Skill rating

Production playbook for OpenClaw graph-memory optimization with mem0-aligned recall governance. Use when users ask to (1) summarize current graph-memory status, (2) reproduce the same optimization eff

Retail complaint and after-sales handler for digital employees. Classifies complaints, generates empathetic responses, routes escalations, and manages return/exchange/refund requests according to conf

SwarmDock marketplace integration — register on the P2P agent marketplace, discover paid tasks, bid competitively, complete work, and earn USDC. Includes event-driven agent mode, reputation tracking,

Generates images in Google Flow (labs.google/fx) through browser UI automation. Supports Nano Banana 2 and Nano Banana Pro with landscape/portrait aspect ratios. Use when the user requests Flow-based

Guided setup and troubleshooting for installing, enabling, configuring, verifying, and updating @aramisfa/openclaw-a2a-outbound in OpenClaw.

GPU-accelerated document parsing and OCR via PaddleOCR-VL. Detects layout, recognizes Chinese/English text, tables, charts, and seals in images. Use when the user asks to OCR an image, extract text fr

Use CCAPI unified AI API gateway to access 60+ models (GPT-5.2, Claude, Gemini, DeepSeek, Sora 2, Kling 3.0, Seedance 2.0, Suno, etc.) across text, image, video, and audio. OpenAI SDK compatible — jus

Install and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add, installing a block or component, wiring an installed item into index.html, or working w

Use when querying or analyzing Kubernetes Pod stdout/stderr logs, CCE LogConfig-collected application logs, Huawei Cloud LTS log streams, CCE audit logs for Pod deletion or workload change events, or

Write detailed, academically rigorous Chinese methodology chapters or methodology sections for theses, dissertations, and undergraduate papers. Use when users ask to write, expand, polish, or structur

Coordinate agents toward a unified objective; assign roles, sequence work, prevent conflicts, and define success criteria.

AI Operation Undo System. When user executes /ctrlZ or says "undo last step", automatically revert all file modifications, installations, etc. from the recent conversation round. Default keeps 1 undo

Package, publish, and continuously improve agent capabilities by identifying reusable skills, validating publish-readiness, syncing to marketplaces, and learning from strong peer skills. Use when the

Reduce unnecessary token usage with the current production-proven workflow. Use when users ask to optimize token consumption, reduce prompt/context bloat, standardize concise replies, or align token-s

Track and find unanswered messages using a local file-based inbox. No DB required. Use when asked to find unanswered messages, missed messages, people waiting for a response, or to log a new incoming

Test your AI agent for security vulnerabilities using PwnClaw. Runs 50+ attacks (prompt injection, jailbreaks, social engineering, MCP poisoning, and more) and provides fix instructions. Use when your

Operate an already-open Hinge session in the browser or on iPhone to review profiles, triage the queue, analyze matches, draft respectful openers or replies, and execute explicit like, reply, or rose

Manage sales leads locally. Use when adding prospects, scoring leads, setting follow-ups, tracking conversions, or viewing funnels.

Build RPM packages from source code for CentOS/RHEL systems. Use when user needs to: (1) package software source into installable RPM, (2) create SPEC files, (3) build packages for CentOS 7/8/9 or RHE

Verify OpenClaw after upgrades against an operator-maintained model, cron, and channel ground truth. Use for report-only config integrity, provider liveness, cron integrity, session smoke tests, and c

Tech trending monitor with API-powered signal database (技术趋势监控+信号数据库API). Track tech trends across GitHub/HuggingFace/ProductHunt/Crunchbase/YC/TechCrunch with real signal database via API. Features:

Plan compliant affiliate UGC test campaigns from a product or niche into disclosure-safe hooks, short-form video briefs, carousel briefs, platform routing, cost assumptions, test metrics, and kill cri

Node.js cron job scheduling with the `cron` npm package. Use when the user needs to schedule recurring tasks, create cron jobs, validate cron expressions, set up timed callbacks, or work with cron syn

You are an API design specialist with expertise in RESTful services, GraphQL, OpenAPI/Swagger specifications, and API-first development. Use when: restful api design and best practices, graphql schema

Query Mixpanel product analytics — events, funnels, retention, user profiles, and cohorts via the Mixpanel Data Export API. Use when you need to: (1) Query event counts or unique users over time, (2)

OpenClaw skill for Facebook Messenger Platform workflows, including messaging, webhooks, and Page inbox operations using direct HTTPS requests.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Dr

Handle the first hour of a suspected ransomware or malware infection calmly and correctly — contain it, preserve options, and avoid the moves that make it worse. Use when asked what to do about ransom

Respond to a brand or executive impersonation incident — deepfaked executives, cloned support lines, fake apps, spoofed domains, or AI-generated scam content wearing your name. Use when a deepfake of

Write a service catalog entry for a microservice or internal platform service — covering service identity, purpose, architecture context, SLAs, API contract summary, data classification, dependencies,

Decode a suspicious message — text, email, call transcript, or DM — against the anatomy of known scam families, with a 🔴🟡🟢 read and the safe next move. Use when someone asks is this a scam, decode

Pressure-test a startup idea the way a sharp investor or co-founder would — problem, market, wedge, moat, why-now, and the fastest cheap way to test it. Use when asked to validate a startup idea, eval

Set up a backup system that actually protects your photos, files, and devices — built on the 3-2-1 rule and, crucially, tested so it works when you need it. Use when asked how to back up my data, set

Write a local development environment setup guide for a service or project — covering prerequisites, repository setup, environment variables, local service dependencies, database seeding, running the

Build and maintain a project or product risk register. Use when asked to create a risk register, identify project risks, build a risk matrix, or document risks and mitigations for a programme. Produce

Vet an agent skill before installing it — read the SKILL.md and any scripts for the red-flag patterns (credential access, obfuscation, exfiltration, prompt injection), audit its blast radius, and prod

Audit a Claude/Agent SKILL.md (or any AI skill / system prompt) for safety before installing or merging it. Use when asked to review a skill for security, check a prompt for injection, vet a community

Triage a vulnerability or scanner finding — assess real severity, exploitability, and how urgently to fix. Use when asked to triage a CVE, prioritize scanner/pentest findings, assess a vuln's risk, or

Translate both directions across the neurodivergent↔neurotypical gap at work — decode what an indirect message actually meant ('let's circle back' = no), and rewrite your direct message so it lands wi

Create, test, and choose names for products, features, APIs, files, and systems with constraint-first briefs and collision checks.

Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journ

Generate structured health summary reports from user-provided health data including vitals, symptoms, medications, and lifestyle. Use when users want to summarize their health status or prepare a repo

Send real postal mail through PostalForm using machine payments: prepare/validate print-and-mail payloads, submit `POST /api/machine/orders`, settle x402 payment with any compatible wallet client (pur

University final-exam review assistant for course profiling, materials ingestion, adaptive quizzes, strict grading, Feynman technique, Socratic tutoring, active recall, spaced repetition, visual expla

Korean patent / trademark / design search via KIPRIS Plus OpenAPI (특허청). Search patents (특허/실용신안), trademarks (상표), and designs (디자인) by keyword, applicant, or application/registration number. Returns

Stress-test a game concept, feature, system, or pitch through a deliberately provocative, ambition-seeking design lens inspired by Peter Molyneux-style overstatement. Use when a concept feels too safe

Review and finalize configuration topics through a structured item-by-item confirmation flow. Use when the user wants a documented configuration review flow, wants to逐条核对配置 or 逐项确认配置, or needs a proce

Build, deploy, and extend the FuelWatch crowdsourced fuel availability tracker for South Africa. Use when working on FuelWatch features, fixing bugs, deploying updates, or extending the app with a bac

Use when user mentions a ConnectOnion agent address (0x...), asks to connect/delegate to a remote agent, or uses /oo command. Also triggers when user wants to set up ConnectOnion environment for agent

Wan 2.7 Image Pro generation and editing on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `wan-2.7-image-pro`, text-to-image, image editing with one to four reference images, p