Loading...
Loading...
Found 313 Skills
Use when running Ralph-style iterative autonomous development. Triggers on /ralph or /loop commands, when autonomous iterative development is needed, when a project has specs and an implementation plan ready for iterative execution, or when deterministic context loading with subagent delegation and dual-condition exit gates is required. Orchestrates PLANNING, BUILDING, and STATUS cycles.
Debugs errors and traces failures in AI agents and their tools. Use this skill when the user says: "the agent is failing", "tool call not working", "error in the pipeline", "debug this", "why is the agent doing X instead of Y", "trace the execution", "agent is stuck", "infinite loop", "model response won't parse", "context overflow". Identifies context errors, infinite loops, malformed tool calls, response parsing issues and subagent conflicts.
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested. Integrated into Cavekit: enabled by default for build, inspect, and subagent phases via caveman_mode config. See scripts/bp-config.sh for caveman_mode and caveman_phases.
Manage context-mode GitHub issues, PRs, releases, and marketing with parallel subagent army. Orchestrates 10-20 dynamic agents per task. Use when triaging issues, reviewing PRs, releasing versions, writing LinkedIn posts, announcing releases, fixing bugs, merging contributions, validating ENV vars, testing adapters, or syncing branches.
Use when the user wants Claude Code to generate images from prompts, use /gi or /gi-setup, configure an OpenAI Images API-compatible endpoint, create placeholder images, delegate generation to a background subagent named painter, pass model parameters, choose output paths, or maintain an image index. If generation is requested before setup, guide the user through /gi-setup instead of failing.
Lightweight workflow for straightforward changes — plan → implement → optional PR. Direct-commit by default; synthesize is opt-in via synthesisPolicy or a runtime request_synthesize event. Use for trivial fixes, config tweaks, single-file changes, or exploratory work that doesn't warrant subagent dispatch or two-stage review. Triggers: 'oneshot', 'quick fix', 'small change', or /oneshot.
Builds new project-specific skills or audits existing ones against the seven principles. Use when user says 'build a skill', 'create a skill', 'review this skill', 'audit our skills', 'is this skill good', 'what skills should we have', or 'clean up our skills directory'. Do NOT use for CLAUDE.md files (use create-or-audit-claude-md), subagents (use create-or-audit-agent), or hooks (use create-or-audit-hook).
Claude Code subagents for offensive security research, penetration testing planning, recon analysis, exploit research, detection engineering, and security reporting
Coordinate multi-perspective project, code, docs, design, or delivery reviews into focused recommendations. Use for multiple subagents, perspectives, named roles like UI/UX, DevOps, architecture, security, docs, or integrated feedback before changes.
Forensic audit of the user's recent Claude Code sessions to surface step-change workflow improvements — not marginal ones. Use when the user asks to "audit my Claude Code sessions", "analyze how I use Claude Code", "find patterns in my usage", "improve my Claude Code workflow", "review my sessions", "find leverage in my setup", or wants to understand where their Claude Code setup is leaking time. Samples dozens of real transcripts, extracts quantitative signal via scripts, uses parallel subagents for deep reads, then synthesizes into a short prioritized report with drafted implementations (new skills, CLAUDE.md rules, hooks, settings diffs) that the user can install directly. Trigger even when the user doesn't say the word "audit" — if they're asking about improving or reviewing their Claude Code habits at scale, use this skill.
Local mirror of OpenAI Codex product documentation (developers.openai.com/codex): CLI, Cloud, web app, IDE extension, hooks, skills, plugins, MCP, subagents, AGENTS.md, prompts, rules, sandboxing, models, pricing, security, and configuration. Use whenever the user asks how Codex behaves, how to install or configure Codex, or what a Codex flag, slash command, or feature does (including informal phrasing such as "hooks", "--resume", "sandbox modes", "cloud environments"). Read this skill's references/ before generic web search for Codex product questions. Do NOT use for Claude Code, Cursor, or other agents -- in particular, do not use for "Claude Code hooks" or general OpenAI API, ChatGPT, Realtime, or non-Codex coding help.
Use Browser Use cloud API to spin up cloud browsers for Clawdbot and run autonomous browser tasks. Primary use is creating browser sessions with profiles (persisted logins/cookies) that Clawdbot can control. Secondary use is running task subagents for fast autonomous browser automation. Docs at docs.browser-use.com and docs.cloud.browser-use.com.