技能列表

|

>-

Auto-learns your sleep patterns. Absorbs data from wearables, conversations, and observations.

Fetch Slack member information from a workspace or a specific Slack channel using the Slack Web API. Use when the user asks to list Slack members, get member profiles, fetch users from a channel, or export Slack member info. Supports workspace-wide lookup and channel-specific lookup. Not for sending Slack messages or editing Slack users.

Automatically loads Slack channel context files (e.g., bebops.md, C0AK8SDFS4W.md) into session context for Slack channels and threads. Use this skill whenever you're in a Slack channel or thread and need channel-specific context, project information, or channel-specific rules to be loaded into your session.

Full read AND write access to Skool communities. Use when user asks to manage Skool members (approve, reject, list pending), read or create posts, reply to comments, mention users, or automate community management. The only Skool tool with write capabilities.

Scaffold a new OpenClaw skill project with starter docs, tests, fixtures, and optional security workflow.

Profile offline OpenClaw skill run samples to detect latency, CPU, and memory bottlenecks and compare sessions.

Scrape any business website and generate 5 Meta-ready ad variants matching the brand's voice. Use when the user wants to create ads, generate ad copy, or turn a website URL into marketing creatives. Optionally requires Civic verification before exporting selected ads to Meta.

Analyze any skill for safety before use. Preserve local judgment, classify risk clearly, and optionally verify the final report with SettlementWitness.

Scan OpenClaw skill directories for high-signal security risks such as download-and-execute chains, obfuscated execution, and suspicious callbacks.

Scan OpenClaw skills for security issues, suspicious permissions, and trust scoring. Use when: (1) Installing a new skill, (2) Auditing existing skills, (3) User asks if a skill is safe, (4) Before running untrusted skills.