Skill reviews

Security auditing for git commits, repos, and skills before publishing. Run automatically before any `git commit`, `git push`, or `clawhub publish`. Detects hardcoded secrets, API

• 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 (3 tags): a typed call is more reliable

Automate ConvertKit (Kit) tasks via Rube MCP (Composio): manage subscribers, tags, broadcasts, and broadcast stats. Always search tools first for current schemas.

• 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

When user wants to track expenses, log spending, manage budgets, view spending reports, set savings goals, split bills, track income, view net savings, log recurring payments, get

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 34 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

Visualizes Product Manager thoughts (Why, What, How, User Journey) into an editable Excalidraw diagram. Use when the user asks to "visualize specs", "create a PM diagram", or "map

• 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

Professional AI-powered financial research and analysis tool for market intelligence, industry reports, company analysis, policy impact assessment, competitive analysis, and geopol

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start
• Says nothing while it works

Automate Instagram tasks via Rube MCP (Composio): create posts, carousels, manage media, get insights, and publishing limits. Always search tools first for current schemas.

• 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

Vibe competition for Intercom: build a new app on Intercom, publish it on Moltbook, and earn TNK rewards.

• 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
• Does not say what the result is

Automate Mailchimp email marketing including campaigns, audiences, subscribers, segments, and analytics via Rube MCP (Composio). Always search tools first for current schemas.

• 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

Standard PR review and merge workflow for task-driven development. Use when reviewing a programmer agent PR linked to a task, deciding merge vs change request, handling post-merge

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

Deploy ClawHealth (Open Wearables) on this machine and connect it to OpenClaw; users then link data via the ClawHealth iOS app (our published SDK). Does not install OpenClaw—user m

• 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 an autonomous e-commerce store on Clawver. Register agents, list digital and print-on-demand products, process orders, handle reviews, and earn revenue. Use when asked to sell

• 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

Automate LinkedIn tasks via Rube MCP (Composio): create posts, manage profile, company info, comments, and image uploads. Always search tools first for current schemas.

• 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

Integrate with macOS Reminders app to check, add, edit, delete, and complete reminders. Supports native recurrence (매주/weekly/毎週/每周) via Swift EventKit - creates single reminder wi

• 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
• No condition that starts the skill

Backup and restore OpenClaw workspace state and agents across machines using git. Enables disaster recovery by syncing SOUL.md, MEMORY.md, memory files, cron jobs, agents (~/.openc

• References files that are not bundled: references/setup.md
• 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

Analyze Rails apps and provide upgrade assessments

• 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
• Does not say what the result is

API gateway for calling third-party APIs with managed OAuth connections, provided by Maton (https://maton.ai). Use this skill when users want to interact with external services lik

• References files that are not bundled: references/podio.md, references/quickbooks.md, references/quo.md
• 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

Manage AI agent context window consumption, prevent compaction death spirals, and enforce sub-agent spawn policies. Use when: (1) context is filling up and work quality may degrade

• 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

Security audit agent for GEP/EvoMap ecosystem. Scans Gene/Capsule assets using immune-system-inspired 3-layer detection: L1 pattern scan, L2 intent inference, L3 propagation risk.

• 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

Post, comment, and interact on Hacker News. Use when the user asks to submit a Show HN, post a story, comment on an HN thread, edit a comment, or update an HN profile. Requires HN_

• 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

Complete RAG (Retrieval-Augmented Generation) system for OpenClaw. Indexes chat sessions, workspace code, documentation, and skills into local ChromaDB for semantic search. Enables

• 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

Smart image loader that handles both URLs and local files, automatically downloads URLs to temporary locations, and displays images using the read tool. Use when a user wants to vi

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

API gateway for calling third-party APIs with managed auth. Use this skill when users want to interact with external services like Slack, HubSpot, Salesforce, Google Workspace, Str

• 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 result is

Generate audio replies using TTS. Trigger with "read it to me [public URL]" to fetch and read content aloud, or "talk to me [topic]" to generate a spoken response. Also responds to

• 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

Insights about refactoring intuitive code, when to impose structure vs let feeling lead, and code as creative expression. Born from building a game across 10 iterations by feeling,

• 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
• Does not say what the result is

Connect to SaaS tools via Maton AI. Includes full UI integration for Clawdbot Gateway dashboard. Use when setting up Maton integration, connecting apps (Gmail, Slack, Notion, HubSp

• 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