Skill Claude CodeCodex
GitHub CLI (gh) comprehensive reference for repositories, issues, pull requests, Actions, projects, releases, gists, codespaces, organizations, extensions, and all GitHub operations from the command line.
Skill Claude CodeCodex
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive…
Skill Claude CodeCodex
Detects the running AI agent environment (Claude Code, Codex, Gemini CLI, Cursor, Windsurf, etc.), scans the codebase, and generates the appropriate context config file: CLAUDE.md, AGENTS.md, GEMINI.md, or .cursorrules. Also offers AGENTS.md as a cross-agent universal standard. Use when starting work in a new codebase…
Skill Claude CodeCodex
Bootstraps a new AI-assisted project through a structured 4-phase conversation, then generates PROJECT.md, JOURNAL.md, .gitignore, and tmp/README.md. Also searches skills.sh and installs relevant skills for the approved tech stack. Optionally initializes OpenSpec for spec-driven development workflows. Use when…
Skill Claude CodeCodex
Keeps PROJECT.md, JOURNAL.md, README.md, and AI context files (CLAUDE.md, AGENT.md, AGENTS.md) accurate and consistent with each other. Automatically reads recent git history and file changes to determine what's been completed and what's planned. JOURNAL.md is a lightweight checklist — [x] for done, [ ] for planned.…
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Agent Codex
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent Codex
Compare two outputs WITHOUT knowing which skill produced them.
Agent Codex
Evaluate expectations against an execution transcript and outputs.
Instructions file
Claude Code instructions for neithhogg/lair, covering claude.md, what this repo is, commands, architecture and skills (skills//skill.md).
Skill Claude CodeCodex
Detects and runs CI-equivalent commands locally before a git push: tests, lint, type-check, and build. Scans the project for available commands across any language stack, presents a confirmation menu, then runs each command in sequence and reports a clear pass/fail summary. Invoke explicitly with /pre-push — never…
Skill Claude CodeCodex
Guides a strict red-green-refactor TDD cycle for any language. Detects the project's test runner and conventions, writes the failing test first (red), then the minimal implementation (green), then offers a refactor pass. Never writes implementation code before a failing test exists and has been run. Invoke explicitly…