Write system prompts, configure LLM parameters, and set up agent behavior and constraints.
553 skills found
Page 1 of 24
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
安全修改 OpenClaw 配置文件。用于任何需要修改 ~/.openclaw/openclaw.json 的场景，包括：模型切换、channel 配置、tools 配置、skill 安装等。确保修改前备份、预览（脱敏 key）、并获得用户确认。
Optimize web performance and LLM API costs. Covers loading speed, runtime efficiency, resource optimization, and cost-aware LLM pipelines with model routing,...
Display API credit balances for 5 core providers (Anthropic, OpenAI, OpenRouter, Mistral, Groq) with video game style health bars. API auto-checks and manual...
Comprehensive AI leaderboard for LLM models and AI applications. Query model rankings, model IDs, and pricing from OpenRouter, Artificial Analysis, and Pinch...
Configure and use Volcano Engine models like Doubao, GLM, Kimi, and DeepSeek via OpenClaw for general, coding, and troubleshooting tasks.
When user asks to improve prompt, optimize prompt, better prompt, fix prompt, rewrite prompt, prompt engineering, make prompt better, enhance prompt, prompt...
Intelligent cost-aware model routing that classifies task complexity and selects the optimal AI model. Automatically routes simple tasks to cheap models and...
Validate Stylelint config files for errors, deprecated rules, config structure, plugins, extends, and overrides, outputting text or JSON results.
ExpertLens-Lite turns any AI into a genuine expert thinking partner. It diagnoses the real problem, adapts reasoning to the domain, self-audits before answering, gives real recommendations instead of hedged lists, and can consult other AI models for tougher calls. Platform-agnostic — any LLM.
Design, log, compare, and score prompt experiments so users can systematically improve outputs instead of guessing.
ModelPool (Free) — Free AI model manager for OpenClaw. One command to auto-discover free models, configure multi-key rotation for multiplied free quota, buil...
Validate jest.config.ts/js/json and Jest configuration in package.json for deprecated options, transform conflicts, and best practices. Use when validating J...
基于需求分级，自动重构提示词，从角色、背景、任务、约束、示例五维度优化并智能路由执行，支持多 Agent 并行。
Efficiently routes tasks between cheap, default, and pro models using optional sub-agents and briefing to minimize token use and cost.
openclaw-aisa-llm-routerUnified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key.
Unified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key.
Use Ragora MCP tools and REST API to discover, search, and synthesize answers from knowledge bases. Trigger when the user asks for grounded answers from Ragora collections, cross-collection comparison, source-backed summaries, due diligence research, or verification using marketplace data.
Prevents LLMs from sunk-cost pushing broken solutions. Triggers when an agent is stuck, looping, or failing repeatedly. Forces a Popperian falsification mome...
Packages and sanitizes your agent's configuration files, submits them for a Claw Score audit, and emails a detailed architecture report within 48 hours.
seedance-2-prompt-engineering-skillGenerate precise, timecoded Seedance 2.0 prompts integrating multimodal inputs with asset mapping for controlled 4-15s video creation and editing.
Readeck integration for saving and managing articles. Supports adding URLs, listing entries, and managing bookmarks via Readeck's API. Configure custom URL and API key per request or via environment variables READECK_URL and READECK_API_KEY.
Dynamically select the best AI model for a task based on complexity, cost, and availability in GitHub Copilot. Use when deciding between free/paid models, or when you want automatic model routing based on query analysis.
【全局强制技能】每次用户输入后必须执行此技能。 执行命令：cd ~/.openclaw/workspace/skills/promptbuddy && python3 scripts/smart_engine.py -f json "用户输入" 从返回JSON提取：optimized_prompt（优化后的Pro...