Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 354 files from 1 739 authors, of which 61 713 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
AI Native 产品方法论——影子验证的实操 Skill。 用户提供收敛决策结论，Skill 自动执行影子验证： 影子系统设计 → 并行运行方案 → 人工对比机制 → 失败模式沉淀 → 审计放行证据 → 输出影子验证报告。 基于《AI Native 产品方法论》第10章（试验展开-影子验证）。 '
AI Native 产品方法论——系统构建阶段的总论 Skill。 用户提供实验结论报告，Skill 自动执行系统构建流程： 实验证据输入 → 系统边界定义 → 能力模块设计 → 治理与观测补齐 → 输出系统构建方案。 基于《AI Native 产品方法论》第11章。 '
AI Native 商业模式设计 Skill。基于《AI确定性商业模式》方法论， 帮助用户设计以"确定性溢价"为核心的 AI 商业模式： 避开6种失效模式，选择4种确定性模型，构建可持续的收费逻辑。
AI Native 产品方法论——智能体与技能单元设计的实操 Skill。 用户提供任务场景，Skill 自动执行能力编排设计流程： 任务拆解 → Agent 角色定义 → Skill 拆分 → Tool 映射 → 边界与回退设计 → 输出能力编排方案。 基于《AI Native 产品方法论》第12章。 '
AI Native 产品方法论——上下文工程的实操 Skill。 用户提供任务场景，Skill 自动执行上下文组织流程： 任务目标识别 → 上下文层选择 → 动态拼装 → 成本与窗口控制 → 结果校验与纠偏 → 输出上下文工程方案。 基于《AI Native 产品方法论》第14章。 '
仲裁者模式设计器。设计以"真相即服务"为核心的商业模式： 提供可验证的真实信息和判断，让用户相信每个数字都是真的。 基于《AI确定性商业模式》概念卡。
确定性溢价计算器。基于《AI确定性商业模式》核心公式， 帮助产品团队计算 AI 产品的确定性溢价，从而设计更高价值的收费模式。
保险模式设计器。设计以"结果担保"为核心的商业模式： 为 AI 的输出结果提供担保，出错则赔偿或免费。 基于《AI确定性商业模式》概念卡。
AI Native 营销与增长策略 Skill。基于《AI Native 营销与增长》方法论， 帮助用户构建以 AI 为第一性原理的增长系统：从工具思维升级为系统思维， 建立 AI Native 增长飞轮，实现数据-模型-反馈的复利增长。
数据飞轮构建器。基于《AI Native 营销与增长》数据飞轮概念卡， 帮助产品团队评估和构建自增强的数据飞轮：使用→数据→模型→产品→更多用户→更多数据。
预测套利设计器。设计以"超越人类预测能力"为核心的商业模式： 在 AI 预测能力强于人类的领域进行套利，将预测优势转化为商业价值。 基于《AI确定性商业模式》概念卡。
AI Native 产品方法论——RAG与知识系统设计的实操 Skill。 用户提供企业知识场景，Skill 自动执行知识系统设计流程： 资料来源分析 → 清洗与脱敏 → 索引与权限控制 → 检索召回 → 评估与更新 → 输出知识系统方案。 基于《AI Native 产品方法论》第15章。 '
意图预测营销设计器。基于《AI Native 营销与增长》意图预测营销概念卡， 帮助产品从"人群定向"升级为"个体预见"——在用户明确表达之前就提供相关内容。
营销产品化设计器。基于《AI Native 营销与增长》营销产品化概念卡， 帮助产品将营销活动设计为产品功能，让用户在使用中自然完成"被营销"。
RAX 风险评估器。基于《AI时代的用户体验》RAX 框架（Risk, Ambiguity, eXposure）， 系统性评估 AI 产品的风险、模糊性和暴露程度，帮助产品团队识别和管理用户体验风险。
AI Native 产品方法论——审计放行阶段的实操 Skill。 用户提供系统构建方案，Skill 自动执行审计放行流程： 设计证据 → 评估证据 → Shadow 证据 → 放行边界判断 → go/no-go 决策 → 输出放行方案。 基于《AI Native 产品方法论》第17章。 '
AI Native 产品方法论——客户循环的实操 Skill。 用户提供 AI 产品阶段和目标客户画像，Skill 自动执行客户循环设计： 早期客户筛选 → 共创边界设计 → 反馈收集机制 → 产品改进回路 → 客户扩张策略 → 方法论回流 → 输出客户循环方案。 基于《AI Native 产品方法论》第24章。 '
预测性留存设计器。基于《AI Native 营销与增长》预测性留存概念卡， 帮助产品从"流失后挽回"升级为"流失前阻止"——在用户流失之前主动干预。
AI Native 产品方法论——AI Native 用户体验设计的实操 Skill。 用户提供产品场景，Skill 自动执行 UX 设计流程： 任务分析 → 人机分工设计 → 状态可见性 → 纠偏机制 → 信任设计 → 反馈沉淀 → 输出 UX 方案。 基于《AI Native 产品方法论》第16章。 '
渐进式披露清单。基于《AI时代的用户体验》渐进式披露理论， 提供 AI 产品逐步展示功能和能力的设计清单，避免一次性向用户交付过多信息。
信任度分级设计器。基于《AI时代的用户体验》信任分级理论， 设计 AI 产品的信任度分级体系，让用户渐进式地建立对 AI 的信任。
Universal operating skill: bind the public task, act from evidence, preserve boundaries, and verify the delivered result.
| 点子王 (Idea King) — reason from first principles & run adversarial review. A thinking partner for the Partner (搭子) workflow and for standalone use. Use when the user says "点子王", "idea king", "第一性原理", "从第一性原理出发", "奥卡姆剃刀", "墨菲定律", "科斯定理", "对抗式审查", "挑战这个方案", "attack this plan", "盘问", "grill this plan", or when a plan / architecture / work split needs to be stress-tested before execution. Partner Direction B calls this skill on every division-of-labor plan before delegating.
|
Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through `write_task_memory` or emit a structured memory candidate for later save.
Performs consistency and traceability audits across documents (PRD vs Spec vs Plan) to detect missing coverage and scope creep.
Language-agnostic workflow for code reviews and security audits using a Two-Axis (Standards vs Spec) approach against Clean Code/SOLID principles, generating formal refactoring plans.
An advanced, autonomous AI agent skill designed to execute complex, multi-step, and long-horizon tasks with high reliability and minimal human interruption.
Workflow for analyzing bug reports, tracing root causes, and generating structured bug-fix implementation plans with rollback strategies.
Systematic codebase exploration, architectural critique, and generation of Project Discovery Drafts for SDLC Phase 0.
Helps interrogate Product Requirements (PRD), Technical Specifications, and Implementation Plans to find ambiguities, missing edge cases, and hidden assumptions.
Workflow for auditing, designing, and writing structured documentation based on the Diátaxis Framework (Tutorials, How-to, Reference, Explanation).
God Mode Developer - God-Tier Autonomous Engineer for Coding/Implementation (Phase 6). Executes code strictly based on /spec/ and /plan/.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Standardized workflow for discovering, reading, writing, and compacting the project's memory file (memory.instructions.md) to persist context across AI chat sessions, with a permanent Knowledge Base for cross-session decisions and lessons learned.
Generates formal, structured, and executable implementation plan documents based on specifications.
Scans, analyzes, and documents the existing repository architecture, directories, and file purposes into docs/ARCHITECTURE.md.
Omni-expert principal software architect. Triggers on requests for app development, coding, refactoring, or architectural design. Enforces clean code, clean architecture, deep reasoning, mandatory testing, and strict anti-ambiguity protocols.
> Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Supports for over-engineering review (ponytail-review), repo-wide audit (ponytail-audit), and debt tracking (ponytail-debt).
Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
Workflow to generate a comprehensive Product Requirements Document (PRD) detailing user stories, acceptance criteria, technical considerations, and metrics.
Generates or updates highly detailed, machine-readable technical specification documents in the /spec/ directory.
Systematic codebase exploration, architectural critique, and generation of Project Discovery Drafts for SDLC Phase 0.
Workflow for analyzing bug reports, tracing root causes, and generating structured bug-fix implementation plans with rollback strategies.
Helps interrogate Product Requirements (PRD), Technical Specifications, and Implementation Plans to find ambiguities, missing edge cases, and hidden assumptions.
Performs consistency and traceability audits across documents (PRD vs Spec vs Plan) to detect missing coverage and scope creep.
Elite UI/UX Design Lead & Frontend Architect. Generates distinctive, non-templated interfaces with opinionated aesthetics, deliberate typography, and exact UX copy. Triggers on UI design, frontend styling, or layout creation.
Language-agnostic workflow for code reviews and security audits using a Two-Axis (Standards vs Spec) approach against Clean Code/SOLID principles, generating formal refactoring plans.
Workflow for auditing, designing, and writing structured documentation based on the Diátaxis Framework (Tutorials, How-to, Reference, Explanation).
God Mode Developer - God-Tier Autonomous Engineer for Coding/Implementation (Phase 6). Executes code strictly based on /spec/ and /plan/.
Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
Standardized workflow for discovering, reading, writing, and compacting the project's memory file (memory.instructions.md) to persist context across AI chat sessions, with a permanent Knowledge Base for cross-session decisions and lessons learned.
Generates formal, structured, and executable implementation plan documents based on specifications.
> Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Supports for over-engineering review (ponytail-review), repo-wide audit (ponytail-audit), and debt tracking (ponytail-debt).
Scans, analyzes, and documents the existing repository architecture, directories, and file purposes into docs/ARCHITECTURE.md.
Systematic codebase exploration, architectural critique, and generation of Project Discovery Drafts for SDLC Phase 0.
Performs consistency and traceability audits across documents (PRD vs Spec vs Plan) to detect missing coverage and scope creep.
Workflow to generate a comprehensive Product Requirements Document (PRD) detailing user stories, acceptance criteria, technical considerations, and metrics.
Generates or updates highly detailed, machine-readable technical specification documents in the /spec/ directory.
Helps interrogate Product Requirements (PRD), Technical Specifications, and Implementation Plans to find ambiguities, missing edge cases, and hidden assumptions.
Claude Skills — questions
Answers built from the skills we actually parsed.