Loading...
Loading...
Found 1,620 Skills
Compress documentation, prompts, and context into minimal tokens for AGENTS.md and CLAUDE.md. Achieves 80%+ token reduction while preserving agent accuracy.
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
Shell out to OpenAI Codex CLI for headless code generation, analysis, and question-answering. Optimized for code tasks. Requires OPENAI_API_KEY env var.
Build Model Context Protocol servers and implementations. Creates protocol-compliant tools and integrations for AI-powered applications.
A validation framework that ensures Claude's responses are current, accurate, complete, and clear. Use this skill whenever the user asks a factual or research question, requests analysis or recommendations (e.g., "What's the best framework for X?", "Compare options for Y"), or any prompt where recency and accuracy matter. Also trigger when the user explicitly asks for validated, verified, or fact-checked answers. This skill should activate broadly — if the answer depends on facts that could have changed in the last few months, use it. Even questions that seem straightforward ("Is X still the recommended approach?") benefit from this skill's validation pipeline. Do NOT trigger for purely creative writing, casual chat, or tasks that are entirely opinion-based with no factual claims.
Provides rules for handling multi-language documentation. Use this when configuring agent skill documents using starlight-skills on an i18n-enabled project. Do not use this for standard single-language sites or plugin configuration options.
LlamaIndex integration. Manage data, records, and automate workflows. Use when the user wants to interact with LlamaIndex data.
Evaluate the quality of CAW (Cobo Agentic Wallet) Agent in local Claude Code, and generate scoring data and analysis reports. Use when: Users want to run CAW evaluation, conduct evaluation, test Skill, assess Agent quality, generate evaluation reports, or say "run evaluation", "evaluate CAW", "eval", "score". For weak model / openclaw evaluation, please use caw-eval-openclaw (only installed on openclaw servers).
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.
Engineer system prompts for LiveKit voice agents with multilingual support. Use when creating or optimizing AI agent conversation flows.
Intelligent system governor that continuously shadow-tests APIs for performance while enforcing strict financial and security guardrails against runaway costs.
Use when bootstrapping a new personal wiki for any knowledge domain — research, codebase documentation, reading notes, competitive analysis, or any long-term knowledge accumulation project.