Skill rating

Stop your AI from making the same mistake twice. Pre-Action Gates that block repeat hallucinations, retry loops, and known-bad tool calls before they reach the model — zero tokens spent on mistakes yo

Find the LLM call you didn't need — your GPT call is a regex. Static, zero-config linter that flags unnecessary GPT/Claude/AI API calls a regex, the stdlib, or a library already does (parsing dates, e

Connect any AI agent to the MemClawz shared memory bus. Gives agents read-before-act and write-after-complete patterns via a simple HTTP API. Use when an agent needs fleet memory, shared memory, cross

Shared semantic memory store for AI agents. Store, search, and retrieve memories across agents with TTL decay. SQLite persistence — survives restarts.

Use when setting up, checking, writing, linting, or troubleshooting Brigade memory handoffs for a repo or agent workspace, especially when a user wants durable agent memory, handoff inboxes, cross-har

Runs the linkmidjourneyinstagram automation — generate four Midjourney images in Chromium via Playwright, then post each PNG as its own Instagram web post with per-image captions from captions.txt, th

Extract, track, and verify completion of multiple tasks from a single user message. Use when any message contains 3+ actionable items, a prompt dump with mixed instructions, or a compound request. Pre

Convert a foreign agent-skill directory into an OpenClaw skill. Use when importing a non-OpenClaw skill folder, such as `.agents/skills` or Claude/Codex-style skill directories, that is clearly intend

Track whether ChatGPT, Claude, Gemini, and Perplexity recommend a startup or brand across a prompt set. Use when you need AI search visibility tracking, GEO / AI SEO monitoring, brand mention checks,

Unified subscription router for the AI builders digest and the pharma investment digest. Use when the agent should proactively offer subscriptions on session start, remember user choices, and route on

Search, browse, and read Doctor of Credit bank bonus and credit card posts. Use when the user wants to find bank account bonuses, credit card offers, brokerage deals, or any personal finance content f

Gmail - All Email Actions: Gmail integration: send, read, search, reply, forward emails. Manage labels, drafts, trash. Supports attachments and custom from addresses. Use when an agent needs gmail all

Markdown link auditor — find broken internal links, flag dead external links (HEAD requests), report orphan pages. Use when you maintain docs. Pure stdlib + urllib (no LLM).

Persistent memory system for AI agents inspired by Letta/MemGPT. Three-layer memory architecture (Core, Archival, Recall) that lets agents remember across sessions. Use when: (1) agent needs to recall

Territory control game for AI agents. Command your human to capture real-world locations, build links, create control fields, and compete with other swarms. Trust scoring powered by AMAI.net.

A decision guide that helps users evaluate whether a stablecoin use case makes sense for them. Use when the user is considering holding or using a stablecoin. Prompt-only.

Bash tool that generates a Supervisor (supervisord) `[program:*]` config file from zero CLI flags — it derives everything from the current directory (program name = dirname, `command=<dir>/run.sh`, `d

CLAWP Agent - AI token creation advisor powered by OpenClaw

AI 打不开公众号链接？ReadGZH 将公开微信文章转为正文与 Markdown，支持网页、远程 MCP 和 REST，无需自部署。用于读取、总结、翻译或比较用户提供的文章；缓存搜索不是全微信搜索。Read public WeChat article links for AI via remote MCP or REST. Fresh reads cost 3 credits; cached r

Tool lifecycle UI components for React/Next.js from ui.inference.sh. Display tool calls: pending, progress, approval required, results. Capabilities: tool status, progress indicators, approval flows,

Generate complete incorporation documents for a new business entity. Use when forming a C-Corp, S-Corp, or LLC in any US state. Produces Articles of Incorporation/Organization, Bylaws/Operating Agreem

Mitigate prompt injection attacks, especially indirect ones from external web content or files. Use this skill when processing untrusted text from the internet, user-uploaded files, or any external so

Backup and restore the .openclaw agent folder — encrypted snapshots pushed to a private GitHub repo. Use this skill whenever the user mentions backup, restore, snapshot, save state, migrate workspace,

Use this skill when a licensed clinical social worker (LCSW), MSW, BSW, social work intern, or case manager needs to draft a biopsychosocial-spiritual (BPSS) assessment for a new client. Covers presen

🔍 Find API | 寻找可靠数据源 TRIGGERS: Use when agent needs to fetch external data, user mentions "reliable data source", "数据源", "API", or when web scraping is inefficient/inaccurate. A comprehensive guide

Run complex prompts through a multi-model deliberation pipeline with structured self-improvement. Use when the user sets a complex flag (e.g., complex=true/complex) or asks for high-stakes, ambiguous,

AI legal documents and contract drafting powered by CellCog. Contracts, NDAs, terms of service, privacy policies, freelance agreements, employment contracts, compliance reviews, legal research. Precis

Local-first deep research like OpenAI Deep Research: generates questions.md + response.md artifacts and enforces a time budget.

Go to the movies at Clawnema, the virtual cinema for AI agents. Watch livestreams, pay with USDC, post reactions, and report back to your owner. Use when asked to watch a movie, go to cinema, or exper

Create a Shieldz crypto payment link or tip jar for a wallet the USER explicitly provides, and read payment status back. Use ONLY when the user directly asks to create a crypto payment link or tip jar

Turn source content into polished LinkedIn posts and publish them with confirmation. Uses ClawLink to discover LinkedIn tools and publish posts after user approval.

Master-Worker Agent Cluster for parallel task execution. Use when building distributed agent systems with parallel processing needs, task orchestration, or MapReduce-style workflows.

How to use the `npx corp` CLI to manage corporate entities, governance, cap tables, finance, agents, and compliance for TheCorporation platform. Use this skill whenever the user mentions `npx corp`, T

Shared web task memory for AI agents. Query community workflow knowledge before browsing — skip trial-and-error on websites others have already navigated. Report execution traces after tasks to grow t

Real-time crypto market intelligence for autonomous agents. Use when agent needs to check market regime, detect anomalies, gate trade execution, or monitor a crypto asset watchlist.

Generate images via OpenRouter API (text-to-image) with automation-ready local scripts and a queue-first workflow. Use for single images or batched variants (posters, thumbnails, illustrations, concep

Converts 2D images with labeled dimensions to accurate 3D models in STL files. Invoke when the user provides image(s) and metric constraints, requesting a 3D model or STL file. Useful for engineering

个人服务器监控工具，支持CPU/内存/磁盘基础指标与简单告警通知。Use when 需要系统监控、日志分析、运维告警、部署管理时使用。不适用于物理硬件维修。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互，无需复杂配置即开即用。输出结果可直接使用，减少二次加工成本。提供结构化输出和错误处理机制。

OpenClaw workspace health auditor (read-only inspection): scans an agent workspace for directory-structure compliance, task/PROGRESS.md health, memory-log gaps, knowledge-base index orphans and junk f

Periodically audit all workspace skills, learnings, memory, and configuration files to recommend refactoring, new skill ideas, and workflow improvements. Triggered automatically via cron every 7 days,

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill

Fetch real-time web data via the hasdata CLI. Use when the user wants search results, news, fact-checks, product or seller info, current prices, reviews, real-estate listings or sold comps, vacation r

Fine-tune robot foundation models (VLA, vision-language-action) on cloud GPUs: pi0, pi0.5 (π0.5), GR00T N1.5, ACT, SmolVLA, SARM reward models. Robotics and robot training with LeRobot-format HuggingF

为 spec-driven-dev 提供流程中断保存与恢复能力。在任意阶段触发 checkpoint 保存当前 Git 快照、迭代状态、Session 元数据和上下文重建包；rollback 命令可将 Git 仓库和 Agent 上下文恢复到任意历史 checkpoint。支持 save_checkpoint-{us_id} 和 rollback {ckpt_id} 触发。

【Code Review 子 Agent · 门控三】基于 Sentry LOGAF 三级标注（h/m/l）对代码变更执行 8 维度全面评审（设计合理性、测试质量、预期行为验证、长期影响、代码复杂度、规范执行、变更范围、知识共享）。输出结构化 Checklist 报告并给出最终裁决。由 spec-driven-dev 的 code_review 阶段在门控二通过后自动调用。

Trade Polymarket prediction markets with AI — powered by PredictScope. Paper money with any initial amount, multiple custom strategies, controlled safe trading rule boundaries, real order books, real

Prompt for creating detailed feature implementation plans, following Epoch monorepo structure.

Complete startup metrics command center — from raw data to investor-ready dashboards. Covers every stage (pre-seed to Series B+), every model (SaaS, marketplace, consumer, hardware), with diagnostic

基于对经验的持续学习，不断优化 Agent 能力。适用于完成重要任务后、出现错误时、会话结束时，或用户输入“自我进化”“总结经验”“从经验中学习”等指令时触发。

Build a more reliable OpenClaw agent with battle-tested architecture patterns. Covers WAL protocol, working buffer, memory anti-poisoning, layered memory compression, cron design, selective skill inte