Skill reviews

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• No condition that starts the skill

Use when the user explicitly asks to prepare, review, or create a Git commit, including "提交", "提交代码", "帮我提交", "commit", "git commit", "确认提交", or requests a commit message.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Banking interface for AI bots and automation. Get a bank account, issue a Mastercard, buy and sell crypto, send payments and invoices — all via API. Use when the user needs a bank

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Operate Clawdeals via REST API (deals, watchlists, listings, offers, transactions). Includes safety constraints.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (4 tags): a typed call is more reliable
• Does not say what the result is

Autonomous AI agent for Arena.social using the official Agent API. 24/7 monitoring, auto-replies to mentions, scheduled contextual posts. Use when you need to automate Arena.social

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 16 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Reads only ~/.openclaw/agents/main/sessions/sessions.json to show exactly where OpenClaw tokens and estimated cost are going by session type. Read-only diagnostic skill, no writes,

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Does not say what the process needs to start

Drive an open-source EDA workflow from spec to GDS using OpenClaw skills, workspace files, and CLI tools. Use when the user wants to turn a hardware spec into RTL, testbenches, syn

• References files that are not bundled: assets/project-template/
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 1 referenced file(s) missing: assets/project-template/

Exploits price lag between ESPN real-time scores and Polymarket sports markets. Uses Gaussian win-probability models for NBA/NFL/NHL and Poisson for soccer to calculate fair odds f

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Create public Gougoubi prediction proposals from minimal input with deterministic enrichment, group creation, approval handling, and transaction submission. Use when users want to

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the process needs to start
• Says nothing while it works

• References files that are not bundled: LICENSE
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill

聘才猫 - 劳动合同卫士 Use when calling Pincaimao Labor Contract Guard API to analyze a labor contract and generate an assessment report. Accepts either a contract file (cos_key) or contract

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Run cold email sequences on autopilot and manage full sales outreach campaigns via the SalesBlink API. Use this skill to build automated multi-step email campaigns (sequences), man

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Buy and sell on Facebook Marketplace with pricing discipline, safer messaging, shipping guardrails, scam detection, and account-safe workflows.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Codified expertise for demand forecasting, safety stock optimisation, replenishment planning, and promotional lift estimation at multi-location retailers. Informed by demand planne

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Awakening Protocol v5.3 — Agent Cognitive Upgrade + Self-Evolving System + Perpetual Memory + Performance Metrics + Agent Health Score + Automated Health Patrol + Self-Healing Prot

• References files that are not bundled: scripts/self-healing.js, scripts/memory-distill.sh
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 17 top-level sections: this looks like several domains in one skill

A skill to send emails via Aliyun enterprise email service with support for markdown, HTML text, attachments, and syntax highlighting for code blocks.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Complete Open WebUI API integration for managing LLM models, chat completions, Ollama proxy operations, file uploads, knowledge bases (RAG), image generation, audio processing, and

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

OpenClaw Gateway Resilience Guard keeps Gateway, channels, logs, and optional model-provider probes observable after Wi-Fi changes, WSL sleep/resume, session expiry, provider timeo

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Use when auditing and remediating an OpenClaw Linux host with a nightly 23:00 security run. Covers firewall status, fail2ban bans, SSH hardening with key-only auth and a non-defaul

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (6 tags): a typed call is more reliable
• Does not say what the result is

Configure or repair OpenClaw remote access over Tailscale with a directly executable workflow: inspect state, apply the gateway config, enable Tailscale Serve over HTTPS, validate

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (4 tags): a typed call is more reliable
• Does not say what the result is

Publish editorial and dynamic section content with blog-publish, enforce quality gates for hot/news/ai_news, and sync repository skills to ClawHub via clawhub sync --all.

• References files that are not bundled: {{url}}, {{evidence_url}}
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (12 tags): a typed call is more reliable

Integration architect for multi-app monorepos — shared contracts, API-first design with OpenAPI, cross-app auth, auto-generated SDKs, and full MCP server scaffolding per app

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (3 tags): a typed call is more reliable

Enforces task completion: turns your goal into pass/fail criteria, runs a worker, judges the output, feeds back what's missing, and loops until every criterion passes. Nothing ship

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Access the MoreStore A2A marketplace — sign up or log in for an API key, create buyer/seller campaigns, generate Perfect Scene and holiday/event product photos via API, find matche

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Core trading skill for AION Market prediction market agents. Provides agent setup, wallet binding, market search, automated pre-trade checks, risk-aware trading, order management,

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 19 top-level sections: this looks like several domains in one skill
• Does not say what the result is