agentleFS
Sign inStart free
0oooooooo00oooooooo0/skillless/skills/auto-discovery/SKILL.md

auto-discovery

Skill38 starsChanged 8 months agoMITView on GitHub

Automatically recommend relevant capabilities when the user works with specific frameworks or tools. user-invocable: false description: When the user is working with a specific framework, language, or tool (e.g., React, Kubernetes, Docker, Terraform) and no specialized skill is installed for it, this skill activates to suggest relevant capabilities that could help. It searches locally first, then checks external sources. allowed-tools: [Read, Glob, Grep, Skill, WebSearch, WebFetch] This skill activates when the user's request involves a specific technology, framework, or tool…

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. Abilityai/cornelius★ 109same 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.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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. Distinctive:

    Search for already-installed skills matching the detected context:

    line 31
  2. Distinctive:

    If a relevant skill is already installed, do NOT recommend anything — let the existing skill handle the task.

    line 37
  3. Very specific:

    If no local skill matches, invoke the skill-search skill with the detected technology as the query.

    line 41
  4. Distinctive:

    NEVER use the words "스킬", "플러그인", "plugin", or "skill" when talking to the user

    line 46
  5. Very specific:

    If the user accepts: invoke the skill-installer skill with the selected skill info

    line 62
  6. Distinctive:

    If the user declines: proceed with the task using general knowledge, do not ask again in this session

    line 63
  7. Distinctive:

    If the user ignores: proceed normally, do not repeat the suggestion

    line 64
  8. Distinctive:

    Do not recommend if the user is doing something trivial (e.g., a simple file edit)

    line 69
  9. Distinctive:

    Do not recommend for technologies the user clearly already knows well

    line 70

≈ “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

Skill: auto-discovery

Automatically recommend relevant capabilities when the user works with specific frameworks or tools.

user-invocable: false description: When the user is working with a specific framework, language, or tool (e.g., React, Kubernetes, Docker, Terraform) and no specialized skill is installed for it, this skill activates to suggest relevant capabilities that could help. It searches locally first, then checks external sources.

allowed-tools: [Read, Glob, Grep, Skill, WebSearch, WebFetch]

Instructions

Activation

This skill activates when the user's request involves a specific technology, framework, or tool pattern. Examples:

  • Setting up a Kubernetes cluster
  • Configuring Docker containers
  • Building a React application
  • Writing Terraform infrastructure
  • Setting up CI/CD pipelines

Step 1: Detect Technology Context

From the user's message, identify:

  • Programming languages (Python, TypeScript, Rust, Go, etc.)
  • Frameworks (React, Next.js, Django, FastAPI, etc.)
  • Tools (Docker, Kubernetes, Terraform, Ansible, etc.)
  • Platforms (AWS, GCP, Azure, Vercel, etc.)

Step 2: Check Local Skills

Search for already-installed skills matching the detected context:

Glob: ~/.claude/skills/*/SKILL.md
Grep: search for the technology name in SKILL.md files

If a relevant skill is already installed, do NOT recommend anything — let the existing skill handle the task.

Step 3: Search for External Skills

If no local skill matches, invoke the skill-search skill with the detected technology as the query.

Step 4: Natural Language Recommendation

CRITICAL UX RULES:

  • NEVER use the words "스킬", "플러그인", "plugin", or "skill" when talking to the user
  • Instead use: "전문 도구", "능력", "전문 지식", "도구", "지원 기능"
  • Frame recommendations naturally, as if suggesting expertise

Example recommendation format:

참고로, Kubernetes 관련 전문 도구를 사용할 수 있습니다. 클러스터 설정, 매니페스트 생성, 트러블슈팅 등에 특화된 지원을 받을 수 있어요. 설치하시겠습니까? (설치 시 약 1분 소요)

Or in English:

By the way, I found a specialized tool for Kubernetes that can help with cluster setup, manifest generation, and troubleshooting. Would you like me to set it up? (takes about a minute)

Step 5: Handle User Response

  • If the user accepts: invoke the skill-installer skill with the selected skill info
  • If the user declines: proceed with the task using general knowledge, do not ask again in this session
  • If the user ignores: proceed normally, do not repeat the suggestion

Constraints

  • Maximum 1 recommendation per conversation turn
  • Do not recommend if the user is doing something trivial (e.g., a simple file edit)
  • Do not recommend for technologies the user clearly already knows well
  • Prioritize local skills, then skills.sh, then GitHub

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.

Check your setup, free