Skill Fetch
Search skills.sh and related catalogs, compare scored candidates, and install the best match without manual repo hunting.
Overview
skill-fetch is a journey-wide agent skill that ranks external skills, pages results, and installs your pick—usable whenever you need a capability you do not have loaded yet.
Install
npx skills add https://github.com/girofu/skill-fetch --skill skill-fetchWhat is this skill?
- Deduped search results sorted by quality score with 5 results per page
- Plain-text comparison blocks: pros, cons, stars, last-updated, and source URLs
- Pagination via `c` / continue without re-running search; global item numbers across pages
- First-page recommendation with score and short rationale
- Scoring ties to documented quality signals in references
- Results displayed 5 per page with global numbering
- Quality scores shown on a 0–100 scale with 🟢/🟡 indicators in the template
Adoption & trust: 1 installs on skills.sh; 28 GitHub stars; 1/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You know you need a specialized agent skill but drowning in duplicate GitHub and marketplace listings with no consistent way to compare or install.
Who is it for?
Builders who want agent-driven skill shopping with explicit scoring and multi-select install (`1,3`).
Skip if: Curated-only workflows where you already pinned exact skill IDs in repo config and forbid dynamic installs.
When should I use this skill?
You need an external agent skill for the current task and want ranked catalog results with install-by-number flow.
What do I get? / Deliverables
You receive a scored, paginated shortlist, a recommended default on page one, and installed skill(s) after replying with item numbers.
- Ranked comparison listing
- User-selected skill installation
- Optional multi-install from comma-separated IDs
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Search for competitor-research or audience skills when kicking off a new product thread.
Pull a landing-page or scope skill after pagination shows the top five matches.
Install an API or payment skill recommended on page one with a 🟢 score.
Add a code-review skill when none is loaded in the current agent session.
Fetch analytics or lifecycle skills when instrumentation work starts mid-journey.
How it compares
Operational install workflow for live catalogs—not the same as browsing Prism journey hubs for editorial placement.
Common Questions / FAQ
Who is skill-fetch for?
Solo builders using Claude Code, Cursor, or similar agents who pull skills from skills.sh-style sources during real tasks.
When should I use skill-fetch?
Across Idea through Operate whenever you lack a skill for the task—e.g., finding a validator in Validate, an integration in Build, or an analytics skill in Grow.
Is skill-fetch safe to install?
Installing third-party skills can run arbitrary guidance; review the Security Audits panel on this page and vet repos before executing install steps.
SKILL.md
READMESKILL.md - Skill Fetch
# Installation Guide Complete installation workflow for skill-fetch. Referenced from SKILL.md Step 3. --- ### Step 3: Analyze, Select, Install #### 3a. Display Comparison Analysis (plain-text) Sort all deduplicated results by quality score. Maintain the full sorted list. Display 5 per page (1-5, 6-10, 11-15...): ``` 🔍 Found {N} relevant skills, showing {start}-{end} of {N}: {start}. {skill-name} [{source}] 🟢 {score}/100 | ⭐{stars} | Updated: {YYYY-MM} 📦 {githubUrl or skillsmp URL} Content: {what the skill provides} Pros: {match with current task, coverage} Cons: {limitations or gaps} {start+1}. {skill-name-2} [{source}] 🟡 {score}/100 | ⭐{stars} | Updated: {YYYY-MM} 📦 {repo URL} ... ...5 items per page... 💡 Recommendation: #{N} {skill-name-X} ({score}/100 🟢) Reason: {1-2 sentences explaining why it best fits the need} --- Reply with a number to install (e.g., `1`), comma-separated for multiple (e.g., `1,3`) Reply `c` or "continue" to see next 5 ({end+1}-{end+5}) Reply "skip" to end search ``` **Pagination rules:** - First page shows items 1-5 with recommendation - User replies `c` or "continue" → show next 5 (6-10), ranking continues, no re-search - Can keep paging until list is exhausted; last page shows "All {N} results displayed" - User can reply with a number on any page (numbers are global, e.g., `7` on page 2 = item #7) - Recommendation is only shown on the first page **Scoring formula:** See `references/quality-signals.md` and SKILL.md Step 2.5 for the full scoring algorithm. **Analysis principles:** - Sort by total score descending; break ties by relevance first - Each header line shows score and color grade (🟢/🟡/🔴) - Add `⚠️` for skills not updated in 6+ months - Apply security labels per `references/quality-signals.md` §6: `🔒 Official`, `🔒 Verified`, `⚠️ Partial`, `⚠️ Unverified`, `⚠️ Security Concerns` - When multiple skills have different strengths, explain the differences so the user can decide #### 3b. Wait for User Reply - **Number** (e.g., `1` or `7`) → Install the selected skill (global numbering, works across pages) - **Multiple** (e.g., `1,3`) → Install multiple skills - **`c` or "continue"** → Show next 5 results (ranking continues, no re-search) - **"skip"** → Output `External skill fetch: user chose to skip installation.` and continue task - **New keywords** → Return to Step 2 and re-search #### 3c. Choose Installation Location (MANDATORY — must ask before installing) **⚠️ MANDATORY: Always display this menu and wait for user reply. Never auto-select based on default.** Before installing, ask the user for installation scope (if not already specified): ``` 📦 Install location: [G] Global (available to all projects) → ~/.claude/skills/{skill-name}/ [L] Local (this project only) → .claude/skills/{skill-name}/ 👉 Reply G or L to continue. ``` **Installation path reference:** | Scope | Path | Use Case | |-------|------|----------| | Global | `~/.claude/skills/{skill-name}/` | General skills (shared across projects) | | Local | `{project-root}/.claude/skills/{skill-name}/` | Project-specific skills (travels with repo) | **Claude Code Skill Discovery order** (first found wins): 1. `{project}/.claude/skills/` — Project local 2. `~/.claude/skills/` — User global **Cross-platform skill directories:** | Agent | Global Path | Local Path | |-------|-------------|------------| | Claude Code | `~/.claude/skills/{name}/` | `.claude/skills/{name}/` | | Cursor | `~/.cursor/skills/{name}/` | `.cursor/skills/{name}/` | | Codex | `~/.codex/skills/{name}/` | `.codex/skills/{name}/` | | Gemini CLI | `~/.gemini/skills/{name}/` | `.gemini/skills/{name}/` | | Windsurf | `~/.windsurf/skills/{name}/` | `.windsurf/skills/{name}/` | | Amp | `~/.amp/skills/{name}/` | `.amp/skills/{name}/` | **Auto-detection:** Check which agent directories exist and install to the detected agent's path. If multiple agents are detected, ask the user which to install for. #### 3d. Execute In