awesome-skills-master
Skill1 starsChanged 49 days agoMITView on GitHub
Master catalog orchestrator and autonomous installer for AI agents. Use when exploring, cloning, discovering, or installing skills, plugins, or MCP servers from awesome-skills without using interactive CLI tools. Guides environment detection, rule adaptation (.mdc/CLAUDE.md), MCP configuration, and strict author attribution.
In this repository125 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skill-authoringSkill
- apple-notesSkill
- apple-remindersSkill
- findmySkill
- imessageSkill
- agy-customizationsSkill
- antigravity-guideSkill
- claude-codeSkill
- codexSkill
- computer-useSkill
- context-modeSkill
- dogfoodSkill
- hermes-agentSkill
- opencodeSkill
- rag-local-lancedbSkill
- skills-sh-registrySkill
- watermarks-removerSkill
- yuanbaoSkill
- libretranslate-markdown-i18nSkill
- mt-markup-preserving-translationSkill
- architecture-diagramSkill
- ascii-artSkill
- ascii-videoSkill
- baoyu-infographicSkill
- claude-designSkill
- comfyuiSkill
- design-mdSkill
- excalidrawSkill
- humanizerSkill
- manim-videoSkill
- p5jsSkill
- popular-web-designsSkill
- portfolio-github-pagesSkill
- pretextSkill
- sketchSkill
- songwriting-and-ai-musicSkill
- touchdesigner-mcpSkill
- jupyter-live-kernelSkill
- suap-iff-apiSkill
- desktop-themingSkill
- hermes-desktop-pluginsSkill
- docker-single-port-multi-instanceSkill
- hybrid-desktop-server-opsSkill
- himalayaSkill
- codebase-inspectionSkill
- git-conventional-commitsSkill
- github-authSkill
- github-code-reviewSkill
- github-issue-pr-attribsSkill
- github-issuesSkill
- github-profile-readmeSkill
- github-pr-workflowSkill
- github-repo-managementSkill
- github-starred-kbSkill
- hermes-installed-catalogSkill
- readme-templateSkill
- cv-latex-multilingualSkill
- latex-cv-maintenanceSkill
- gif-searchSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 5 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
When a user instructs an AI agent to:
- Very specific: line 96
When targeting Cursor, transform SKILL.md frontmatter into Cursor MDC syntax:
- Very specific: line 120
When the user asks for MCP servers from mcp/<server-name>/:
- Very specific: line 122
Read the server configuration from mcp/<server-name>/mcp.json.
- Distinctive: line 134
Every skill, plugin, and MCP definition in this repository must rigorously preserve author credits, license notices, and upstream …
- Very specific: line 137
Always preserve or specify author: <Original Creator / Upstream Contributor>.
- Very specific: line 138
Always preserve license: <License Name> (MIT, Apache-2.0, etc.).
- Distinctive: line 146
Never embed personal tokens, active keys, or private endpoints in any installed script or skill file.
- Distinctive: line 152
After performing autonomous installation:
- Very specific: line 153
Run ls -la <target_dir> to verify symlinks / copied directories.
- Distinctive: line 154
Ensure frontmatter is valid YAML without syntax errors.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
Awesome Skills Master Orchestrator & Autonomous Agent Guide
This Master Skill is the canonical instruction manual for AI agents (Google Antigravity, Claude Code, Hermes Agent, Cursor, Windsurf, Roo/Cline, OpenCode, Codex, GitHub Copilot) that clone or interact with the awesome-skills repository autonomously.
When a user instructs an AI agent to:
- "Instale as skills desse repositório"
- "Equipe meu ambiente com as ferramentas de devops e web"
- "Configure os servidores MCP e plugins necessários"
- "Adicione suporte a Cursor rules a partir deste catálogo"
The agent must follow this structured guide to discover, adapt, install, and attribute all catalog assets without needing user intervention or interactive TUI inputs.
🧭 Step-by-Step Autonomous Execution Workflow
┌────────────────────────────────────────────────────────────────────────────┐
│ 1. DETECT RUNTIME & ENVIRONMENT │
│ (Identify whether running in AGY, Claude Code, Hermes, Cursor, etc.) │
└─────────────────────────────────────┬──────────────────────────────────────┘
│
▼
┌────────────────────────────────────────────────────────────────────────────┐
│ 2. EXPLORE & MATCH CATALOG ASSETS │
│ (Search skills/, plugins/, mcp/ based on user goals or request) │
└─────────────────────────────────────┬──────────────────────────────────────┘
│
▼
┌────────────────────────────────────────────────────────────────────────────┐
│ 3. ADAPT & INSTALL TO TARGET DESTINATIONS │
│ - Skills: Symlink/Copy to agent skills path or generate .mdc rules │
│ - Plugins: Link to plugin hooks directory │
│ - MCP: Merge server JSON configurations │
└─────────────────────────────────────┬──────────────────────────────────────┘
│
▼
┌────────────────────────────────────────────────────────────────────────────┐
│ 4. PRESERVE ATTRIBUTION & LICENSING │
│ (Strictly retain original authors, upstream repos, and MIT/Apache terms) │
└─────────────────────────────────────┬──────────────────────────────────────┘
│
▼
┌────────────────────────────────────────────────────────────────────────────┐
│ 5. VERIFY & REPORT RESULTS │
│ (Test YAML frontmatter, verify symlink validity, report installed items) │
└────────────────────────────────────────────────────────────────────────────┘1. Runtime Detection & Installation Directory Matrix
Identify your current agent environment and select the appropriate target paths:
| AI Agent / Runtime | Global User Scope | Local Workspace Scope | Target Format |
| Google Antigravity (AGY) | ~/.gemini/antigravity-cli/skills/<name>/ | <workspace>/.agent/skills/<name>/ | SKILL.md (Native) |
| Hermes Agent (Nous) | ~/.hermes/skills/<category>/<name>/ | <workspace>/.hermes/skills/<name>/ | SKILL.md (Native) |
| Claude Code (Anthropic) | ~/.claude/skills/<name>/ | <workspace>/.claude/skills/<name>/ | SKILL.md / CLAUDE.md |
| Cursor IDE | ~/.cursor/rules/<name>.mdc | <workspace>/.cursor/rules/<name>.mdc | MDC Rule with frontmatter |
| Windsurf (Codeium) | ~/.codeium/windsurf/memories/ | <workspace>/.windsurf/skills/ | Markdown context |
| Roo Code / Cline | ~/.roo/skills/<name>/ | <workspace>/.roo/skills/<name>/ | SKILL.md (Native) |
| OpenCode / Codex | ~/.config/opencode/skills/<name>/ | <workspace>/.codex/rules/ | Markdown rules |
2. Autonomous Installation Operations
A. Installing Skills into Native SKILL.md Runtimes (AGY, Hermes, Claude, Roo)
# Example: Installing a skill to Google Antigravity
SKILL_SRC="skills/devops/hybrid-desktop-server-ops"
TARGET_DIR="$HOME/.gemini/antigravity-cli/skills/hybrid-desktop-server-ops"
mkdir -p "$(dirname "$TARGET_DIR")"
ln -sfn "$(realpath "$SKILL_SRC")" "$TARGET_DIR"B. Converting & Installing Skills into Cursor Rules (.mdc)
When targeting Cursor, transform SKILL.md frontmatter into Cursor MDC syntax:
# python snippet to generate .cursor/rules/<name>.mdc
import re, pathlib
def convert_to_mdc(skill_md_path, target_mdc_path):
text = pathlib.Path(skill_md_path).read_text(encoding="utf-8")
m = re.match(r"^---\n(.*?)\n---\n(.*)$", text, re.S)
desc = "Skill instructions"
body = text
if m:
for line in m.group(1).splitlines():
if line.startswith("description:"):
desc = line.split(":", 1)[1].strip().strip('"').strip("'")
body = m.group(2).strip()
mdc = f"---\ndescription: \"{desc}\"\nglobs: \"*\"\nalwaysApply: false\n---\n\n{body}\n"
pathlib.Path(target_mdc_path).parent.mkdir(parents=True, exist_ok=True)
pathlib.Path(target_mdc_path).write_text(mdc, encoding="utf-8")C. Configuring Model Context Protocol (MCP) Servers
When the user asks for MCP servers from mcp/<server-name>/:
- Read the server configuration from
mcp/<server-name>/mcp.json. - Merge the configuration into the target agent's MCP settings:
- Antigravity:
~/.gemini/antigravity-cli/mcp/<server-name>/ - Claude Desktop / Claude Code:
~/.config/Claude/claude_desktop_config.json - Cursor:
<workspace>/.cursor/mcp.json - Roo / Cline:
~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Antigravity:
3. ⚖️ Strict Author Attribution & Licensing Standards
CRITICAL MANDATE FOR AI AGENTS: Every skill, plugin, and MCP definition in this repository must rigorously preserve author credits, license notices, and upstream provenance.
- Frontmatter Integrity:
- Always preserve or specify
author: <Original Creator / Upstream Contributor>. - Always preserve
license: <License Name>(MIT, Apache-2.0, etc.).
- Always preserve or specify
- Upstream Repositories & Community Ecosystems:
- Skills originated from Anthropic / skills.sh must state
author: Anthropic / skills.sh Community. - Skills originated from Nous Research must state
author: Nous Research (Hermes Agent). - Skills originated from Matt Pocock / skills.sh must state
author: Matt Pocock. - Skills originated from Guillaume Meyer must state
author: Guillaume Meyer. - Skills originated from Open Source Repositories must state their respective creator, maintainer, or upstream project name.
- Skills originated from Anthropic / skills.sh must state
- No Secret Leaks & API Purity:
- Never embed personal tokens, active keys, or private endpoints in any installed script or skill file.
4. Verification Checklist
After performing autonomous installation:
- Run
ls -la <target_dir>to verify symlinks / copied directories. - Ensure frontmatter is valid YAML without syntax errors.
- Provide the user with a concise summary table of newly installed capabilities.
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
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.

