agentleFS
JIRBOYJIRBOY/agent-skills-bridge/SKILL.md

agent-skills-bridge

Skill0 starsChanged 4 months agoMITView on GitHub

Cross-Agent Skills Bridge. Discovers and indexes skill directories from 36 AI coding agents (Claude Code, Cursor, GitHub Copilot, Cline, Roo Code, Windsurf, and more) per the Agent Skills open standard (skills.sh). Builds a unified searchable index, detects cross-agent duplicates, and recommends the best version. Loads skills on-demand from original paths — never copies. Trigger: skill bridge, cross-agent skills, find skills, index skills, search skills, 技能桥接, 跨工具技能, 找技能, 搜索技能.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. sethliao/one-person-studio★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    roots: Check configured roots paths first

    line 91
  2. Distinctive:

    Don't re-read: after reading recommended version, skip duplicates

    line 146
  3. Distinctive:

    Read-only: never modify other agents' skill files

    line 191
  4. Very specific:

    No hardcoded paths: all paths managed via config.json, code uses only env vars

    line 196

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Agent Skills Bridge (v3.0)

Universal cross-agent skills index. Discovers skill directories from 36 AI coding agents on your machine, builds a unified searchable index, detects duplicates, and recommends the best version — all from original paths, no copying.

Core Principle: Index, Don't Copy

Don't move other agents' skills into your own library. Build a unified index, load on demand from the original path, done.

PrincipleDetail
Index37 agents × 2000+ skills indexed, one search covers all
Load on demandWhen a skill matches, Read its original SKILL.md, follow instructions, move on
DedupSame skill across multiple agents → auto-recommend best version
No blind copyingOnly integrate into your own library after ≥3 uses + confirmed superiority
Read-onlyNever modify other agents' skill files

What's New in v3.0

ChangeDetail
UniversalExpanded from 12 to 36 agents per the Agent Skills open standard
Cross-platformForward-slash paths, ${HOME} / ${APPDATA} env vars — works on Windows, macOS, Linux
No hardcoded pathsZero machine-specific paths in code or default config
Dynamic search_rootsIterates all config keys (home/config/local) instead of hardcoded keys
Bundled configFull 37-agent config.json ships with the repo

Supported Agents (37)

Based on the Agent Skills open standard:

PriorityAgents
P1 (major)Claude Code, Cursor, GitHub Copilot
P2 (established)Cline, Roo Code, Windsurf, Continue, Codex, WorkBuddy
P3 (growing)Gemini CLI, CodeBuddy, Qwen Code, Trae, Trae CN, OpenClaude, Amp, Kimi Code CLI, Goose, Kilo Code, OpenHands, OpenCode
P4 (niche)Antigravity, Moltbot, Command Code, Crush, Droid, Junie, Kiro CLI, Kode, MCPJam, Mux, Pi, Qoder, Zencoder, Neovate, Pochi

Each agent has standard roots (global path) and discover patterns (project-level path) defined in config.json.## Configuration

config.json

Path: agent-skills-bridge/config.json

{
  "version": "3.0.0",
  "standard": {
    "name": "Agent Skills Open Standard",
    "url": "https://github.com/scotttrinh/skills"
  },
  "search_roots": {
    "home": ["${HOME}", "${USERPROFILE}"],
    "config": ["${HOME}/.config", "${APPDATA}"],
    "local": ["${HOME}/.local", "${LOCALAPPDATA}"]
  },
  "tools": {
    "claude-code": {
      "label": "Claude Code",
      "roots": ["${HOME}/.claude/skills"],
      "fallback": ["${HOME}/.claude/plugins"],
      "priority": 1,
      "discover": [".claude/skills"]
    },
    // ... 36 more agents
  },
  "domain_keywords": { ... }
}

Environment Variables

VariableExpands toPlatform
${HOME}User home directoryAll
${USERPROFILE}Windows user directoryWindows
${APPDATA}AppData RoamingWindows
${LOCALAPPDATA}AppData LocalWindows
~User home directoryAll (shorthand)

Path Validation (3-tier)

  1. roots: Check configured roots paths first
  2. fallback: Try fallback paths if roots don't exist
  3. discover: Auto-search under search_roots using discover patterns

Discovered paths are saved back to config.json automatically.

Workflow

DISCOVER → VALIDATE → SCAN → INDEX → DEDUP → CACHE → SEARCH → MATCH → LOAD → EXECUTE

Quick Start

# Validate which agents are installed on your machine
python scripts/build_index.py --validate

# Auto-discover agent paths and update config
python scripts/build_index.py --discover

# Build the full index (scan all agent skill dirs)
python scripts/build_index.py --print

# Search for skills by keyword
python scripts/build_index.py --search "code review"

# Search within a specific agent
python scripts/build_index.py --search "patent" --tool claude-code

# List all skills from a specific agent
python scripts/build_index.py --list --tool cursor

# Show duplicate analysis (which skills exist across multiple agents)
python scripts/build_index.py --duplicates

Dedup Analysis

Quality Scoring (7 dimensions)

DimensionScoreDetail
description non-empty+10Has documentation
description > 50 chars+5Detailed
description > 100 chars+5Very detailed
keywords > 5+10Well-indexed
dir name = frontmatter name+10Properly named
TODO/WIP in description-5Unfinished
Tool priority bonus+15/+10/+5/+0P1/P2/P3/P4

When to call recommended version

  1. Prefer [推荐] version: highest quality score
  2. Call non-recommended only when: recommended version lacks a feature you need, or its agent isn't available in current environment
  3. Don't re-read: after reading recommended version, skip duplicates

Integration Criteria

Not every good skill should be copied. Only integrate when ALL conditions are met:

ConditionDetail
✅ Repeated useCalled ≥ 3 times in recent work
✅ Better than ownClearly superior to existing skills
✅ Self-containedNo dependency on source agent's proprietary commands
✅ ImprovableCan be improved based on usage experience

Task Matching

TriggerSearch scopeKeywords
Research/academicClaude Code > Hermes > CC Switchpaper/research/论文
Novel writingHermes > CC Switchnovel/editing/小说
EngineeringClaude Code > OpenClaw > .agentscode/debug/test
PatentCC Switch > Hermespatent/专利/交底
Data visualizationCC Switch > Claudematplotlib/figure/图表
Document processingClaude Code > OpenClawdocx/xlsx/pdf
Fund applicationHermes > Claude Codensfc/fund/基金
Unknown domainAll agentskeyword search first

Migration Guide

To a new machine

  1. Copy the agent-skills-bridge/ directory to the new machine
  2. Run python scripts/build_index.py --discover — auto-detects installed agents
  3. Check python scripts/build_index.py --validate — see which agents were found
  4. Build python scripts/build_index.py --print — generate the index
  5. Optional: manually edit config.json if an agent is installed in a non-standard location

Share with others

  1. Package the agent-skills-bridge/ directory (exclude skills_index.json — it's a machine-specific cache)
  2. The bundled config.json uses ${HOME} env vars — auto-adapts to any machine
  3. Recipient runs --discover to find their installed agents

Notes

  1. Index, not copy: the purpose is unified search + on-demand loading, not skill migration
  2. Read-only: never modify other agents' skill files
  3. Skills are documents: SKILL.md files are AI behavioral instructions, not executables
  4. Script safety: evaluate scripts/ in skills before running (read source, check for destructive ops)
  5. Encoding: some older SKILL.md files may use GBK encoding; the parser falls back to GBK/latin-1
  6. Graceful degradation: missing agent directories are skipped, don't affect others
  7. No hardcoded paths: all paths managed via config.json, code uses only env vars

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.