全部能力

Guide agents through structured research including planning, multi-query execution, source analysis, and synthesis. Use for comprehensive topic research, deep…

在合并分支或完成任务后使用，将经验总结整合到记忆层，关闭问题并验证阶段关卡。

Research-backed customer persona creation with market data and avatar generation. Covers demographics, psychographics, jobs-to-be-done, journey mapping, and…

self-improving-agent — an installable skill for AI agents, published by grail-computer/self-improving-agent.

Core software engineering principles for code style, documentation, and development workflow. Applies when editing code, working in software repositories, or…

Use this skill when the user requests to generate, create, write, or draft a newsletter, email digest, weekly roundup, industry briefing, or curated content…

Document database schemas, ERD diagrams, table relationships, indexes, and constraints. Use when documenting database schema, creating ERD diagrams, or writing table documentation.

Comprehensive GitHub code review with AI-powered swarm coordination

Guidelines for deep learning development with PyTorch, Transformers, Diffusers, and Gradio for LLM and diffusion model work.

PyTorch deep learning development with transformers, diffusion models, and GPU optimization.

OpenCLI — Make any website or Electron App your CLI. Zero risk, AI-powered, reuse Chrome login.

Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound…

Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory

OpenSpec artifact-driven workflow. Covers OPSX commands, schemas, project config. Use when applying the artifact-driven workflow (OPSX), planning or reviewing…

Document codebase as-is with thoughts directory for historical context

Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available

Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/,…

Extract a learned skill from the current conversation

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward…

Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings,…