GitHub
agent-platforms
Guide for multi-platform skill compatibility across Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, and other AI coding agents.
☆ 2查看技能
testing security llm ai AI 技能
发现 testing security 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: testing security llm ai
testing security llm ai 清除筛选
全部技能
GitHub
llm-attacks-security
Guide for LLM security attacks: prompt injection, jailbreaking, data extraction, and where to place resources in README.md.
☆ 2查看技能
GitHub
llm-code-docs
Centralized AI-readable documentation repository with 245+ frameworks and tools. Use to find documentation, add new sources, or update existing docs. Located at ~/github/llm-code-docs.
☆ 2查看技能
GitHub
instruction-writer
Knowledge for writing effective Claude Code instructions. Auto-triggers for CLAUDE.md, SKILL.md, command files.
☆ 2查看技能
GitHub
startup
Review essential documentation and context at session start. Use when beginning a new session to load AI rules, git state, and pending tasks.
☆ 2查看技能
GitHub
historian
Invoke HISTORIAN for session documentation, historical records, and continuity. Creates human-readable narratives for non-technical stakeholders. Not invoked for routine work - only for poignant, significant se...
☆ 2查看技能
GitHub
context-aware-delegation
Understand agent context isolation and write effective prompts for spawned agents. Use when orchestrating multi-agent workflows to ensure subagents receive complete, self-contained context.
☆ 2查看技能
GitHub
bootstrapping-claudecode
Claude Code ベストプラクティスの対話形式セットアップウィザード。Use PROACTIVELY when setting up new projects, configuring Claude Code, adding agents/rules/hooks, or when user mentions "bootstrap", "setup claude...
☆ 2查看技能
GitHub
startupo
Initialize session as ORCHESTRATOR agent with multi-agent coordination capability. Use for complex tasks requiring parallel agent spawning and result synthesis.
☆ 2查看技能
GitHub
creating-commands
Create effective Claude Code custom commands for workflow automation. Use when creating new custom commands, understanding YAML frontmatter structure (description, allowed-tools, argument-hint, model, disable-m...
☆ 2查看技能
GitHub
agent-factory
Create new PAI agents using AGENT_FACTORY.md patterns. Guides through archetype selection (Researcher, Validator, Generator, Critic, Synthesizer), validates against CONSTITUTION.md, and generates agent specific...
☆ 2查看技能
GitHub
startupo
Initialize session as ORCHESTRATOR agent with multi-agent coordination capability. Use for complex tasks requiring parallel agent spawning and result synthesis.
☆ 2查看技能
GitHub
mcp-orchestration
Tool discovery, routing, chaining, error handling, and composition for the 34+ MCP scheduling tools. Use when orchestrating complex multi-tool workflows, handling MCP errors, or discovering available capabiliti...
☆ 2查看技能
GitHub
plan-party
Parallel strategy generation using G-5 Planning. Deploy 10 planning probes for multi-perspective implementation planning. Use for complex task planning after reconnaissance.
☆ 2查看技能
GitHub
greeting-generator
Generate friendly greetings in multiple languages with cultural context. Use when creating welcome messages, international greetings, or multilingual user interfaces.
☆ 2查看技能
GitHub
creating-subagents
Create effective Claude Code sub-agents for project-level workflows. Use PROACTIVELY when creating new sub-agents, improving existing agents, understanding YAML frontmatter structure (name, description, tools,...
☆ 2查看技能
GitHub
startupo-lite
RAG-first ORCHESTRATOR startup. Minimal context (~500 tokens), queries RAG on-demand. Token-efficient alternative to startupO.
☆ 2查看技能
GitHub
devcom
Invoke DEVCOM_RESEARCH for deep research, cross-disciplinary analysis, and novel problem solving. Use when exploring cutting-edge concepts or investigating patterns that require theoretical foundation.
☆ 2查看技能
GitHub
claudecode-headless-automating
Claude Code をヘッドレスモード（非対話モード）でスクリプトから呼び出すための実装ガイド。Use PROACTIVELY when creating automation scripts, shell scripts calling claude, headless mode, non-interactive mode, batch...
☆ 2查看技能
GitHub
claudecode-rules-organizing
Extract file-type specific rules from CLAUDE.md into .claude/rules/ with dynamic loading via paths. Use PROACTIVELY when CLAUDE.md has file-specific rules (API, frontend, testing) that can benefit from on-deman...
☆ 2查看技能
GitHub
context-party
Parallel historical context gathering using G-4 CONTEXT. Deploy 6 probes to gather all relevant context before complex work.
☆ 2查看技能
GitHub
spawn-agent
Spawn PAI agents via MCP factory tool. Loads identity, injects RAG context, validates spawn chain, and executes via Task(). The bridge between MCP tools and Claude Code's agent spawning.
☆ 2查看技能
GitHub
claudecode-skill-creating
Guide for creating effective Claude Code skills with proper YAML frontmatter, directory structure, templates, scripts, and best practices. Use PROACTIVELY when creating new skills, updating existing skills, lea...
☆ 2查看技能
GitHub
measure-ai-proficiency
Assess and improve repository AI coding proficiency and context engineering maturity. Use when users ask about: (1) AI readiness or AI maturity assessment, (2) context engineering quality or improvement, (3) CL...
☆ 2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。