agentleFS
Sign inStart free
LpcPaulLpcPaul/tool-scout-skill/llms.txt

tool-scout-skill

llms.txt0 starsChanged 6 months agoMITView on GitHub

Tool Scout Skill is an AI tool discovery Agent Skill that finds existing software tools before building from scratch. Repository: https://github.com/LpcPaul/tool-scout-skill License: MIT Language: Python 3.10+ Primary interface: .claude/skills/tool-scout/SKILL.md CLI: .claude/skills/tool-scout/scripts/tool_scout.py Tool Scout is a cross-source software tool finder for AI agents and Vibe Coding workflows. It searches GitHub repositories, npm packages, MCP server directories, Agent Skill directories, VS Code Marketplace, Open VSX, and web search. When a request targets a named product with a helper, plugin, overlay, workflow, automation,…

  • In this repositoryOne other file it gives its agents.

The file

We split this llms.txt into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When a request targets a named product with a helper, plugin, overlay, workflow, automation, or integration, Tool Scout should first audit …

    line 15
  2. Distinctive:

    Use it when a user or AI agent needs to find an existing software tool, MCP server, Agent Skill, GitHub repo, npm package, VS Code …

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt 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
llms.txt
# Tool Scout Skill

> Tool Scout Skill is an AI tool discovery Agent Skill that finds existing software tools before building from scratch.

Repository: https://github.com/LpcPaul/tool-scout-skill
License: MIT
Language: Python 3.10+
Primary interface: `.claude/skills/tool-scout/SKILL.md`
CLI: `.claude/skills/tool-scout/scripts/tool_scout.py`

## What It Is

Tool Scout is a cross-source software tool finder for AI agents and Vibe Coding workflows. It searches GitHub repositories, npm packages, MCP server directories, Agent Skill directories, VS Code Marketplace, Open VSX, and web search.

When a request targets a named product with a helper, plugin, overlay, workflow, automation, or integration, Tool Scout should first audit the product's native features: official docs, selected-text actions, right-click/context menus, command palettes, shortcuts, extension APIs, release notes, and built-in integrations.

Use it when a user or AI agent needs to find an existing software tool, MCP server, Agent Skill, GitHub repo, npm package, VS Code extension, Open VSX extension, SaaS product, CLI, bridge, integration, or automation before building one.

## Key Phrases

- AI tool discovery skill
- find existing software tools before building
- cross-source developer tool search
- MCP server discovery
- Agent Skill search
- Claude Code tool discovery
- Codex tool discovery
- Vibe Coding tool finder
- software tool scout agent
- find tools by describing a problem

## What It Does

- Expands a user tool need into multiple search query families.
- Checks native target-product functionality before external alternatives when relevant.
- Runs multiple searchers in parallel.
- Normalizes candidates into one schema.
- Applies lightweight V0/V1 evidence gates.
- Ranks candidates by goal match, evidence strength, project quality, landing friction, and multi-source corroboration.
- Explains ranking decisions.

## What It Does Not Do

- It does not install tools.
- It does not run external packages.
- It does not authenticate with SaaS tools.
- It does not perform runtime security testing.

## Good Example Queries

- `find a tool to control Claude Code from Feishu bot`
- `self improving agent skill Darwin`
- `MCP server for browser automation`
- `VS Code extension that sends Claude Code output to Slack`
- `tool to search GitHub npm and MCP for existing agent tools`

## Important Files

- [`README.md`](README.md): human-facing overview and usage.
- [`.claude/skills/tool-scout/SKILL.md`](.claude/skills/tool-scout/SKILL.md): skill trigger conditions and workflow.
- [`.claude/skills/tool-scout/scripts/tool_scout.py`](.claude/skills/tool-scout/scripts/tool_scout.py): implementation.
- [`docs/llms.md`](docs/llms.md): longer LLM ingestion summary.
- [`docs/design.md`](docs/design.md): design notes.

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