Total 56,847 skills, AI & Machine Learning has 9448 skills
Showing 12 of 9448 skills
Execute Claude Code commands in the telegram_agent project directory. Use when the user wants to work on the telegram agent itself, fix bugs, add features, or modify the bot code. This is a COMMAND HANDLER, not a script executor.
Agent Workflow Designer
HNSW vector search with RuVector embeddings for 150x-12500x faster semantic retrieval
End-to-end hotel booking with USDC wallet payment. Use when the user wants the agent to search, book, and pay for a hotel in one autonomous flow — phrases like "book me a hotel in Tokyo and pay with USDC", "find a place in Paris and pay from my wallet", "handle the whole booking for next week". Orchestrates: search → select → authenticate wallet → fund if needed → pay via x402 → confirm. Do NOT use for search-only, payment-only, or non-hotel bookings.
Build production RAG systems with semantic chunking, incremental indexing, and filtered retrieval. Use when implementing document ingestion pipelines, vector search with Qdrant, or context-aware retrieval. Covers chunking strategies, change detection, payload indexing, and context expansion. NOT when doing simple similarity search without production requirements.
Use when a user has finished using one installed skill and wants to preserve actionable feedback about that skill while the session context is still fresh
Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI/CD quality gates, observability, or cost optimization. Triggers on: "evaluate my agent", "add evaluator", "measure quality", "quality gate", "run evals", "agent too slow", "why is it slow", "reduce latency", "set up observability", "CloudWatch dashboard", "how much does my agent cost", "cost optimization", "logs not showing up", "logs missing", "spans not found", "eval failing", "eval error", "dev traces", "local traces", "agentcore dev traces", "traces to CloudWatch". Not for debugging errors or crashes — use agents-debug. Slow but correct routes here; broken routes to debug.
MCP Server Builder
Use when the user wants AI-generated short-form video — knowledge cards (picstory / 小红书 / TikTok / Reels), narrated explainers, presentations, AI clips, or slides — covering picstory, present, slides, explain, and image generation. For PaperSlide / paper-textured article-to-card reels, use voxflow:paper-slide.
Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltration, (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply chain risks, (7) verifying file system access stays within skill boundaries. Triggers: "audit this skill", "is this skill safe", "scan skill for security", "check skill before install", "skill security check", "skill vulnerability scan".
Use this skill whenever the user wants to transcribe audio to text, convert speech to text, or get a transcript from an audio or video file. Triggers include: any mention of 'transcribe', 'transcription', 'speech to text', 'STT', 'convert audio to text', 'what does this audio say', 'get transcript', 'subtitle generation', or requests to extract spoken words from a file. Also use when the user wants speaker identification from audio, timestamps for captions, or multilingual transcription.
Run a session retrospective against the CLAUDE.md, skills, and hooks — identify guidance violations, stale rules, and gaps. Use when user says 'reflect on this session', 'what did we learn', 'post-mortem this work', 'what should we update in CLAUDE.md', or 'are our skills still right'. Do NOT use for code review (use /review-diff), PR prep (use /create-pr), or creating new skills from scratch (use /create-or-audit-skill).