Loading...
Loading...
Found 376 Skills
Use prefered practices when using git. Use when Codex needs to perform actions with git or Github.
[Hyper] Create, enter, list, remove, clean up, or repair Git worktrees for isolated branches and parallel agent sessions, including direct `git-worktree <ARGUMENT>` creation without follow-up questions. Use when the user asks for git worktree setup/removal, branch-per-folder workflows, parallel Codex/Claude/Cursor workspaces, or the repository-local `.hypercore/git-worktree/<folder_name>` convention; when creating and no argument/task is clear, ask what work will happen there in the user's language, derive the folder name, then move subsequent work into the new worktree.
Consult an advisory council of three AI personas — Cato (skeptic), Ada (optimist), Marcus (pragmatist) — backed by different frontier LLM agents (Gemini, Claude, Codex). Each persona runs as a separate agent process with full repo context and returns independent feedback. Use when the user says "/council", asks for a second opinion, wants feedback on code changes, needs a premortem, wants to pressure-test a decision, or asks "what do you think about this approach?" Claude may also proactively suggest consulting the council before major architectural decisions, risky deploys, or ambiguous trade-offs (but should ask for user approval first).
Universal environment variable loader for AI agent environments. Loads secrets and config from Claude.ai, Claude Code, OpenAI Codex, Jules, and standard .env files.
AI consultation CLI quick reference. Use when running consult commands to check syntax for general queries, protocol reviews, and stats across Gemini, Codex, and Claude.
Turn repeatable outputs of a one-person company into compounding assets. Use when Codex needs to explain asset-compounding concepts when needed, verify prerequisite outputs, ask one question at a time, present multiple assetization priorities, and write user-confirmed outputs into `opc-doc/`.
Use this skill whenever a user wants to run, install, configure, or understand open-ralph-wiggum (ralph). This skill can be used by any AI assistant or IDE agent (GitHub Copilot, Claude Code, Cursor, Windsurf, etc.). Triggers on: "ralph", "ralph wiggum", "agentic loop", "iterative AI loop", "autonomous coding loop", "how to install ralph", "how to use ralph with Claude Code / Codex / Copilot / OpenCode", "ralph --agent", "ralph --tasks", "ralph --status", "--max-iterations", "--rotation", "how do I run ralph in VS Code / Cursor / JetBrains / Neovim", or any question about looping an AI coding agent until a task is done. Even if the user doesn't say "ralph" explicitly — if they want to run an AI agent in a loop until a promise tag appears in its output, use this skill.
Multi-Harness Portability is the engineering discipline of writing agent skills, prompts, and configurations that work across every major AI coding harness — Claude Code, Cursor, Codex, Gemini CLI, OpenCode, and beyond.
Run structured multi-role design reviews and architecture debates for technical decisions. Use when Codex needs to compare options, pressure-test tradeoffs, recommend an MVP path, or simulate a meeting with distinct evaluation roles such as moderator, skeptic, pragmatist, minimalist, maximalist, retrieval architect, Granary workflow lead, semantic purist, lightweight contrarian, context economist, or workflow conservative.
Run the trigger evaluation pipeline — classify, analyze, and optionally compare against a baseline. Only run when explicitly asked — evals are expensive.
Analyze a task, pick the right fleet type, and generate a ready-to-launch fleet (fleet.json + prompt.md files). Discovers available fleet skills dynamically. Use when the user wants to run work in parallel, asks to "plan a fleet", or says "fleet-plan".
Reviewer-gated iterative fleet for headless `claude -p` or `codex exec` workers that run in cycles until a designated reviewer approves the output. Use when the work needs multiple rounds of iteration with a quality gate — a reviewer worker reads all worker logs, writes a verdict (lgtm | iterate | escalate), and the orchestrator decides whether to continue, pause, or stop. NEVER kills or restarts workers automatically; the operator owns all kill/pause decisions.