OpenClaw AI 技能

Polar (polar.sh). Use this skill for ANY Polar request — reading, creating, and updating data. Whenever a task involves Polar, use this skill instead

Ordinal (tryordinal.com). Use this skill for ANY Ordinal request — reading, creating, and updating data. Whenever a task involves Ordinal, use this sk

SheetDB (sheetdb.io). Use this skill for ANY SheetDB request — reading, creating, updating, and deleting data. Whenever a task involves SheetDB, use t

Roam HQ (ro.am). Use this skill for ANY Roam HQ request — reading, creating, and updating data. Whenever a task involves Roam HQ, use this skill inste

Validate, scaffold, and cross-check AI-agent capability manifests so agents stay swappable and safe. Zero dependencies (Python stdlib).

Multi-provider Text-to-Speech: Speechify API (primary) + Edge TTS (fallback).…

Scrape PTT web BBS (ptt.cc) without login to fetch boards, categories, articles, comments, push/boo counts, scores, search results, and essence area d

AI QA Agent — the final quality gate before delivery. Tests code for correctness, verifies data integrity, checks brand voice compliance, and reviews

AI Staff Agent — the production workhorse that handles boilerplate code generation, data cleaning pipelines, copy variant generation, and KM (Knowledg

Use this skill when the user wants to create, maintain, query, or visualize a local Markdown knowledge base. ThinkWiki can initialize a wiki, import f

Minimize pay-to-go xAI/API token spend. Use when user says token saver, save tokens, API budget, pay-to-go burn, or before long Grok/Claude/GPT calls.

Project management and multi-agent work coordination through AuraBaba. Use whenever a user asks to assign or delegate tasks (分配任务/派活), create or advan

Probe an agent's dependency endpoints (gateways/APIs/DBs) and report up/down + latency. Stdlib.

Lint prompts/SKILL.md for quality (role, goal, output format, vague verbs, jailbreak phrases). Stdlib.

Validate a ClawHub/OpenClaw skill folder before publishing (frontmatter, shape, size). Stdlib.

Estimate LLM token usage + cost from agent run logs (gpt/claude/gemini pricing). Stdlib, offline.

Run a self-improving autonomous company OS from a single CONSTITUTION + confidence-gated autonomy loop. Zero cash.

150 curated developer-productivity prompts you can paste into any agent (planning, debugging, code review, docs).

Upsales (upsales.com). Use this skill for ANY Upsales request — reading, creating, updating, and deleting data. Whenever a task involves Upsales, use

TalentLMS (talentlms.com). Use this skill for ANY TalentLMS request — reading, creating, updating, and deleting data. Whenever a task involves TalentL