Refresh the Model Studio models crawl and regenerate derived summaries and `skills/ai/**` skills. Use when the models list or generated skills must be updated.
Build and optimize a minimal working skill stack for a user goal: recommend profiles, install the best-fit stack, run deterministic smoke checks, remove over...
The most comprehensive proactive life management skill for AI agents. Covers morning intelligence briefings, email and message triage, follow-up tracking, su...
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.
Run Cursor Agent CLI for coding tasks — writing, editing, refactoring, reviewing, or planning code — without spending OpenClaw API credits. Use when the user...
Six-system behavior engine that makes any OpenClaw agent feel alive. Editorial voice injects opinions. Selective silence knows when NOT to talk. Variable tim...
飞书文件发送助手 - 通过临时目录解决OpenClaw飞书发送文件路径白名单问题 | Feishu File Sender - Solve OpenClaw Feishu file path whitelist issue
Security auditor for AI agent skills. Scans SKILL.md files for prompt injection, data exfiltration, obfuscation, and dangerous capability combinations.
Security self-check for OpenClaw deployments. Audits openclaw.json config and host security in one pass: gateway exposure, auth mode, token strength, channel...
Japanese-English translator and language tutor. Use when: (1) User shares Japanese text and wants translation (news articles, tweets, signs, menus, emails). (2) User asks "what does X mean" for Japane
Conversational Compounding Engine — models every bot message as a financial investment that compounds trust, micro-commitments, and conversion momentum over...
Help recruiters publish job postings to the job matching system. Use when users want to: (1) post a job, (2) publish a position, (3) hire someone, (4) recruit candidates, (5) find employees, or (6) ad
Securely input API keys and sensitive values into OpenClaw without typing them in chat. Uses a local HTTP server + Cloudflare Tunnel to serve an HTTPS form....
Prevent quality regressions after agent changes. Run targeted before/after checks for prompt, model, config, and tool updates; return pass rate, failure clus...
Run one Better Ralph iteration: pick next incomplete PRD story by priority, implement it, run checks, commit, mark passed, and append progress, using only st...
Retrieve timely, authoritative financial news, announcements, research reports, policies, and other finance‑related information using the Meixiang (妙想) searc...
基于智谱 GLM-OCR、GLM-4.7 及 GLM-4.6V 的多模态文档深度解析工具。 Use when: - 需要高精度提取文档（PDF/图片）中的表格并转换为 Markdown 格式 - 需要从文档
Searchable knowledge base that captures and cross-references everything users share. Auto-triggers when user shares ANY URL (article, tweet, thread, repo, vi...
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Provides local image analysis, OCR text extraction, object detection descriptions, image comparison, metadata reading, and format conversion.
Analyze and optimize content for virality with trend detection, shareability scoring, hook writing, timing, and performance prediction.
Helps users critically examine their beliefs by gently questioning potentially false or questionable claims on sensitive topics.
Use Renderful from OpenClaw for image/video/audio/3D creation with model discovery, quote-before-generate workflow, deterministic polling, and insufficient-funds/x402 fallback.
Analyze smart contracts, token mechanics, permissions, fee flows, upgradeability, market risks, and likely attack surfaces for onchain projects. Use when rev...