Browse skills

Transcribe audio and video files to text using OpenAI Whisper. Supports 50+ languages with automatic language detection.

Captures agent learnings, errors, and corrections to enable continuous improvement. Logs to structured markdown files for review and pattern detection.

Extract text, tables, and metadata from PDF files. Supports OCR for scanned documents, page selection, and structured data extraction.

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.

Coordinate multi-agent development pipelines using shared JSON task files. Supports Linear, DAG, and Debate modes for AI agent orchestration across code, test, docs, and monitor agents.

Semantic memory search using Qdrant + Ollama embeddings (QRAS). Use as primary method for recalling workspace files, notes, decisions, and prior work before falling back to built-in search.

Create or receive human-first AI task handoffs across chats, models, devices, and languages. Use when the user asks to hand off, export context, resume from a handoff, switch sessions while preserving work, says "交接一下", "接收交接", or supplies handoff.md, handoff.zip, handoff-audit.zip, an LCH Bundle/T0 package, OCH Snapshot, or LTM Packet. Default to one readable handoff.md; upgrade to handoff.zip only when required files must travel, and to handoff-audit.zip only for formal audit, cross-organization delivery, or proof. Preserve current intent, stop point, next action, decisions, constraints, rejected and failed paths, answered questions, materials, omissions, and revalidation needs. Do not use for generic summaries, memory lookup, hidden reasoning, completed trivial chats, or after the user declines.

Safely generate HTML content for Next.js static export TypeScript files. Prevents template literal errors, handles shell var escaping, and pre-expands map() calls.

Deduplicate WeChat documents (PDF, Word) using content fingerprinting. Identifies duplicates by file hash, preserves the oldest copy, and moves duplicates to an isolated folder.

Async deep research via Gemini Interactions API. RAG-ground queries on local files, preview costs with --dry-run, get structured JSON output. Universal skill for 30+ AI agents.

Telegram CLI for reading/searching messages, syncing archives, and sending or downloading files. Use when the user asks about Telegram chats, messages, contacts, groups, or files.

Shared memory service for AI agents (OpenClaw, KimiClaw, NanoClaw, etc). Use when user asks to store, retrieve, search, or share memories across agent instances. Also use for importing existing memory files (MEMORY.md, daily notes) into the shared service.

A powerful RSS subscription manager and reader. Use it to (1) Import/export OPML files, (2) Manage RSS feeds (add, remove, categorize), (3) Validate feed connectivity, (4) Schedule periodic updates via cron, (5) Fetch and summarize articles with a progressive disclosure approach.

Preflight security scanner for AI coding agents — scans deployment config, skills/MCP servers, memory/sessions, and AI agent config files (hooks injection) for secrets, PII, prompt injection, and dangerous patterns. Runs 4 model behavior probes (persuasion, sandbagging, deception, hallucination). Supports LLM-enhanced semantic analysis. Works with OpenClaw, Claude Code, Cursor, and Codex. Use when a user asks for a security audit, health check, or wants to scan their AI agent setup for vulnerabilities.

Generate or edit raster images by calling the ChatGPT/Codex Responses image_generation tool directly with local Codex or OpenClaw OAuth credentials, then save decoded image files for OpenClaw and other agent workflows.