Skip to main content
skill CX Codex

skill-hunt — Claude Code skill: search and install

The skill-hunt Claude Code skill finds skills that fill a capability gap. It ranks candidates, checks a selected skill, then installs it in quarantine.

MIT ★ 26 updated 2026-11-16

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add wrg32786/aigent-os --skill skill-hunt -a claude-code
Open on GitHub

What skill-hunt does

skill-hunt searches for a skill when no match exists for a needed capability. It queries GitHub, marketplaces, and skill lists in parallel; without a search argument, it reads the latest open item in SKILL_GAPS.md. Candidates are scored for adoption, update recency, Claude Code compatibility, licensing, and safety.

Before installation, the chosen skill is scanned for destructive commands, suspicious network requests, writes beyond allowed locations, and credential access. It is then copied to quarantine and tested on a safe task. A successful test leads to indexing; a failed test or empty search marks the gap wont-fix and suggests /solution-hunt. GitHub and Tavily MCP tools are required for searches.

What it helps with

  • find a skill to fill an agent capability gap
  • compare candidates by compatibility, license, and safety
  • scan a candidate before installing it
  • test an installed skill in quarantine

Example prompts for the agent

  • Find a skill for database migrations.
  • Search for a skill that analyzes logs and rank the candidates.
  • Use the latest open entry in SKILL_GAPS.md to search for a skill.

How to install skill-hunt

1Skills CLI (Vercel)

npx skills add wrg32786/aigent-os --skill skill-hunt -a claude-code

2Manually: put the files in place

~/.claude/skills/skill-hunt/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/skill-hunt/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about skill-hunt

How do I install skill-hunt in Claude Code?

Run npx skills add wrg32786/aigent-os --skill skill-hunt -a claude-code. The skill file is located at ~/.claude/skills/skill-hunt/SKILL.md.

What does skill-hunt do?

It searches for skills that cover missing capabilities, ranks the results, and scans the selected candidate before placing it in quarantine. After a safe test, the skill can be added to the index.

What does skill-hunt need to run?

Searches require the GitHub and Tavily MCP tools.

Source text

SKILL.md · MIT
---
name: skill-hunt
description: "Search external sources and rank skills for missing capabilities. Use when hunting for a skill to fill a capability gap."
---

# /skill-hunt — Search externally for missing capabilities

When `/skill-recall` finds no match, this skill searches GitHub, skill marketplaces, and awesome-lists for a portable Claude Code skill that fills the gap.

## Trigger

`/skill-hunt <gap description>` or `/skill-hunt` (reads latest open gap from SKILL_GAPS.md)

## Flow

### 1. Identify the gap
- If argument provided: use it as the search query
- If no argument: read `$AIGENT_VAULT/memory/SKILL_GAPS.md`, take the most recent `open` entry

### 2. Search external sources
Run these searches in parallel:

**GitHub repos:**
```
mcp__github__search_repositories: "claude code skill {gap}" OR "claude-code {gap}"
mcp__github__search_code: "SKILL.md {gap keywords}" path:SKILL.md
```

**Skill marketplaces (via Tavily):**
```
mcp__tavily__tavily_search: "claude code skill {gap} site:github.com OR site:skills.pub"
mcp__tavily__tavily_search: "awesome agent skills {gap}"
```

**Known indexes:**
- `anthropics/awesome-claude-code-skills` (if it exists)
- `anthropics/awesome-claude-code` community list
- `rfxlamia/skillkit-marketplace`
- `nicekate/awesome-agent-skills`

### 3. Rank candidates
Score each candidate (0-100) on:
- **Stars/adoption** (0-20): >100 stars = 20, >10 = 10, <10 = 5
- **Recency** (0-20): updated within 30d = 20, 90d = 15, 180d = 10, older = 5
- **Claude Code compatibility** (0-30): has SKILL.md = 30, has .claude/ = 20, generic agent skill = 10, no skill file = 0
- **License** (0-15): Apache/MIT = 15, other OSS = 10, no license = 0
- **Safety** (0-15): no destructive commands = 15, some file writes = 10, network calls to unknown hosts = 5, suspicious patterns = 0

### 4. Present top 3
For each candidate, show:
- Repo name + URL + score
- One-line description
- License
- Safety flags (if any)

### 5. Safety scan (on user selection)
Before installing, scan the SKILL.md and any referenced scripts for:
- `rm -rf`, `git push --force`, destructive bash patterns
- Network calls to hardcoded external URLs (not MCP tools)
- File mutations outside `~/.claude/skills/` or the vault
- Credential access or environment variable reads beyond expected scope
- Obfuscated code

Report findings. If clean: proceed to install. If flagged: surface warnings and ask user.

### 6. Quarantine install
```bash
# Copy skill to quarantine location
cp -r <source> ~/.claude/skills/<name>/
```
Add `quarantine: true` to SKILL.md frontmatter (first line after `---`).

### 7. Test
Run the skill on a dummy/safe task to verify it works. Report result.

### 8. Promote (on success)
- Remove `quarantine: true` from SKILL.md frontmatter
- Add entry to `memory/SKILL_LEDGER.md` under the correct taxonomy path
- Add entry to `.claude/skill-index.json` with at least 3 trigger phrases
- Update `memory/SKILL_GAPS.md`: set status to `resolved`, add resolution note
- Output: "Skill installed with a precise description, indexed in SKILL_LEDGER."

### 9. Failure path
If no suitable candidate found OR test fails:
- Update `memory/SKILL_GAPS.md`: set status to `wont-fix` with reason
- Suggest `/solution-hunt` as fallback (build a workaround instead of installing)

## Boundary

> Creative workaround means legitimate alternate route. NEVER install skills that bypass security, violate ToS, exploit vulnerabilities, or hide behavior.

## Related

- [[concepts/Capability Expansion Doctrine]] — the doctrine governing this flow
- [[memory/SKILL_LEDGER]] — where promoted skills are indexed
- [[memory/SKILL_GAPS]] — the gap ledger this skill reads and updates
- [[Lego Arsenal Doctrine]] — every installed skill is a reusable Lego

© wrg32786 · MIT · wrg32786/aigent-os

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set58

The whole set →
start start — a Claude Code skill that opens a home screen on first launch or when work resumes. It guides setup or gives a brief status update with an action menu. CX Codex +1 ★ 26repo stars sprite-spec This Claude Code skill turns pixel-art character ideas into sprite specifications. It activates for character or sprite-sheet design, covering palettes, proportions, and animation states. CX Codex +1 ★ 26repo stars solution-hunt The solution-hunt Claude Code skill finds legitimate alternatives when a task hits a blocker. It searches local notes and skills, then looks through GitHub and documentation. CX Codex +1 ★ 26repo stars skill-recall This Claude Code skill matches a task with local skills. Run /skill-recall to find candidates or record a gap when none fit. CX Codex +1 ★ 26repo stars Skill Audit The Skill Audit Claude Code skill checks skill usage and whether descriptions match the prompts that trigger them. It also flags idle skills and recurring work with no matching skill. CX Codex +1 ★ 26repo stars ship-adapter The ship-adapter Claude Code skill turns schemas and API contracts into adapters. It runs for database adapters, API client wrappers, interface adapters, and data transformers. CX Codex +1 ★ 26repo stars setup This Claude Code skill configures aigent-OS identity, priorities, and authority boundaries. Run /setup to configure the system or revise specific sections later. CX Codex +1 ★ 26repo stars semantic-search The semantic-search Claude Code skill searches an Obsidian vault by meaning using local embeddings. It runs for finding related notes or recalling what you wrote about a topic. CX Codex +1 ★ 26repo stars

Project sponsors

Companies that keep this analytics open