\u002Fschema\u002Fskills-lock.schema.json\npython3 ~\u002Fskills\u002Fbin\u002Fvalidate-skill-tree.py --root ~\u002Fskills\npython3 ~\u002Fskills\u002Fbin\u002Fhash-skill-tree.py \\\n  --verify-lock ~\u002Fskills\u002Fskills.lock.json \\\n  --root ~\u002Fskills\n```\n\nDo not change a source pin merely to silence drift: inspect the upstream diff,\nrefresh the complete package, reapply reviewed overlays, and update the pin and\ncontent digest together.\n\n### Step 5 — Refresh the published skills map\n\nRefresh the full-machine inventory before committing. The script deduplicates\npersonal, shared-agent, Codex, and plugin skills, then builds and validates the\nHTML site locally:\n\n```sh\n~\u002Fskills\u002Fbin\u002Fupdate-skills-map.sh\n```\n\nInclude `site\u002Finstalled-skills.json` in the same commit when it changed. The\nsite deployment workflow rebuilds the repository catalog and the installed\nskills map after the push.\n\n### Step 6 — Commit for review\n\n```sh\ncd ~\u002Fskills\ngit add \u003Cskill-name>\u002F skills.lock.json site\u002Finstalled-skills.json\ngit commit -m \"Add \u003Cskill-name>: \u003Cone-line purpose>\"\n```\n\nCommit message conventions:\n- **New skill:** `Add \u003Cskill-name>: \u003Cone-line purpose>`\n- **Edit existing:** `Update \u003Cskill-name>: \u003Cwhat changed>`\n- **Remove:** `Remove \u003Cskill-name>: \u003Cwhy>`\n- **Slash command:** `Add \u002F\u003Cname> command` or `Update \u002F\u003Cname> command`\n\nShow the staged diff before committing. Push or merge only when the user\nexplicitly asks for that external action. Use a short-lived branch and a PR for\nvendored upstream updates so the package diff, overlay rebase, source pin, and\ncontent hash can be reviewed together; a scheduled freshness issue is never\nauthority to merge an update.\n\n### Step 7 — Confirm pickup\n\nIn a **fresh** Claude Code, Codex\u002FT3, or Cursor session, the skill should appear in the available-skills list. Skills load at session start; runtime additions don't auto-register. Tell the user to restart their session if it is not showing.\n\n## Common gotchas\n\n- **Symlink already points to `~\u002F.agents\u002Fskills\u002F\u003Cname>`.** That's the legacy npx-install path. `sync.sh` will replace it — `~\u002Fskills\u002F` is now the canonical home. Confirm with the user before clobbering if the existing version differs meaningfully.\n- **Real directory at the target.** `sync.sh` refuses to overwrite a real directory in any discovery path. Inspect and compare it, preserve it outside discovery, then choose exactly one owner for the global name before syncing. Never delete an unknown real directory just to make the warning disappear.\n- **Embedded `.git\u002F` in the skill folder.** If the skill came from a cloned or npx-installed source, it may have its own `.git\u002F`. Build the reviewed package from a separate source checkout while excluding `.git`; never delete unresolved source metadata merely to make Git accept the package. For example:\n\n  ```sh\n  rsync -a --exclude=.git\u002F \u003Creviewed-source>\u002F ~\u002Fskills\u002F\u003Cskill-name>\u002F\n  ```\n\n- **Frontmatter typos.** A missing or malformed `---` block makes the skill invisible to the agent. Quick check:\n\n  ```sh\n  head -5 ~\u002Fskills\u002F\u003Cskill-name>\u002FSKILL.md\n  ```\n\n- **Skill not picked up after restart.** Confirm the symlink resolves (`readlink ~\u002F.claude\u002Fskills\u002F\u003Cname>`), confirm frontmatter parses, and check `~\u002F.claude\u002Fsettings.json` doesn't disable skill loading.\n\n## When NOT to install here\n\nSkip `~\u002Fskills\u002F` (and use a project-local location instead) when:\n\n- The skill is one-off for a single project → put it in that project's `.claude\u002Fskills\u002F` or `.cursor\u002Fskills\u002F`\n- The skill contains secrets, API keys, or private paths — caezium\u002Fskills is **public**\n- The skill duplicates existing functionality — search `~\u002Fskills\u002F` first; consider editing the existing one\n\n## Quick reference\n\nFor an already-validated skill folder at `~\u002Fskills\u002F\u003Cname>\u002F`:\n\n```sh\npython3 ~\u002Fskills\u002Fbin\u002Frecord-skill-state.py record --name \u003Cname> \\\n  --kind custom --update-policy personal-repo --notes \"\u003Cpurpose>\"\npython3 ~\u002Fskills\u002Fbin\u002Fvalidate-skill-tree.py --root ~\u002Fskills\n~\u002Fskills\u002Fbin\u002Fupdate-skills-map.sh\n~\u002Fskills\u002Fbin\u002Fsync.sh all\ncd ~\u002Fskills && git add \u003Cname>\u002F skills.lock.json site\u002Finstalled-skills.json && git commit -m \"Add \u003Cname>: \u003Cpurpose>\"\n```\n",{"name":5,"description":7},"main","6ef866230c1ba3459fd08fc65141dfd37fffd41a",0,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills","https:\u002F\u002Fskills.henryzh.dev","https:\u002F\u002Fgithub.com\u002Fcaezium","henryzh.dev","quant, data science, full-stack, robotics.\r\nbuilding cool stuff","2026-08-24 19:21:44",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add caezium\u002Fskills --skill install-skill",{"tool":64,"command":65},"bunx","bunx skills add caezium\u002Fskills --skill install-skill",{"tool":67,"command":68},"pnpm","pnpm dlx skills add caezium\u002Fskills --skill install-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Finstall-skill\u002FSKILL.md",true,[],[73,93,121,139,159,181],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":87,"publishedAt":44},"01M71JT4RYCAS18RF6003YYR1D","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FSKILL.md",[79,82],{"categoryNo":80,"categoryName":81,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":83,"categoryName":84,"taxonomyType":85,"taxonomyTypeDesc":86},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[88,89,90,91,37,92,36],"writing for agents","for","writing","editing","documents",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":102,"publishedAt":44},"01M71JT0GES4AZ5ADH8EADNN1Z","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwrangler\u002FSKILL.md",[99],{"categoryNo":100,"categoryName":101,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[95,103,104,105,106,107,108,109,110,111,112,113,114,89,115,116,117,118,119,120],"cloudflare","d1","knowledge","workflows","cli","secrets","commands","syntax","cloudflare workers","r2","queues","running","containers","correct","load","workers","best practices","store",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":44},"01M71JSWX4R203M32K9A18AAW8","workers-best-practices","Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fworkers-best-practices\u002FSKILL.md",[],[128,118,119,129,130,131,89,103,132,105,133,95,90,117,36,134,135,136,137,138],"workers best practices","observability","reviews","promises","worker","new","code","common","streaming","state","anti-patterns",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":44},"01M71JST6P88MXGT2MWDTPJGEG","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwizard\u002FSKILL.md",[],[141,114,146,89,38,147,148,149,37,150,36,151,152,153,154,155,156,157,158,108],"setting","ci","provisioning infrastructure","only","invoke","Bash","one","interactive","can","credentials","dashboard","generate","human",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":163,"sourceHtmlUrl":164,"categories":165,"keywords":166,"publishedAt":44},"01M71JSQ95S7BQ61DAPN95X2W4","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available evidence sources, searches each relevant category, and returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FSKILL.md",[],[161,167,168,169,170,89,171,172,37,173,174,175,176,177,178,179,180],"sources","thresholds","evidence","relevant","runtime","design","decisions","work","how","behavior","read","data","rationale","returns",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":188,"publishedAt":44},"01M71JSMHFVSH8HK8GXN6YAX6J","week-prep","Generate a briefing with calendar, tasks, and attention flags. Use for \"week prep\", \"briefing\", or \"what's on this week\".","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fweek-prep\u002FSKILL.md",[187],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[189,190,191,192,193,89,194,195,196,197,37,151,198,199,200,157,201,177,202,203],"week prep","prep","deep","attention","get","search","messages","briefing","MCP","tasks","with","slack","calendar","flags","grep"]