Skill reviews

Deploy OpenClaw AI agent platform on Alibaba Cloud ECS and integrate with DingTalk bot. OpenClaw (formerly Clawdbot/Moltbot, 中文名"龙虾") is an open-source AI assistant and automation

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

Database migration manager. Detects ORM/migration tool in use, generates migrations, handles rollbacks, creates seed scripts, diffs schemas between environments, backs up databases

• 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

Automatically generate sprint release notes from a GitHub Project Board and publish to their respective repositories. Groups completed items by repository, generates per-repo markd

• 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
• Does not say what the result is

Access the Pokoclan forum API using the local auth token and HTTP helper scripts. Use when reading posts, checking health, inspecting users, or creating/updating forum content.

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

Publish videos and photo carousels to TikTok. Use when the user says 'post to TikTok', 'upload TikTok video', 'create TikTok post', 'publish TikTok carousel', or wants to upload vi

• 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

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 18 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

Adaptive tech quiz skill for OpenClaw. Asks one question at a time on any coding or CS topic: Python, JavaScript, SQL, system design, algorithms, networking, Git, Docker, APIs, and

• 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 a Printful account through the Printful REST API using a private API token. Use when the user wants to inspect or manage Printful stores, connected-store sync products, manu

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start
• 15 mutating operations with no state check

Gate spot trading and account operations skill. Use when the user asks to buy/sell crypto on spot, check account value, or place conditional/trigger orders. Triggers on 'buy coin',

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 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

This skill should be used when the user asks to "play a video in Kosmi", "queue a video", "DJ in Kosmi", "start the video DJ", "loop videos in Kosmi", "connect to Kosmi room", "pla

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (6 tags): a typed call is more reliable
• Does not say what the result is

• 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

Post-purchase order and after-sales management skill for mainland China shopping and delivery scenarios that records order state, arrival, return or exchange windows, price-protect

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

Guide users buying a water purifier through source water, household size, contaminant, and usage questions to determine the exact purification technology, flow rate, and certificat

• 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 process needs to start

Finix.js integration for accepting card and ACH bank payments on the web. Embed the hosted payment form, tokenize card/bank data in the browser, and claim tokens server-side to cre

• 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

Ensure all contacts and companies have appropriate lifecycle stages. Backfills missing stages via API, fixes records stuck at disallowed stages, and creates prevention workflows to

• 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

• 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

Git branch cleanup assistant. Audits all local and remote branches, categorizes them as safe-to-delete (merged), stale-unmerged (old + no open PR), or active. Detects branches that

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

Mandatory coding discipline rules that prevent common AI coding anti-patterns. MUST be loaded for ALL code writing, editing, reviewing, bug fixing, and testing tasks. Trigger on: w

• 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

• 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

Generate high-potential skill ideas for ClawHub by analyzing trends, identifying gaps, and suggesting profitable niches. Use when you need inspiration for new skills, want to disco

• 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

Working with .vaudtax files (Swiss canton Vaud tax declarations). Use when the user mentions a .vaudtax file, wants to read/summarize/convert a VD tax declaration, or inspect tax d

• 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

• 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

Korean tourism content (관광지·문화시설·축제공연·여행코스·레포츠·숙박·쇼핑·음식점) via 한국관광공사 TourAPI 4.0 (apis.data.go.kr/B551011/KorService2). Eight subcommands wrap areaCode2, categoryCode2, areaBasedLi

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• 4 mutating operations with no state check

Audit feature flag debt across LaunchDarkly, Unleash, Flagsmith, GrowthBook, Split, and home-grown flag systems. Detects stale flags (older than 90 days, fully rolled out, no toggl

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start
• 41 mutating operations with no state check

Telegram Bot (core.telegram.org). Use this skill for ANY Telegram Bot request — reading, creating, updating, and deleting data. Whenever a task involves Telegram Bot, use this skil

• 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