发现 research llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from s...
Retrieves 10 similar historical cases from AgentDB vector store for RAG-based diagnosis support
Central Goal-Oriented Action Planning orchestrator that plans and executes clinical analysis pipelines
Synthesizes lesion data and historical cases into a comprehensive risk profile using WebLLM SmolLM2
Generates actionable clinical advice (max 25 words) calibrated for patient skin tone using WebLLM or Gemini
Bootstrap and initialize any app/module with custom CLAUDE.md, configs, environments, and workflows using Claude Flow wiki templates and examples
CloudBase Run backend development rules (Function mode/Container mode). Use this skill when deploying backend services that require long connections, multi-language support, custom environments, or AI agent dev...
reverse engineering the codebase to answer user's question. Use this skill whenever a user submits a question.
Guide implementation of production-ready Python RAG components by enforcing correct abstractions, error handling, observability, and safety at coding time.
Review an existing Python RAG codebase against an explicit RAG architecture document and produce a production-readiness backlog with priorities, rationale, and execution guidance.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends capabilities with specialized knowledge, workflows, or tool integr...
Find the right Claude Code docs fast (slash commands, hooks, plugins, agent skills, subagents, MCP). Use when you’re building or debugging Claude Code customizations and need the relevant API reference or guide...
{What the skill does AND when to use it. Be specific about capabilities and file patterns. Max 1024 chars.}
Load for new features, design tasks, and architecture decisions. Provides structured workflow for UNDERSTAND → RESEARCH → DESIGN → HANDOFF phases.
Load when editing .github/copilot-instructions*, skills/*, agents/*, instructions/*, or project_knowledge.json. Provides AKIS framework development patterns optimized for minimal tokens with full completeness.
Transform technical article drafts or source materials into human-like, high-quality Japanese technical articles. Use this skill when the user wants to generate, rewrite, or humanize technical articles (especia...
Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on phrases like 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes', 'clean...
Loads (copies) a skill from a local source directory into the current project's skill library (.claude/skills). Use this when the user wants to import or copy a skill from another location on the filesystem.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or too...
Synchronizes prompt files (agents, rules, commands) from the skill's prompts directory to both GitHub Copilot and OpenCode global configuration directories. Use when the user wants to update their AI editor pro...
Structured human-agent Q&A via HTML or TUI forms. Use when you need clear yes/no/refine decisions from the user on multiple items. Agent provides recommendations, human validates or overrides.
Episodic Memory Archiver. Stores full conversation transcripts with embeddings and analysis into ArangoDB. Use this to save the "User Story" or "Chain of Thought".
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...
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...
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。