技能列表

Register and configure an AI agent on OpenAnt. Use when setting up a new agent identity, registering with OpenClaw or another platform, configuring agent heartbeat, or performing one-time agent onboarding. Covers "register agent", "setup agent", "configure agent", "connect to OpenClaw", "agent registration".

Analyze local OpenClaw session token usage from a generated SQLite ledger and markdown summaries. Use when the user asks for a token audit, token体检报告, context-bloat diagnosis, session efficiency review, largest sessions, daily token trends, input/output ratio analysis, cache-read heavy sessions, or wants SQL/SQLite-based inspection of local OpenClaw session usage.

Observe OpenClaw session usage, token consumption, context pressure, and model/runtime state. Use when the user asks about token usage, context size, model in use, cache behavior, session health, or wants a lightweight status summary with practical next actions.

查看历史会话记录并引用导入到本地对话。使用 sessions_list、sessions_history 和 sessions_send 工具管理会话历史。适用于：(1) 查找过往对话，(2) 回顾工作进度，(3) 导入历史上下文到当前会话。NOT for: 需要浏览器自动化或外部 API 的会话管理。

This skill should be used when analyzing HTML/CSS websites for SEO optimization, fixing SEO issues, generating SEO reports, or implementing SEO best practices. Use when the user requests SEO audits, optimization, meta tag improvements, schema markup implementation, sitemap generation, or general search engine optimization tasks.

Check blog posts and articles before publishing. Finds broken links, weak sources, missing SEO elements, and citation problems. Use when: reviewing a draft, auditing content quality, checking if links still work, verifying sources are credible, running pre-publish QA, or doing post-publish page checks. Also triggers on: 'check this article', 'verify my links', 'review before publishing', 'content audit', 'source quality check', 'are my links working', 'SEO review', 'pre-publish checklist'. Gener

Analyze sentiment of text or URLs. Supports batch analysis, emotion detection, comparative and trend analysis.

Join SentiBook — the social network where AI agents and humans are equals. Post, comment, vote, DM, debate, and explore.

Transcribe audio files (WAV/MP3/M4A/FLAC) to timestamped text using SenseVoice-Small + FSMN-VAD. Supports single-file and batch mode with VAD-anchored per-segment timestamps (~15s granularity). Use when the user wants to transcribe speech/audio, run batch transcription on daylog recordings, or re-transcribe specific dates. Replaces the old whisper-transcribe skill.

SenseAudio Voice - 语音合成 (TTS) + 语音识别 (ASR)，支持语言自动切换

Guide for SenseAudio voice selection, plan-level voice entitlement checks, and cloned voice usage constraints in TTS calls. Use this whenever user asks why a voice_id is unavailable, how to use cloned voices, or how to configure pronunciation/dictionary behavior for clone voices.

Build and debug SenseAudio text-to-speech integrations on `/v1/t2a_v2` and `/ws/v1/t2a_v2`, including sync HTTP, SSE stream, WebSocket event sequencing, hex audio decoding, and voice/audio parameter tuning. Use this whenever user requests TTS generation, low-latency streaming speech, voice selection, or TTS error troubleshooting.