GitHub
workflow-design
Design, discover, and refactor multi-command workflows for Claude Code
☆ 0查看技能
research llm ai AI 技能
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。
分类目录: research llm ai
research llm ai 清除筛选
全部技能
GitHub
pentarchy
Multi-disciplinary strategy council with 5 expert personas. Use for strategic analysis, impact assessment, complex decisions requiring diverse expertise. Includes cross-examination to identify contradictions be...
☆ 0查看技能
GitHub
forge
Lean code implementation pair. Claude (Smith) writes code, Gemini (Temper) reviews for bugs, security, and edge cases. ~2x token cost for high-quality code output.
☆ 0查看技能
GitHub
cartographer
Tree of Thoughts exploration for brainstorming and finding unknown unknowns. Recursively branches hypotheses, ranking by NOVELTY not probability. Use for idea generation, creative unblocking, exploring possibil...
☆ 0查看技能
GitHub
red-team-research
Adversarial research validation using Red Team/Blue Team methodology. Use when researching complex topics, fact-checking claims, or producing research reports. Validates outputs through Gemini 3 Pro critic befo...
☆ 0查看技能
GitHub
gemini-cli-model
Instructions for selecting and configuring Gemini 3 Pro Preview model in Gemini CLI. Use when the user asks about switching models in Gemini CLI, enabling Gemini 3, or configuring Gemini CLI model settings.
☆ 0查看技能
GitHub
triumvirate
3x3 Parallel Debate system for high-confidence research. Spawns 9 agent instances (3 Proposer/Skeptic/Judge cohorts) to argue, critique, and adjudicate claims. Use for complex queries, controversial topics, or...
☆ 0查看技能
GitHub
weaver
Map-Reduce system for comprehensive reports and literature reviews. Breaks topic into chapters, researches each in parallel, then weaves into unified document. Use for deep research, reports, and synthesis.
☆ 0查看技能
GitHub
foundry
Three-stage code implementation with planning. Gemini (Engineer) plans, Claude (Caster) implements, Gemini (Inspector) verifies. ~3x token cost for complex, multi-file changes.
☆ 0查看技能
GitHub
vanguard
Scout swarm for broad domain mapping and edge case discovery. Launches multiple high-temperature agents with distinct search vectors. Use for finding obscure data, edge cases, and mapping new territories.
☆ 0查看技能
GitHub
reflect
End-of-session consolidation for AI-ready vaults. Use before ending a work session to capture learnings, store important memories, and preserve context for future sessions. Counterpart to /hydrate.
☆ 0查看技能
GitHub
hydrate
Load context from an AI-ready vault at session start. Use when beginning a new conversation, starting work on a vault, or when context feels stale. Reads CLAUDE.md, checks recent session logs, loads relevant me...
☆ 0查看技能
GitHub
evaluate-vault
Analyze an Obsidian vault's AI-readiness with pass/fail checks. Use when assessing a new vault, auditing an existing vault, or verifying setup is complete. Returns a structured report with clear status indicato...
☆ 0查看技能
GitHub
glean
Surface emergent patterns and insights from the AI-ready vault memory system. Use periodically to discover connections between memories, identify recurring themes, and generate meta-insights that aren't obvious...
☆ 0查看技能
GitHub
recall
Search the AI-ready vault memory system by keyword or concept. Use when needing to retrieve previously stored information, find past decisions, or locate relevant context from earlier sessions.
☆ 0查看技能
GitHub
remember
Store a memory in the AI-ready vault memory system. Use when encountering information worth preserving across sessions—decisions made, patterns discovered, facts learned, or significant events. Creates properly...
☆ 0查看技能
GitHub
init-memory
Initialize the memory system in an AI-ready vault. Creates the folder structure, Memory.md dashboard, and example files needed for cross-session memory persistence. Use when setting up a new vault or adding mem...
☆ 0查看技能
GitHub
init-claude-md
Generate a CLAUDE.md file for an Obsidian vault. Analyzes existing vault structure and creates an instruction file that helps AI understand and navigate the vault. Use when setting up a new vault or when CLAUDE...
☆ 0查看技能
GitHub
session-start
Combined workflow for starting an AI collaboration session. Runs hydrate, vault-status, and prompts for session focus. Use at the beginning of any work session to load context and orient.
☆ 0查看技能
GitHub
session-end
Combined workflow for ending an AI collaboration session. Runs reflect to capture learnings, consolidates memories, and summarizes session work. Use before ending any work session to preserve context.
☆ 0查看技能
GitHub
writing-skills
This skill should be used when the user asks to "create a skill", "write a skill", "build a skill", "author a skill", "improve a skill description", "make my skill better", or needs guidance on skill structure,...
☆ 0查看技能
GitHub
content-personalization
Personalize textbook chapter content for logged-in users based on their background, preferences, and learning style collected during signup.
☆ 0查看技能
GitHub
user-profile-management
Manage user signup/signin and collect software/hardware background to enable personalized content in the Physical AI & Humanoid Robotics textbook.
☆ 0查看技能
GitHub
subagent-coordinator
Coordinate all subagents in the Physical AI & Humanoid Robotics textbook project. Assign tasks, validate outputs, and track progress to determine eligibility for extra points and reusable intelligence.
☆ 0查看技能
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。