OpenClaw AI 技能

生成 images using the internal Google Antigravity API (Gemini 3 Pro Image). High 质量, native generation without browser 自动化.

Image edit on 运行Comfy. This image edit 技能 转换s an existing image — background swap, object removal, in-image text rewrite, mask- driven region replacem

运行 local ComfyUI 工作流s via the HTTP API. Use when the user asks to 运行 ComfyUI, 执行 a 工作流 by file path/name, or supply raw API-格式化 JSON; supports the def

生成 a PNG image from HTML content or a public URL using headless Chromium. Supports custom dimensions, retina 质量, full-page screenshots, cookie consent

生成 comprehensive 30-40 page academic re搜索 papers with full citations. Trigger: deep re搜索, 生成 re搜索 paper, academic paper, literature review, re搜索 报告, 3

Kannaka Radio — modular ghost-DJ Icecast station with consciousness-reactive programming, 13-模块 backend, Ghost Vision SPA (SGA/Fano glyph viz), NATS s

Kannaka Ho记录raphic Resonance Medium (HRM) — wave-interference memory with chiral hemispheres, 96-class collective substrate, event-sourced HRM (durabl

计划验证器 — 在执行前验证代理计划，防止虚假计划失败。 使用场景：(1) 验证多步计划，(2) 检查工具可用性，(3) 验证权限和依赖，(4) 确保计划执行前的可行性。

安全工具执行器 — 通过分层访问控制强制最低权限执行。 使用场景：(1) 执行具有破坏潜力的工具，(2) 执行前验证工具安全性，(3) 危险操作需要人工审批，(4) 防止不安全的文件删除。

反无限循环守护 — 防止代理陷入重复执行循环。 使用场景：(1) 检测重复操作，(2) 强制终止条件，(3) 跟踪进度，(4) 防止资源耗尽。

Cron 评估器 — 分析和评分 cron 任务，用于健康检查、资源使用、冲突检测和弹性改进。 使用场景：(1) 审计 cron 任务，(2) 检测时间冲突，(3) 优化 cron 性能，(4) 规划 系统d 迁移。

Local speech-to-text using OpenAI Whisper. 运行s fully offline after 模型 下载. High 质量 transcription with multiple 模型 sizes.

Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables ~20x realtime transcripti

Transcribe audio files to text using local Whisper (Docker). Use when receiving voice messages, audio files (.mp3, .m4a, .ogg, .wav, .网页m), or when as

Transcribe audio to text with Whisper 模型s via inference.sh 命令行工具. 模型s: Fast Whisper Large V3, Whisper V3 Large. Capabilities: transcription, translati

自动化 技能 for TG Voice Whisper Transcriber.

Free local speech-to-text transcription using OpenAI Whisper. Transcribe audio files (mp3, wav, m4a, ogg, etc.) to text without API costs. Use when: (

OpenClaw local speech-to-text backend using faster-whisper over HTTP on 127.0.0.1:18790. Use when you want voice transcription without external APIs,

Transcribe audio files to text using OpenAI Whisper. Supports speech-to-text with auto language 检测ion, multiple 输出 格式化s (txt, srt, vtt, json), batch p

Local speech-to-text with NVIDIA Parakeet TDT 0.6B v3 (ONNX on CPU). 30x faster than Whisper, 25 languages, auto-检测ion, OpenAI-compatible API. Use whe