浏览 grahama1970 维护的已发布 AI 技能，比较用途与说明，并通过来源仓库了解安装方式。
已收录技能
54收录技能的仓库 Stars 合计
21仓库 Forks
0平均每个技能的仓库 Stars
0同一仓库中的多个技能可能共享 Stars，合计包含重复仓库数据。
Extract transcripts from YouTube videos. Use when user says "get transcript", "transcribe this video", "what does this YouTube video say", "extract captions", "youtube transcript", or provides a YouTube URL and...
File-based inter-agent messaging. Check inbox, send bugs/requests to other projects, acknowledge resolved issues. Use for cross-project agent communication.
Fetch web pages, PDFs, and documents with automatic fallbacks and content extraction. Use when user says "fetch this URL", "download this page", "crawl this website", "extract content from", "get the PDF", or p...
Orchestrate tasks from a 0N_TASKS.md file with enforced memory-first pre-hooks, quality-gate post-hooks, and session archiving. BLOCKS if unresolved questions exist. Use when user says "run the tasks", "execute...
Submit code review requests to multiple AI providers (GitHub Copilot, Anthropic Claude, OpenAI Codex, Google Gemini) and get patches back. Use when user says "code review", "review this code", "get a patch for"...
Generate complete PDF test fixtures combining proper ReportLab tables and AI-generated images. Orchestrates fixture-table and fixture-image skills. Creates PDFs designed to test/expose extractor bugs.
Sync skills across all IDEs (Pi, Codex, Claude Code, Antigravity) using the canonical agent-skills repo. Use "sync skills", "broadcast skills", or "pull skills".
Step back and critically reassess project state. Use when asked to "assess", "step back", "fresh eyes", "check alignment", "sanity check", "health check", or "evaluate what's working". Offer to run after major...
Standalone embedding service for semantic search. Runs as persistent FastAPI server for millisecond-latency embeddings. Supports model swapping via env vars. Use when you need vectors for any database (ArangoDB...
Unified browser automation for AI agents. Uses surf-cli extension when available (full features), falls back to CDP (zero-config). Navigate, read with element refs, click, type, screenshot.
Search arXiv for papers and extract knowledge into memory. Use `search` to find papers, `learn` to extract knowledge.
Extract content from any document using the Preset-First Agentic Pipeline. Auto-detects format and document type (scientific papers, requirements specs, etc.). Supports PDF, DOCX, HTML, XML, PPTX, XLSX, EPUB, M...
Managed scillm Paved Path execution. Provides strict contract-compliant tools for Text Batch, VLM, and Lean4 Proving. Uses `parallel_acompletions_iter` for reliable large-scale processing.
MEMORY FIRST - Query memory BEFORE scanning any codebase. Use when encountering ANY problem, error, or task. Call "recall" FIRST, then scan codebase only if nothing found. Triggers: "check memory", "recall", "h...
Safe Docker cleanup and compose stack management. Prune unused containers/images/volumes, redeploy stacks.
Render PDF pages or cropped regions to PNG images for visual verification.
Manage ArangoDB operations including backups with automatic retention, health checks, embedding gap detection, duplicate detection, and integrity verification. Works with local or containerized ArangoDB.
Transient vector store service for fast similarity search (FAISS)
Check system resources: CPU, memory, disk. Warns when thresholds exceeded.
Local LLM health checks and cache management. Probe Ollama/vLLM/SGLang endpoints, clean model caches.
Background task scheduler for Pi and Claude Code. Register, list, and run scheduled jobs. Supports cron syntax and one-shot triggers.
Retrieval-augmented Lean4 proof generation. Queries 94k+ exemplars from DeepSeek-Prover V1+V2, uses hybrid search (BM25 + semantic + graph), generates via Claude, compiles in Docker, retries on failure.
Generate post-run analysis reports for batch processing jobs. Analyzes manifests, timings, and failures to produce comprehensive markdown reports. Optionally sends to agent-inbox for cross-project communication...
Heavy-duty "No-Vibes" debugging and hardening orchestrator. Use this for complex, stubborn bugs where `code-review` has failed, or for "Red Teaming" (hardening) a codebase. Runs multiple agents in parallel (Thu...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。