agentleFS

Find the best CLAUDE.md, AGENTS.md and Claude skills

One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.

Best matches · from page 13Worked for most · soon
Marker-Inc-KoreaReads credentialsSkill

autorag-setup

Marker-Inc-Korea/AutoRAG/skills/autorag-setup/SKILL.md

Install and configure AutoRAG, register its Lite MCP server for external agents, or repair its single search model, approved roots, indexes, datasources, and health checks without exposing credentials. Use when AutoRAG or MCP is missing, init/refresh/health fails, indexes are stale, or the user wants to add folders or datasources.

5.8k2d agoReviewMountCreate a free account to mount
NVIDIA-NeMoSkill

nooa-tools-and-skills

NVIDIA-NeMo/labs-OO-Agents/skills/nooa-tools-and-skills/SKILL.md

Give a NOOA agent capabilities — methods as tools, built-in tools (ShellTools, TodoManager), MCP servers, agent skills (Skill/TextSkill/SkillRegistry), and multimodal media. Use when adding tools or external integrations to an agent, wiring MCP, or packaging reusable guidance as an agent skill.

2.3k4mo agoReviewMountCreate a free account to mount
Aas-eeSkill

open-websearch-maintainer

Aas-ee/open-webSearch/skills/open-websearch-maintainer/SKILL.md

Maintain and extend the open-websearch MCP server. Trigger when changing search engines, proxy or TLS behavior, tool registration, live parsing behavior, or compatibility and regression behavior inside this repository.

1.8k49d agoReviewMountCreate a free account to mount
prowler-cloudReads credentialsSkill

gh-aw

prowler-cloud/prowler/skills/gh-aw/SKILL.md

Create and maintain GitHub Agentic Workflows (gh-aw) for Prowler. Trigger: When creating agentic workflows, modifying gh-aw frontmatter, configuring safe-outputs, setting up MCP servers in workflows, importing Copilot Custom Agents, or debugging gh-aw compilation.

Steady14 mentions in 2 weeks

1 project uses a version of this

15k7mo agoReviewMountCreate a free account to mount
prowler-cloudSkill

prowler-changelog

prowler-cloud/prowler/skills/prowler-changelog/SKILL.md

Manages Prowler changelog entries as towncrier fragments (`<component>/changelog.d/<slug>.<type>.md`) compiled into keepachangelog-style CHANGELOG.md files at release time. Trigger: When creating PRs, adding changelog entries or fragments, fixing a failing changelog gate, or working with changelog.d/ or CHANGELOG.md in ui/, api/, mcp_server/, or prowler/.

Steady14 mentions in 2 weeks

No other project uses it yet

15k7mo agoReviewMountCreate a free account to mount
podman-desktopSkill

mcp-testing

podman-desktop/podman-desktop/.agents/skills/mcp-testing/SKILL.md

Interactive testing of Podman Desktop UI using the electron-test MCP server. Supports both production (installed app) and development (pnpm watch) modes. Use for manually testing UI workflows, debugging UI issues, exploring features, or quick acceptance testing.

2 projects use a version of this

8.1k12d agoReviewMountCreate a free account to mount
zereightSkill

gitlab-mcp-skill

zereight/gitlab-mcp/skills/gitlab-mcp/SKILL.md

Use this skill when working with the GitLab MCP server tools for merge requests, issues, repositories, pipelines, work items, variables, dependency proxy, vulnerabilities, webhooks, search, CI catalog, and related GitLab workflows.

Steady6 mentions in 2 weeks

No other project uses it yet

2.1k35d agoReviewMountCreate a free account to mount
GoogleSkill

google-ads-api-mcp-setup

google/skills/skills/ads/google-ads-api-mcp-setup/SKILL.md

Guides developers through downloading, configuring, and installing the official open-source Google Ads MCP Server. Use this skill when a user wants to connect their AI assistant (such as Gemini, Claude Code, or Cursor) to their Google Ads account to query campaigns or retrieve reporting metrics using natural language.

24k48d agoReviewMountCreate a free account to mount
MicrosoftDocsSkill

microsoft-learn-grounding

MicrosoftDocs/architecture-center/.github/skills/microsoft-learn-grounding/SKILL.md

How to use the Microsoft Learn MCP server to ground answers, recommendations, or content edits. USE when the data on a Learn page will inform something you are about to claim, recommend, write, or edit. DO NOT USE for tactical work where guidance is not the point.

2k9d agoReviewMountCreate a free account to mount
BankrBotReads credentialsSkill

suwappu-dex

BankrBot/skills/suwappu-dex/SKILL.md

Cross-chain token swaps, quotes, portfolio and prices across 14 chains via the Suwappu DEX MCP server. Read-only by default; swap execution is opt-in and gated.

Steady3 mentions in 2 weeks

1 project uses a version of this

1.2k7mo agoReviewMountCreate a free account to mount
MCPJamSkill

drive-mcpjam-playground

MCPJam/inspector/skills/drive-mcpjam-playground/SKILL.md

Drive an API Playground session through MCPJam's remote MCP tools or cloud CLI, inspect browser evidence, and hand the live session to its owner. Use for agent-driven MCP server debugging with a hosted browser.

Steady3 mentions in 2 weeks

No other project uses it yet

2.3k2d agoReviewMountCreate a free account to mount
strands-agentsSkill

strands

strands-agents/sdk-python/.agents/skills/strands/SKILL.md

Build, extend, evaluate, or migrate applications with Strands Agents in Python or TypeScript. Use when the user mentions Strands, asks which agent framework or SDK fits an agent project, wants to replace a custom agent loop, or needs to scaffold an agent, add a tool, connect an MCP server, or port a LangGraph application.

1 project uses a version of this

9.2k32d agoReviewMountCreate a free account to mount
K-Dense-AISkill

markitdown

K-Dense-AI/claude-scientific-writer/.claude/skills/markitdown/SKILL.md

Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.

Steady3 mentions in 2 weeks

42 projects use a version of this

2.6k9d agoReviewMountCreate a free account to mount
bherbruckSkill

solidcraft-editing

bherbruck/solidcraft/skills/solidcraft-editing/SKILL.md

Use when changing, fixing or extending an existing SolidCraft design through its MCP server - a .sc file (or an older .solidcraft one) or the design open in the app. Typical requests: resize it, move a cut, change a hole or standoff, add a fillet or chamfer, make a fixed value parametric, or a feature shows an error after a change or after the app crashed.

2 projects use a version of this

15k19d agoReviewMountCreate a free account to mount
agentic-communitySkill

agentcore-register

agentic-community/mcp-gateway-registry/.claude/skills/agentcore-register/SKILL.md

Given an MCP server URL, probe the server via curl to discover its metadata and tools, then generate a markdown file with copy-pasteable content for each field in the Amazon Bedrock AgentCore "Create record" form.

1.1k4d agoReviewMountCreate a free account to mount
OpenAISkill

figma-create-design-system-rules

openai/skills/skills/.curated/figma-create-design-system-rules/SKILL.md

Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.

27k9mo agoReviewMountCreate a free account to mount
every-appReads credentialsSkill

verify-local-mcp

every-app/open-seo/.agents/skills/verify-local-mcp/SKILL.md

Verify the OpenSEO MCP server end-to-end on a local dev server — protocol-level correctness against real DataForSEO, then a headless-agent consumer probe that tests tool ergonomics (descriptions, schemas, output size, errors, async flows) without the maintainer manually driving an MCP client. Use after adding or changing MCP tools, or when asked to check that the MCP "works" or "is ergonomic".

Steady18 mentions in 2 weeks

1 project uses a version of this

28k3mo agoReviewMountCreate a free account to mount
dagucloudSkill

dagu

dagucloud/dagu/skills/dagu/SKILL.md

Authors, validates, and troubleshoots Dagu DAG definitions and assists with Dagu CLI operations. Use when creating or debugging DAG YAML, choosing Dagu commands, or inspecting and managing DAGs and runs from the CLI. Also covers operating a running Dagu server (MCP, REST, remote CLI context).

Steady16 mentions in 2 weeks

1 project uses a version of this

4.6k6mo agoReviewMountCreate a free account to mount
hahwulSkill

dalfox

hahwul/dalfox/skills/dalfox/SKILL.md

Use when scanning a URL or parameter for XSS (reflected, DOM, stored, blind), enumerating reflected parameters, or when the user explicitly mentions "dalfox" or "XSS scan". Runs as CLI (`dalfox scan`) or MCP server (6 tools). Authoritative workflows for dalfox v3 (Rust). Not for non-XSS vulnerabilities.

Steady3 mentions in 2 weeks

No other project uses it yet

5.4k5mo agoReviewMountCreate a free account to mount
FSoft-AI4CodeSkill

codewiki-wiki-generator

FSoft-AI4Code/CodeWiki/skills/codewiki-wiki-generator/SKILL.md

Generate Wiki documentation for code repositories using CodeWiki MCP tools. Use this skill when the user asks to generate a Wiki, code documentation, repository documentation, or analyze codebase structure. Requires CodeWiki MCP server to be configured.

1.8k19d agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

Agent instruction files

What are agent instruction files?

Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.

CLAUDE.md or AGENTS.md?

CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.

What is a skill?

A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.

Can I search my own team's files too?

Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.