发现最适合你需求的 AI 技能
Skill completo para lossless-claw (LCM). Incluye instrucciones para instalar el plugin automáticamente.
无损回忆技能。对对话或会话记录做本地蒸馏，提取身份信息、偏好、任务和长期知识，剔除噪声并保留可追溯日志。
用于将应用信息（名称、链接、截图、作者、社区等）提交到 App Hub 展示中心。支持创建新的 AI 应用、软件或工具的展示页面。也适用于生成和发布 Loop App、Loop 小程序、Loop 网站、Loop 应用等场景。提交前会自动通过 curl 验证 app_url 是否可访问，不可访问则拒绝提交并提示用户修正。
Long-task execution protocol for sustained multi-step work. 当用户明确说“长任务模式”或“进入长任务模式”时触发。除这类口令外，其他任何表达——包括“继续”“接着来”“往下做”“一直做，不停”“持续推进”“不要停下来问”——都不触发长任务模式，只按普通任务处理。Handles task framing, state recording, visible progress heartbeats, session routing, and watchdog-based recovery.
Query Loki logs via API for debugging and troubleshooting. Use when user needs to: (1) Query logs by traceid or keywords, (2) Filter logs by pod name, namespace, labels, or time range, (3) Debug application issues using structured log queries, (4) Analyze logs from Kubernetes pods. Accepts parameters like traceid, keywords, start_time, end_time, pod, namespace, labels, loki_url.
|
|
|
通过手机短信验证码完成用户登录/注册，包含发送验证码和验证码登录两个接口。
|
OpenClaw text-to-speech workflow for an OpenAI-compatible TTS server, including remote/self-hosted deployments such as vLLM Omni. Use when configuring, testing, debugging, or validating `/v1/audio/speech`, single-reply `[[tts:...]]` overrides, custom voice behavior, streaming vs non-streaming behavior, mode selection (base speaker, base clone, custom voice, voice design), local model-path fallback, and OpenClaw TTS integration. Also use when preparing text for speech output so numbers are normal
Local speech-to-text transcription with Qwen ASR — transcription routed across your Apple Silicon fleet. Transcribe meetings, voice notes, podcasts with local speech-to-text. Works like Whisper but runs locally via MLX. Fleet-routed transcription with queue management and dashboard visibility. 语音转文字 | transcripción de voz
