[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BK3GTB8BGHWMQJC4ZEM2R4":3,"skill-same:01M7BK3GTB8BGHWMQJC4ZEM2R4":56},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7BK3GTB8BGHWMQJC4ZEM2R4","find-skills",null,"Discover, vet, and install agent skills by searching ACROSS every major registry at once — skills.sh, clawhub.ai, and GitHub — presenting each board on its own native metric (installs \u002F stars) with the top entry per board, security-scanning the top candidates' real SKILL.md for risky patterns, and flagging what's already installed. Use when the user asks \"how do I do X\", \"find a skill for X\", \"is there a skill that…\", \"what skill should I install for…\", or wants to extend the agent with a capability that might already exist as a published skill. Unlike single-registry search, this surfaces the best of every platform side by side, so you recommend the genuinely relevant, popular, well-maintained, and SAFE one — not whatever ranked first on one site.","om-scogo\u002Fskillsh-scraper","om-scogo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160466840?v=4","01M79AWB6DFVCQ7RK70CS34B96","Om Achrekar","01M79AWB6ZM9SKR8KDH1WSSM22",0,"MIT","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fagentspace-so-skills\u002Ffind-skills\u002FSkill.md",[],[],"2026-11-15 14:19:17",false,"---\nname: find-skills\ndisplayName: \"🔍 Find Skills — Search Every Skill Registry at Once\"\ndescription: >\n  Discover, vet, and install agent skills by searching ACROSS every major\n  registry at once — skills.sh, clawhub.ai, and GitHub — presenting each board\n  on its own native metric (installs \u002F stars) with the top entry per board,\n  security-scanning the top candidates' real SKILL.md for risky patterns, and\n  flagging what's already installed. Use when the user asks \"how do I do X\",\n  \"find a skill for X\", \"is there a skill that…\", \"what skill should I install\n  for…\", or wants to extend the agent with a capability that might already exist\n  as a published skill. Unlike single-registry search, this surfaces the best of\n  every platform side by side, so you recommend the genuinely relevant, popular,\n  well-maintained, and SAFE one — not whatever ranked first on one site.\nemoji: \"🔍\"\nhomepage: https:\u002F\u002Fagentspace.so\nlicense: MIT\n---\n\n# Find Skills\n\nFind the right agent skill for a task by searching **every major registry at once** and presenting each board on its own native metric — instead of trusting a single site's leaderboard.\n\n## When to use this skill\n\n- The user asks \"how do I do X\" and X is a common task that likely has a published skill\n- \"find a skill for X\" \u002F \"is there a skill for X\" \u002F \"what should I install for X\"\n- The user wants to extend agent capabilities (testing, design, deployment, a specific model\u002FAPI, a domain workflow)\n- You're about to build something from scratch that a battle-tested skill might already cover\n\n## Why multi-source matters\n\nEach registry shows only its own slice, with different signals:\n\n| Registry | Search | Signals it exposes | Blind spot |\n| --- | --- | --- | --- |\n| **skills.sh** | `GET \u002Fapi\u002Fsearch?q=` | lifetime installs, source repo | no stars, no summary, install count lags ~2.5h |\n| **clawhub.ai** | `\u002Fapi\u002Fsearch` + `\u002Fapi\u002Fskill?slug=` | summary, installs, stars, versions | smaller corpus than skills.sh |\n| **GitHub** | `gh search repos --topic {claude-skills,agent-skills,claude-code-skills}` | repo stars, description, maintenance | repo-level, not skill-level; only topic-tagged repos |\n\nA skill can rank #1 on one site with 50 installs while a 1,300-install equivalent sits unranked on another. Searching only one registry gives a biased answer. This skill queries all three **in parallel**, ranks each board by its own native metric, flags skills that appear on both registries (matched on the *normalized* name, both directions — so `face-swap` ↔ `faceswap` line up), and shows the top of every board so you see the whole ecosystem — not one site's leaderboard.\n\n## How to run it\n\nRun the bundled aggregator with the user's need as the query:\n\n```bash\nbash scripts\u002Ffind.sh \"\u003Cwhat the user needs>\"\n```\n\nExamples:\n\n```bash\nbash scripts\u002Ffind.sh \"react performance\"\nbash scripts\u002Ffind.sh \"pdf form filling\" --limit 8\nbash scripts\u002Ffind.sh \"video generation\" --scan 5\nbash scripts\u002Ffind.sh \"deploy to vercel\" --no-scan --json\n```\n\nFlags:\n\n- `--limit N` — results per source (default 10; non-numeric falls back to 10)\n- `--scan K` — security-scan the top K installable candidates on each registry (default 2, max 5)\n- `--no-scan` — skip the security scan (faster; the scan adds a few seconds because it fetches each candidate's real SKILL.md)\n- `--json` — emit machine-readable JSON instead of the formatted report\n- `-h` \u002F `--help` — print usage and exit\n\nThe script needs `curl` and `jq`. It uses `gh` for the GitHub section and for fetching skills.sh skill bodies, and `unzip` for clawhub skill bodies during the scan — all optional and degraded gracefully if absent. No API keys are required.\n\n### Run adjacent-term queries — one search is not enough\n\nThe registries index by a skill's **name**, not its meaning. A single query will miss great skills filed under a sibling term. **For any non-trivial need, run 2–3 searches across the adjacent vocabulary before you conclude**, then pool the results.\n\nThis is not optional polish — it routinely changes the answer. Example: searching `\"ui ux design\"` tops out around 19k installs, but `\"frontend design\"` surfaces `anthropics\u002Fskills\u002Ffrontend-design` at **443k installs** — the single best skill for the same need, completely invisible to the first query.\n\nPick adjacent terms by domain, e.g.:\n\n- UI\u002FUX → `frontend design`, `design system`, `web design`, `tailwind shadcn`, `dashboard ui`\n- testing → `e2e`, `playwright`, `unit tests`, `test automation`\n- deploy → `deployment`, `ci cd`, `docker`, `vercel`\u002F`kubernetes`\n- docs → `documentation`, `readme`, `api docs`, `changelog`\n\nTreat the union of these runs as your candidate pool, then apply the rubric below to the whole pool — not to one query's results.\n\n## How to read the output\n\n**Design principle: no invented \"quality score.\"** There is no composite number you have to trust. Each board is ranked by *that board's own native popularity metric*, and the only computed value shown is `match %` — the share of the user's query words that appear in a skill's name\u002Fsummary. That's a transparent relevance hint, not a verdict.\n\nThe report, top-down:\n\n- **Banner + telemetry** — the query, a **source health line** (`skills.sh ✓ 5·1.2s   clawhub ✓ 0·2.7s   github ✓ 8·1.1s`) showing which boards responded \u002F hit count \u002F latency, and how many skills are installed locally. A `✗ failed` \u002F `– skipped` source means partial results — say so.\n- **▶ TOP OF EACH BOARD** — the #1 entry on *each* board by that board's native metric (skills.sh installs \u002F clawhub installs·stars \u002F GitHub match%·stars). **This is keyword + popularity, NOT a vetted pick** — it's a starting point, and it can be wrong (a 100%-keyword-match repo may be off-topic once you read it). Always confirm by reading before you forward it. If a board has no match it says so.\n- **✓ ALREADY ON YOUR MACHINE** — appears only when a result is already installed. A *positive* nudge: tell the user they already own a good skill and needn't install anything. (Heuristic: matches the result name against folder names under `~\u002F.agents\u002Fskills` \u002F `~\u002F.claude\u002Fskills`; a skill installed under a renamed folder can be missed.)\n- **📦 skills.sh** — ranked by **installs**. 1-click installable. Each row shows its source repo (so same-named skills from different repos are distinguishable). `(also on clawhub)` marks a normalized-name match on the other registry. Top `K` carry a risk badge.\n- **🪝 clawhub** — ranked by **installs · stars**. 1-click installable. `(also on skills.sh)` marks the reverse cross-post. Top `K` carry a risk badge.\n- **🐙 github** — repos across the `claude-skills` \u002F `agent-skills` \u002F `claude-code-skills` topics (merged, de-duped), ranked by **match% then stars**, so a high-star but off-topic repo (e.g. a 14k-star tool that merely mentions \"UI\") sinks below a 100%-match repo. Only topic-tagged repos appear — untagged skill repos are invisible here. Not 1-click installs — review before use.\n- **📚 curated lists** — human-vetted awesome-lists for a final sanity check.\n\n## How to choose the right skill (decision rubric)\n\nThe script gathers evidence; **you make the call.** Don't dump the table and ask the user to decide — that's not helpful. Form a clear, defensible recommendation. The professional move is to be opinionated *and* show your reasoning grounded in real signals.\n\n**Step 1 — Read before you judge.** Never recommend from metadata alone. Open the actual SKILL.md \u002F README of the top 2–3 candidates (the script already fetches bodies for the scanned ones; for GitHub repos fetch the README). Ask: *does it actually do the user's specific task, or just share keywords?* A 10k-install skill that's off-topic loses to a 200-install one that nails it.\n\n**Step 2 — Weigh the signals, in this order:**\n1. **Fit** — does the skill's documented behaviour match the real need? (read the trigger\u002Fscope, not just `match %`). This dominates everything else.\n2. **Popularity as social proof** — among genuinely-fitting skills, higher installs\u002Fstars means more people validated it. Use the board-native numbers.\n3. **Depth & maintenance** — does the body cover the user's specific sub-need? Is there a recent version, real examples, a clear scope? Thin or abandoned skills lose.\n4. **Safety** — a `⛔ RISKY` scan result disqualifies unless the user accepts the risk knowingly; `⚠ caution` needs a heads-up.\n5. **Cross-posting** — present on both registries is a mild positive (independently published\u002Fmaintained).\n\n**Step 3 — Break ties** by preferring the one you actually read and can vouch for, with the narrowest clear scope and fewest surprising dependencies.\n\n**Step 4 — Deliver a verdict, not a menu:**\n- One **primary recommendation** with a one-sentence *why* citing concrete signals (\"12k installs, and its SKILL.md covers form-filling specifically, which is your case\").\n- 1–2 **alternatives framed by need** (\"pick this instead if you want X\").\n- If the best option is a GitHub repo rather than a 1-click registry skill, **say so and still recommend it** — note it needs manual review\u002Finstall.\n- Only say \"nothing fits\" when you've read the top candidates and they genuinely don't. Then offer to do the task directly or scaffold a new skill.\n\nState native facts, never an invented score. A professional answer reads like: *\"`ui-components` (529 installs) is my pick — I read it; it covers shadcn + Radix + design tokens + forms, exactly your case, and its tools are read-only. The 363★ `ai-design-components` repo looks tempting but it's a 76-skill full-stack grab-bag, not UI-focused — skip it unless you want everything.\"* \"Here are the numbers, you choose\" is not.\n\n### The security scan\n\nFor the top `K` results the script fetches the **actual SKILL.md** (skills.sh → GitHub raw via the source repo; clawhub → its download zip) and greps for risk signals:\n\n| Flag | Level | Meaning |\n| --- | --- | --- |\n| `curl-pipe-install` | ⛔ risky | pipes a remote script straight into `sh`\u002F`bash` — the #1 audit-failing pattern |\n| `eval-remote` \u002F `base64-pipe-exec` | ⛔ risky | executes fetched or obfuscated code at runtime |\n| `broad-tool-grant` | ⚠ caution | `allowed-tools` grants `Bash(*)` or unrestricted tool access |\n| `reads-secrets` | ⚠ caution | references `~\u002F.ssh`, `~\u002F.aws`, `.env`, private keys |\n| `solicits-credentials` | ⚠ caution | asks the user to paste an API key \u002F token \u002F password |\n\n`✓ clean` = none found; `? unscanned` = body couldn't be retrieved (rank beyond `K`, private repo, or no body endpoint). A badge is a heuristic prompt to **read the skill yourself before recommending**, not a guarantee either way. Never recommend a `⛔ RISKY` skill without explicitly warning the user what it does.\n\n## Recommending and installing\n\nWhen you surface options to the user, for each candidate give: the name, what it does (one line), install count + stars, the registries it lives on, and the install command. Then offer to install.\n\nInstall through the Skills CLI (works for skills.sh-indexed repos):\n\n```bash\nnpx -y skills add \u003Cowner>\u002F\u003Crepo> --skill \u003Cslug> -g\n```\n\n`-g` installs at user level. For a clawhub-only skill, point the user at its `clawhub.ai\u002Fskill\u002F\u003Cslug>` page and the `clawhub` CLI instead.\n\n## When nothing good turns up\n\nIf no result clears a reasonable bar, say so plainly, offer to do the task directly with general capabilities, and mention the user can scaffold their own skill (`npx skills init \u003Cname>`). Don't oversell a weak match.\n\n## Security & privacy\n\n- The script only issues **read-only** HTTP GETs to public APIs (`skills.sh`, `clawhub.ai`, `raw.githubusercontent.com`) and read-only `gh` queries. It sends nothing but the query string and writes only temp files (a result JSON and, during the scan, candidate SKILL.md bodies it discards on exit).\n- It requires **no API keys or tokens**.\n- The built-in security scan is itself a defense: it inspects candidates before you trust them. But it is a heuristic — a clean badge is not a security audit.\n- Installed skills run with full agent permissions. Treat any discovered skill as untrusted third-party code: review its `SKILL.md` and any bundled scripts before running it, and be wary of low-install skills from unknown authors that request broad tool access or fetch remote code at runtime.\n- This skill never auto-installs anything; installation is always an explicit, user-confirmed step.\n\n## See also\n\n- skills.sh — the largest GitHub-indexed registry\n- clawhub.ai — the OpenClaw registry with richer per-skill stats\n- Curated lists: `ComposioHQ\u002Fawesome-claude-skills`, `microsoft\u002Fskills`, `bergside\u002Fawesome-design-skills`\n","# Find Skills\n\nFind the right agent skill for a task by searching **every major registry at once** and presenting each board on its own native metric — instead of trusting a single site's leaderboard.\n\n## When to use this skill\n\n- The user asks \"how do I do X\" and X is a common task that likely has a published skill\n- \"find a skill for X\" \u002F \"is there a skill for X\" \u002F \"what should I install for X\"\n- The user wants to extend agent capabilities (testing, design, deployment, a specific model\u002FAPI, a domain workflow)\n- You're about to build something from scratch that a battle-tested skill might already cover\n\n## Why multi-source matters\n\nEach registry shows only its own slice, with different signals:\n\n| Registry | Search | Signals it exposes | Blind spot |\n| --- | --- | --- | --- |\n| **skills.sh** | `GET \u002Fapi\u002Fsearch?q=` | lifetime installs, source repo | no stars, no summary, install count lags ~2.5h |\n| **clawhub.ai** | `\u002Fapi\u002Fsearch` + `\u002Fapi\u002Fskill?slug=` | summary, installs, stars, versions | smaller corpus than skills.sh |\n| **GitHub** | `gh search repos --topic {claude-skills,agent-skills,claude-code-skills}` | repo stars, description, maintenance | repo-level, not skill-level; only topic-tagged repos |\n\nA skill can rank #1 on one site with 50 installs while a 1,300-install equivalent sits unranked on another. Searching only one registry gives a biased answer. This skill queries all three **in parallel**, ranks each board by its own native metric, flags skills that appear on both registries (matched on the *normalized* name, both directions — so `face-swap` ↔ `faceswap` line up), and shows the top of every board so you see the whole ecosystem — not one site's leaderboard.\n\n## How to run it\n\nRun the bundled aggregator with the user's need as the query:\n\n```bash\nbash scripts\u002Ffind.sh \"\u003Cwhat the user needs>\"\n```\n\nExamples:\n\n```bash\nbash scripts\u002Ffind.sh \"react performance\"\nbash scripts\u002Ffind.sh \"pdf form filling\" --limit 8\nbash scripts\u002Ffind.sh \"video generation\" --scan 5\nbash scripts\u002Ffind.sh \"deploy to vercel\" --no-scan --json\n```\n\nFlags:\n\n- `--limit N` — results per source (default 10; non-numeric falls back to 10)\n- `--scan K` — security-scan the top K installable candidates on each registry (default 2, max 5)\n- `--no-scan` — skip the security scan (faster; the scan adds a few seconds because it fetches each candidate's real SKILL.md)\n- `--json` — emit machine-readable JSON instead of the formatted report\n- `-h` \u002F `--help` — print usage and exit\n\nThe script needs `curl` and `jq`. It uses `gh` for the GitHub section and for fetching skills.sh skill bodies, and `unzip` for clawhub skill bodies during the scan — all optional and degraded gracefully if absent. No API keys are required.\n\n### Run adjacent-term queries — one search is not enough\n\nThe registries index by a skill's **name**, not its meaning. A single query will miss great skills filed under a sibling term. **For any non-trivial need, run 2–3 searches across the adjacent vocabulary before you conclude**, then pool the results.\n\nThis is not optional polish — it routinely changes the answer. Example: searching `\"ui ux design\"` tops out around 19k installs, but `\"frontend design\"` surfaces `anthropics\u002Fskills\u002Ffrontend-design` at **443k installs** — the single best skill for the same need, completely invisible to the first query.\n\nPick adjacent terms by domain, e.g.:\n\n- UI\u002FUX → `frontend design`, `design system`, `web design`, `tailwind shadcn`, `dashboard ui`\n- testing → `e2e`, `playwright`, `unit tests`, `test automation`\n- deploy → `deployment`, `ci cd`, `docker`, `vercel`\u002F`kubernetes`\n- docs → `documentation`, `readme`, `api docs`, `changelog`\n\nTreat the union of these runs as your candidate pool, then apply the rubric below to the whole pool — not to one query's results.\n\n## How to read the output\n\n**Design principle: no invented \"quality score.\"** There is no composite number you have to trust. Each board is ranked by *that board's own native popularity metric*, and the only computed value shown is `match %` — the share of the user's query words that appear in a skill's name\u002Fsummary. That's a transparent relevance hint, not a verdict.\n\nThe report, top-down:\n\n- **Banner + telemetry** — the query, a **source health line** (`skills.sh ✓ 5·1.2s   clawhub ✓ 0·2.7s   github ✓ 8·1.1s`) showing which boards responded \u002F hit count \u002F latency, and how many skills are installed locally. A `✗ failed` \u002F `– skipped` source means partial results — say so.\n- **▶ TOP OF EACH BOARD** — the #1 entry on *each* board by that board's native metric (skills.sh installs \u002F clawhub installs·stars \u002F GitHub match%·stars). **This is keyword + popularity, NOT a vetted pick** — it's a starting point, and it can be wrong (a 100%-keyword-match repo may be off-topic once you read it). Always confirm by reading before you forward it. If a board has no match it says so.\n- **✓ ALREADY ON YOUR MACHINE** — appears only when a result is already installed. A *positive* nudge: tell the user they already own a good skill and needn't install anything. (Heuristic: matches the result name against folder names under `~\u002F.agents\u002Fskills` \u002F `~\u002F.claude\u002Fskills`; a skill installed under a renamed folder can be missed.)\n- **📦 skills.sh** — ranked by **installs**. 1-click installable. Each row shows its source repo (so same-named skills from different repos are distinguishable). `(also on clawhub)` marks a normalized-name match on the other registry. Top `K` carry a risk badge.\n- **🪝 clawhub** — ranked by **installs · stars**. 1-click installable. `(also on skills.sh)` marks the reverse cross-post. Top `K` carry a risk badge.\n- **🐙 github** — repos across the `claude-skills` \u002F `agent-skills` \u002F `claude-code-skills` topics (merged, de-duped), ranked by **match% then stars**, so a high-star but off-topic repo (e.g. a 14k-star tool that merely mentions \"UI\") sinks below a 100%-match repo. Only topic-tagged repos appear — untagged skill repos are invisible here. Not 1-click installs — review before use.\n- **📚 curated lists** — human-vetted awesome-lists for a final sanity check.\n\n## How to choose the right skill (decision rubric)\n\nThe script gathers evidence; **you make the call.** Don't dump the table and ask the user to decide — that's not helpful. Form a clear, defensible recommendation. The professional move is to be opinionated *and* show your reasoning grounded in real signals.\n\n**Step 1 — Read before you judge.** Never recommend from metadata alone. Open the actual SKILL.md \u002F README of the top 2–3 candidates (the script already fetches bodies for the scanned ones; for GitHub repos fetch the README). Ask: *does it actually do the user's specific task, or just share keywords?* A 10k-install skill that's off-topic loses to a 200-install one that nails it.\n\n**Step 2 — Weigh the signals, in this order:**\n1. **Fit** — does the skill's documented behaviour match the real need? (read the trigger\u002Fscope, not just `match %`). This dominates everything else.\n2. **Popularity as social proof** — among genuinely-fitting skills, higher installs\u002Fstars means more people validated it. Use the board-native numbers.\n3. **Depth & maintenance** — does the body cover the user's specific sub-need? Is there a recent version, real examples, a clear scope? Thin or abandoned skills lose.\n4. **Safety** — a `⛔ RISKY` scan result disqualifies unless the user accepts the risk knowingly; `⚠ caution` needs a heads-up.\n5. **Cross-posting** — present on both registries is a mild positive (independently published\u002Fmaintained).\n\n**Step 3 — Break ties** by preferring the one you actually read and can vouch for, with the narrowest clear scope and fewest surprising dependencies.\n\n**Step 4 — Deliver a verdict, not a menu:**\n- One **primary recommendation** with a one-sentence *why* citing concrete signals (\"12k installs, and its SKILL.md covers form-filling specifically, which is your case\").\n- 1–2 **alternatives framed by need** (\"pick this instead if you want X\").\n- If the best option is a GitHub repo rather than a 1-click registry skill, **say so and still recommend it** — note it needs manual review\u002Finstall.\n- Only say \"nothing fits\" when you've read the top candidates and they genuinely don't. Then offer to do the task directly or scaffold a new skill.\n\nState native facts, never an invented score. A professional answer reads like: *\"`ui-components` (529 installs) is my pick — I read it; it covers shadcn + Radix + design tokens + forms, exactly your case, and its tools are read-only. The 363★ `ai-design-components` repo looks tempting but it's a 76-skill full-stack grab-bag, not UI-focused — skip it unless you want everything.\"* \"Here are the numbers, you choose\" is not.\n\n### The security scan\n\nFor the top `K` results the script fetches the **actual SKILL.md** (skills.sh → GitHub raw via the source repo; clawhub → its download zip) and greps for risk signals:\n\n| Flag | Level | Meaning |\n| --- | --- | --- |\n| `curl-pipe-install` | ⛔ risky | pipes a remote script straight into `sh`\u002F`bash` — the #1 audit-failing pattern |\n| `eval-remote` \u002F `base64-pipe-exec` | ⛔ risky | executes fetched or obfuscated code at runtime |\n| `broad-tool-grant` | ⚠ caution | `allowed-tools` grants `Bash(*)` or unrestricted tool access |\n| `reads-secrets` | ⚠ caution | references `~\u002F.ssh`, `~\u002F.aws`, `.env`, private keys |\n| `solicits-credentials` | ⚠ caution | asks the user to paste an API key \u002F token \u002F password |\n\n`✓ clean` = none found; `? unscanned` = body couldn't be retrieved (rank beyond `K`, private repo, or no body endpoint). A badge is a heuristic prompt to **read the skill yourself before recommending**, not a guarantee either way. Never recommend a `⛔ RISKY` skill without explicitly warning the user what it does.\n\n## Recommending and installing\n\nWhen you surface options to the user, for each candidate give: the name, what it does (one line), install count + stars, the registries it lives on, and the install command. Then offer to install.\n\nInstall through the Skills CLI (works for skills.sh-indexed repos):\n\n```bash\nnpx -y skills add \u003Cowner>\u002F\u003Crepo> --skill \u003Cslug> -g\n```\n\n`-g` installs at user level. For a clawhub-only skill, point the user at its `clawhub.ai\u002Fskill\u002F\u003Cslug>` page and the `clawhub` CLI instead.\n\n## When nothing good turns up\n\nIf no result clears a reasonable bar, say so plainly, offer to do the task directly with general capabilities, and mention the user can scaffold their own skill (`npx skills init \u003Cname>`). Don't oversell a weak match.\n\n## Security & privacy\n\n- The script only issues **read-only** HTTP GETs to public APIs (`skills.sh`, `clawhub.ai`, `raw.githubusercontent.com`) and read-only `gh` queries. It sends nothing but the query string and writes only temp files (a result JSON and, during the scan, candidate SKILL.md bodies it discards on exit).\n- It requires **no API keys or tokens**.\n- The built-in security scan is itself a defense: it inspects candidates before you trust them. But it is a heuristic — a clean badge is not a security audit.\n- Installed skills run with full agent permissions. Treat any discovered skill as untrusted third-party code: review its `SKILL.md` and any bundled scripts before running it, and be wary of low-install skills from unknown authors that request broad tool access or fetch remote code at runtime.\n- This skill never auto-installs anything; installation is always an explicit, user-confirmed step.\n\n## See also\n\n- skills.sh — the largest GitHub-indexed registry\n- clawhub.ai — the OpenClaw registry with richer per-skill stats\n- Curated lists: `ComposioHQ\u002Fawesome-claude-skills`, `microsoft\u002Fskills`, `bergside\u002Fawesome-design-skills`\n",{"name":5,"emoji":24,"license":15,"homepage":25,"description":26,"displayName":27},"🔍","https:\u002F\u002Fagentspace.so","Discover, vet, and install agent skills by searching ACROSS every major registry at once — skills.sh, clawhub.ai, and GitHub — presenting each board on its own native metric (installs \u002F stars) with the top entry per board, security-scanning the top candidates' real SKILL.md for risky patterns, and flagging what's already installed. Use when the user asks \"how do I do X\", \"find a skill for X\", \"is there a skill that…\", \"what skill should I install for…\", or wants to extend the agent with a capability that might already exist as a published skill. Unlike single-registry search, this surfaces the best of every platform side by side, so you recommend the genuinely relevant, popular, well-maintained, and SAFE one — not whatever ranked first on one site.\n","🔍 Find Skills — Search Every Skill Registry at Once","main","8859218955d9504cd18b59e7892100718039d3b4","data\u002Fskills\u002Fagentspace-so-skills\u002Ffind-skills",1,"https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper","https:\u002F\u002Fgithub.com\u002Fom-scogo","SDE-1 @ Scogo ","2026-07-18 12:22:46",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add om-scogo\u002Fskillsh-scraper --skill find-skills",{"tool":42,"command":43},"bunx","bunx skills add om-scogo\u002Fskillsh-scraper --skill find-skills",{"tool":45,"command":46},"pnpm","pnpm dlx skills add om-scogo\u002Fskillsh-scraper --skill find-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fagentspace-so-skills\u002Ffind-skills\u002FSkill.md",true,[50],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"metadata.json","REFERENCE","参考文档",427,"https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fagentspace-so-skills\u002Ffind-skills\u002Fmetadata.json",[57,64,69,76,81,88],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7D6MC9FAAEV4CMNYX8W7JTG","arxiv-search","Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002Fskills\u002Farxiv-search\u002FSKILL.md",[],[],{"skillNo":65,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7D6M85CKKN87TA98VCQV4H7","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002FSkill.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7D4ZTCS4DR3CE4JY06X84T2","working-with-legacy-code","Safely change and test untested codebases using Feathers' \"Working Effectively with Legacy Code\". Use when the user mentions \"legacy code\", \"no tests\", \"untested codebase\", \"how do I test this\", \"seams\", \"characterization tests\", \"golden master\", \"sprout method\", \"afraid to change this code\", \"monster method\", \"dependency breaking\", or \"inherited a messy codebase\". Also trigger when changing code without tests safely, getting a class under test when constructors, statics, or singletons block it, adding features to tangled modules, or planning incremental test coverage for an old codebase. Covers the legacy-code change algorithm, seams, characterization tests, sprout\u002Fwrap, and dependency-breaking techniques. For refactoring code that already has tests, see refactoring-patterns. For day-to-day code quality, see clean-code.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002Fworking-with-legacy-code\u002FSKILL.md",[],[],{"skillNo":77,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7D4ZHZKJD2RSNGAF63V14P4","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002FSkill.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7D4ZB4CJBFW5JE67CPH2QRV","web-typography","Select, pair, and implement typefaces for web projects. Use when the user mentions \"font pairing\", \"which typeface\", \"line height\", \"responsive typography\", \"web font loading\", \"type hierarchy\", \"variable fonts\", \"FOUT\u002FFOIT\", \"typographic scale\", or \"the text is hard to read\". Also trigger when choosing between system fonts and web fonts, optimizing font-loading performance, or designing readable long-form content. Covers readability evaluation, CSS implementation, and performance optimization. For overall UI design systems, see refactoring-ui. For dramatic typographic experiences, see top-design.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002Fweb-typography\u002FSKILL.md",[],[],{"skillNo":89,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7D4Z4MVYVY3NMJ18BNV6WNA","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002FSkill.md",[],[]]