OpenClaw AI 技能

fal.ai sync-lipsync v3 — given an input video and audio, generate a new video where the speaker's lip movement matches the audio. Good for dubbing, lo

Generate realistic digital human broadcast videos from portrait images and audio/text using Jimeng OmniHuman 1.5.

Audio generation skill. Automatically selects the best dlazy CLI audio/TTS model based on the prompt. 音频生成技能。根据提示词自动选择最佳的 dlazy CLI 音频/TTS 模型。

Skill Router — centralized index and intelligent router for all installed skills. Consult this FIRST before answering any question to determine which

When users search for information using Google AI Model, this skill is employed

Decision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus reason in natural language: classify eac

Screens biomedical / life-science papers for signs of data fabrication, image manipulation, and statistical anomalies, using the detection techniques

SOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format + human-in-loop REPL). Use when

Cross-framework enhancement overlay for choosing a multi-agent topology BEFORE writing any agent. A binary-question rubric — is single-agent + tools e

Task Decomposition & Skill Profiling Expert. Systematically breaks down vague, complex business requirements into highly executable work modules, skil

Analyze a Go/Weiqi position from an image or board state, use KataGo to recommend the next move at beginner, intermediate, or advanced playing strengt

SOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical processes, Flows, memory, delegation. Use when mo

Split a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions and a cheap model do the many

SOP for writing, loading, and evolving a project-level convention file (CONVENTIONS.md / CLAUDE.md / .cursor/rules / .clinerules / AGENTS.md) so that

Coder-agent working-file budget discipline: keep the editable working set (files you /add into writable context) under ~25k tokens, separate "read" fr

Enhances LLM chat by managing conversation history, caching responses, templating prompts, counting tokens, and tracking usage for efficient interacti

Manage Dropbox files securely with OAuth 2.0 PKCE via CLI or MCP server, supporting upload, download, search, delete, and account info operations.

Perform SysOM deep diagnosis on Alibaba Cloud PAI products (EAS / DLC) to identify root causes of instance-level issues. Use when users report: - EAS

When the user requests "call Google Scholar" or "academic search/paper search", or explicitly mentions the academic search field, the dataify-google-s

Manage and control local LLM services like Ollama and vLLM, including starting services, pulling models, and querying APIs via a unified interface.