GitHub
greeting-skill
Activates automatically when user greets warmly. Demonstrates the auto-trigger pattern—Claude detects friendly intent and engages accordingly.
☆ 0查看技能
tools llm ai AI 技能
发现 tools 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: tools llm ai
tools llm ai 清除筛选
全部技能
GitHub
omo
OmO multi-agent orchestration skill. This skill should be used when the user invokes /omo or needs multi-agent coordination for complex tasks. Triggers on /omo command. Loads Sisyphus as the primary orchestrato...
☆ 0查看技能
GitHub
ha-codex-skills
Codex 执行者技能包。Claude 通过 codeagent-wrapper 派发任务时，根据任务类型路由到子技能。
☆ 0查看技能
GitHub
workflow-or-agent-decider
Decide between a scripted workflow and an autonomous agent harness, then scaffold the chosen path. Use when scoping new agentic systems or tool integrations.
☆ 0查看技能
GitHub
long-running-harness-kit
Design long-running agent harnesses with resumable checkpoints and initializer/coder handoffs. Use when tasks span multiple sessions or require recovery after interruption.
☆ 0查看技能
GitHub
creating-mcp-code-mode-skills
A meta-skill for authoring high-performance, verifiable, long-running MCP skills using Code Mode. This skill blends Anthropic and OpenAI skill-authoring guidance with Code-Mode-first, MCP-backed execution, dyna...
☆ 0查看技能
GitHub
slicing-long-contexts
Use when a prompt or corpus is long/dense (multi-docs, logs, codebases) and you want a reproducible map/reduce pipeline. Trigger this skill to slice inputs, run per-slice codex/gemini subcalls, and aggregate re...
☆ 0查看技能
GitHub
creating-skills
General skill authoring and improvement. Use when creating or updating any skill (with or without MCP), selecting structure, generating scaffolds, or packaging resources (scripts/references/assets/templates) th...
☆ 0查看技能
GitHub
eval-harness-kit
Build and run deterministic evaluation suites for agent workflows (single-turn or agentic). Use when you need reproducible eval runs with manifests, graders, metrics, and JSONL logs for capability or regression...
☆ 0查看技能
GitHub
inspecting-the-environment
Fast environment briefing for agents and subagents. Use at session start to learn OS/shell, container/WSL/VM status, git repo + upstream + dirty state, Python venv status/locations, markdown folders to read, an...
☆ 0查看技能
GitHub
pincer-planning
Bidirectional planning for ambiguous or design-heavy tasks. Use when the user requests help breaking down a problem or formulating a plan, and also when an existing plan has too many gaps or needs refinement; c...
☆ 0查看技能
GitHub
tool-quality-audit
Audit tool integrations for deterministic behavior, error contracts, and logging before agents depend on them. Use when adding or updating tools or MCP servers.
☆ 0查看技能
GitHub
agent-workflow-playbook
Guide plan → instrument → execute → validate with explicit checkpoints and questions. Use for ambiguous tasks or when enforcing a consistent agent workflow.
☆ 0查看技能
GitHub
prompt-engineering
Generates optimized prompts for AI professional developers through interactive clarification. Asks targeted questions to refine requirements, saves tokens, and ensures reliable outputs. Use when seeking the bes...
☆ 0查看技能
GitHub
conda-env-setup
This skill should be used when the user asks to "setup conda environment", "configure Python environment", "activate conda automatically", "set conda environment for workspace", or mentions conda environment ac...
☆ 0查看技能
GitHub
implement
Generate clean C# code, Markdown files, agents, prompts, skills in MacroFlow.
☆ 0查看技能
GitHub
clarify
Refine user intent through questions and context gathering in MacroFlow.
☆ 0查看技能
GitHub
macroflow-network
Orchestrate MacroFlow as a flow network for dynamic AI orchestration.
☆ 0查看技能
GitHub
tools
Get information about available tools
☆ 0查看技能
GitHub
creating-agent-skills
Creates Agent Skills for Claude Code following official standards. Use when the user wants to create a Skill, teach Claude new capabilities, add specialized knowledge, or create reusable instructions. Keywords:...
☆ 0查看技能
GitHub
hemingwayesque
Ruthless concision for AI prompts and context - "Not One Word Wasted"
☆ 0查看技能
GitHub
workflow-design
Design, discover, and refactor multi-command workflows for Claude Code
☆ 0查看技能
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
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。