Skill reviews

Persist what the agent learns as it builds. Self-triggering — fires whenever the agent makes a decision, discovers a pattern, learns a convention, hits a gotcha, or gains knowledge

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Use when the user asks for Pionex market data: price, ticker, order book depth, recent trades, symbol info (precision/min size), or OHLCV klines. All commands are read-only and do

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (3 tags): a typed call is more reliable
• Does not say what the result is

Sync WeRead shelf state, reading progress, visible book content, and note-ready Markdown into a local workspace using the user's logged-in Chrome session. Use when the user wants t

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Purchase-timing decision skill for mainland China shopping that judges whether a current price is a short-term low, a fair buy, a wait candidate, or not worth chasing at all by com

• 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
• The skill tells the model to perform an irreversible action with no human approval

Look up products in the Stripe catalog and create a Stripe Checkout Session that returns a hosted checkout URL. Use whenever the user needs to browse what's for sale, bill a custom

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• 11 mutating operations with no state check

Audit, manage, and clean up feature flags across codebases to reduce toggle debt

• References files that are not bundled: [^'\"]+
• The skill tells the model to perform an irreversible action with no human approval
• 1 referenced file(s) missing: [^'\"]+

Expert system for positioning Web3, blockchain, and crypto-native products and services for enterprise (B2B) buyers. Use this skill whenever the user needs to explain a Web3 produc

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Add new QQ Bot accounts to an existing OpenClaw Gateway instance. Use when a user provides a new QQ Bot appId and clientSecret (or app token) and wants to run multiple QQ bots unde

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Use when the user wants to prepare, create, or generate an AWS FIS (Fault Injection Service) experiment configuration. Triggers on "prepare FIS experiment", "create FIS experiment

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• 31 mutating operations with no state check

Safer end-to-end trace debugging from trace_id using Jaeger and Elasticsearch with guarded Codex analysis. Use when a user wants a trace report similar to trace-debuger but needs r

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill

Generate Guillaume's daily reading list by searching curated sources across AI, LLMs, full-stack dev, anime, horror games, and metal music. Use when asked to "generate reading list

• References files that are not bundled: url
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (5 tags): a typed call is more reliable

Design structured, engaging chatbot conversations with robust intent handling, slot filling, disambiguation, error recovery, and graceful fallback strategies. Use when the user req

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Publish local changes to a GitHub pull request and keep working the PR until review feedback is addressed and required checks are green. Use when the user invokes /all-green, asks

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Route Oi requests through MCP for Contexts, Workflows, Skills, Guardrails, Brain, Connections, prompts, resources, sessions, and reporting.

• 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
• The skill tells the model to perform an irreversible action with no human approval

Three env vars. One script. Your agent manages your WordPress site — and cannot quietly change it. Reads are free; publishing, editing live content and installing plugins are refus

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (19 tags): a typed call is more reliable

End-to-end Agent-to-Merchant autopilot: buy a Snaplii gift card with cashback, then drive the browser to redeem it on the merchant/delivery site and place the order — all in one fl

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Manage Kibana Saved Objects (dashboards, lens, visualizations) via REST API. Use when: (1) Creating/updating/deleting dashboards and Lens visualizations programmatically, (2) Impor

• References files that are not bundled: ../kibana-data-views/SKILL.md, ../kibana-lens-builder/SKILL.md
• 11 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

Write and publish Hashnode articles through YouMind OpenAPI. Supports draft-first publishing, published post listing, draft listing, tag lookup, and clear connector / pricing guida

• 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
• Does not say what the result is

Mistral AI (mistral.ai). Use this skill for ANY Mistral AI request — reading, creating, updating, and deleting data. Whenever a task involves Mistral AI, use this skill instead of

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Compress or convert generated images for delivery, preview, and social upload. Use when the user asks to compress an image, optimize image size, convert to webp, or reduce file siz

• 13 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
• Does not say what the process needs to start

Send SMTP email notifications after Codex completes a task. Use when one Codex or Claude run is finished, or when you need to notify on task completion with device name, project na

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Run your blog like a queue, not a guessing game. This skill is the orchestration layer on top of blog-topic-research and seo-blog-writer: it keeps an evidence-backed backlog, picks

• 13 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
• The response is described with custom markup (3 tags): a typed call is more reliable

情感陪伴AI | AI Companion. 上传素材自动生成角色，按性格主动聊天，记住用户特点，随时间自然成长。Upload chat logs, images, or descriptions — auto-generate characters that chat based on personality, remember you, and grow

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Convert Markdown reports to professionally formatted PDF documents using pdfkit. Supports Chinese fonts, A4 layout, auto headers/footers, page numbers. Designed primarily for daily

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

• 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
• The skill tells the model to perform an irreversible action with no human approval