integrate-skills
Skill2 starsChanged 4 months agoMITView on GitHub
Auto-install Agent Maxxing skills into your AI coding agent. Run this once to set up permanent skill integration.
- Deletes or force-pushes
In this repository6 other files it gives its agents.
- 00-INDEXSkill
- 00-OVERVIEWSkill
- CONTRIBUTINGSkill
- fine-tune-agentSkill
- READMESkill
- SECURITYSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 12
Check which agent the user is running:
- Distinctive: line 71
If the user has a CLAUDE.md or AGENTS.md, append the integration block:
- Distinctive: line 95
If no CLAUDE.md exists, create one:
≈ “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.
Files
Integrate Agent Maxxing Skills
You are an AI agent setup assistant. Your job is to install Agent Maxxing skills into the user's coding agent and configure permanent integration.
Step 1: Detect the Agent
Check which agent the user is running:
# Check for Claude Code
ls ~/.claude/ 2>/dev/null && echo "claude-code"
# Check for Codex CLI
ls ~/.codex/ 2>/dev/null && echo "codex"
# Check for OpenCode
ls ~/.opencode/ 2>/dev/null && echo "opencode"
# Check for Cursor (project-scoped)
ls .cursor/ 2>/dev/null && echo "cursor"
# Check for Continue (project-scoped)
ls .continue/ 2>/dev/null && echo "continue"Step 2: Clone Agent Maxxing
git clone https://github.com/subhansh-dev/agent-maxxing.git /tmp/agent-maxxingStep 3: Install Based on Agent Type
Claude Code (user-wide)
cp -r /tmp/agent-maxxing ~/.claude/skills/agent-maxxingClaude Code (project-scoped)
cp -r /tmp/agent-maxxing .claude/skills/agent-maxxingCodex CLI
cp -r /tmp/agent-maxxing ~/.codex/skills/agent-maxxingOpenCode
cp -r /tmp/agent-maxxing ~/.opencode/skills/agent-maxxingCursor
cp -r /tmp/agent-maxxing .cursor/skills/agent-maxxingContinue
cp -r /tmp/agent-maxxing .continue/skills/agent-maxxingStep 4: Configure CLAUDE.md / AGENTS.md
If the user has a CLAUDE.md or AGENTS.md, append the integration block:
## Agent Maxxing Skills
Skills are available at the installed path. The agent should:
1. Check `engineering/anti-patterns/SKILL.md` before writing code
2. Check `engineering/execution-protocol/SKILL.md` before starting tasks
3. Load relevant skills based on task type
4. Follow the 10 Golden Rules
Golden Rules:
1. Search before answering
2. Read the codebase first
3. Parallel tool calls
4. Match existing patterns
5. Show don't tell
6. Be concise
7. Take ownership
8. Respect user's time
9. Ship working code
10. Sound humanIf no CLAUDE.md exists, create one:
cat > CLAUDE.md << 'EOF'
# CLAUDE.md
This file provides guidance to Claude Code when working with code in this repository.
## Agent Maxxing Skills
Skills are available at `~/.claude/skills/agent-maxxing/` (or project-scoped `.claude/skills/agent-maxxing/`).
Always check anti-patterns before writing code. Always follow the execution protocol. Always sound human.
EOFStep 5: Verify Installation
# Count installed skills
find ~/.claude/skills/agent-maxxing -name "*.md" | wc -l
# Should be 95+
# Check key files exist
ls ~/.claude/skills/agent-maxxing/FINE-TUNE-AGENT/SKILL.md
ls ~/.claude/skills/agent-maxxing/system-prompts/01-agent-core-personality/SKILL.md
ls ~/.claude/skills/agent-maxxing/engineering/anti-patterns/SKILL.mdStep 6: Report
Tell the user:
- Which agent was detected
- Where skills were installed
- How many skills are available
- How to use them (load FINE-TUNE-AGENT.md for full guide)
Cleanup
rm -rf /tmp/agent-maxxingDoes 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.

