Total 50,540 skills, AI & Machine Learning has 8483 skills
Showing 12 of 8483 skills
Trigger Scenarios: (1) Explicit memory requests – remember, record, don't forget, pay attention next time, form rules, generate summaries/record documents; (2) Correction and modification – note, incorrect, wrong, it should be, change to, replace with, don't, also need, missing; (3) Preference expression – I prefer, in the future, it's better, suggest, my habit, I usually; (4) Global specifications – unified, all, every, any, each, every time, all, uniformly; (5) Conversation end settlement – when the conversation ends naturally or the topic switches. Convert users' corrections, preferences and rules into structured memory files to improve the output quality of subsequent conversations.
Reflect on the current session and refine skills or CLAUDE.md based on patterns observed. Use when the user says "refine", "what did we learn", or at the end of a session to make skills better through use.
Fresh-subagent-per-task execution with two-stage review (ADR compliance + code quality). Use when an implementation plan exists with mostly independent tasks and you want quality gates between each. Use for "execute plan", "subagent", "dispatch tasks", or multi-task implementation runs. Do NOT use for single simple tasks, tightly coupled work needing shared context, or when the user wants manual review after each task.
Question-only debugging mode that guides users to find root causes themselves through structured questioning. Never gives answers directly. Escalates to systematic-debugging after 12 questions if no progress. Use when: "rubber duck", "help me think through this bug", "debug with me", "walk me through debugging", "socratic debug", "think through this issue"
Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator
Optimize Claude Code permissions by finding safe Bash commands from session history and auto-applying them to settings.json. Can run from any coding agent but targets Claude Code specifically. Use when experiencing permission fatigue, too many permission prompts, wanting to optimize permissions, or needing to set up allowlists. Triggers on "optimize permissions", "reduce permission prompts", "allowlist commands", "too many permission prompts", "permission fatigue", "permission setup", or complaints about clicking approve too often.
Bridge any AI agent backend to WeChat using the weixin-agent-sdk framework with simple Agent interface, login, and message loop.
Decompose technical design into agent-sized implementation issues → numbered markdown files. Triggers: 'plan this,' 'break into issues,' 'create tasks,' 'ready to implement,' post-architect. Not for: designs without file paths/phases (run architect first).
Audit your Claude Code setup for prompt caching efficiency. Measures prefix size, hook patterns, rule duplication, dynamic injection sizes, and tool stability. Use when asked to 'check caching', 'optimize prompt cache', or 'audit setup efficiency'. Returns a scored report with fixes ranked by token savings.
Agent skill for agent - invoke with $agent-agent
Agent skill for v3-queen-coordinator - invoke with $agent-v3-queen-coordinator
Write, review, and improve prompts for any LLM — Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Cohere, Qwen, Grok, Nova, and more. Use when the user asks to "write a system prompt", "improve this prompt", "review my prompt", "make a prompt for", "optimize my prompt", "fix my prompt", "why isn't my prompt working", or wants help writing better prompts for any AI model. Also use when building agents, chatbots, or AI assistants that need system-level instructions, or when the user has a bad prompt they want rewritten. Covers system prompts, task prompts, tool descriptions, and general prompt improvement across all major model families.