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. 80 149 files from 1 774 authors, of which 62 489 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.
数学建模竞赛解题全流程指导。覆盖国赛(CUMCM)和美赛(MCM/ICM)全部题型(A-F)，提供12种问题本质分析、95+场景模型决策矩阵、5本算法Cookbook、11本完整例题Playbook、22个Python+7个MATLAB可运行代码模板。与math-modeling-paper形成"解题→写作"配对。当用户提及建模思路、选什么模型、怎么建模、赛题求解、粘贴赛题文本、美赛/国赛题目分析、CVaR/NSGA-II/Monte Carlo/时间序列/ANOVA/灰色关联、网络流/图论/生态建模、模型命名/Memo/Letter/Our Work流程图时，使用此skill。
Review ClawHub or local Skill packages before installation, classify risk, and return a structured security report.
审查、安装、配置、激活、验证、更新和回滚 AgentDock Skill 时使用；负责来源校验、安全评估、环境配置和已安装版本验收。
创建、设计、修改、升级、重构和验证 AgentDock Skill 时使用；负责可移植核心、文档、引用、辅助脚本、测试、版本和本地安装验证。
Use this to design a nice UI in single html as inspiration & UI exploration.
Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.
Architectural thinking partner for an existing repository — scans the codebase, conducts a structured interview, agrees on current architectural state and recommended direction, and produces a shareable insights document. Scoped to one repository, module, or folder. Does not execute transformation — it orients. Use when the user says 'assess my codebase architecture', 'what direction should my codebase go', 'architecture compass', 'understand my architecture', 'audit architecture drift', 'architectural assessment', or 'help me understand what is wrong with my codebase'.
Validate any Lattice SKILL.md against all tier conventions — atoms, molecules, and refiners. Catches structural errors, broken cross-references, and convention violations before they reach the repo. If you just wrote or modified a Lattice skill file and haven't run this yet, run it now — manual review consistently misses the same categories of errors this skill is specifically designed to catch. Use when the user says 'validate this skill', 'check this skill', 'does this follow conventions', 'review this skill file', 'check my SKILL.md', or 'skill validate'. Reports PASS/FAIL with specific file-and-section findings and actionable fixes. Standalone — does not call other skills.
Enforce architectural rules when generating or modifying code. Defaults to clean architecture; supports any architecture style via the architecture-refiner. Validates layer responsibilities, dependency direction, and structural constraints using the loaded architecture rules. Use when generating code, reviewing architecture, creating new files, or when the user mentions 'architecture', 'layers', 'structure', 'dependency rules', 'hexagonal architecture', 'ports and adapters', 'modular monolith', or 'onion architecture'. Also use when reviewing generated code for structural compliance.
Audit and fix all Lattice documentation, README, docs/, PROJECT.md, GitHub issue templates, and CLAUDE.md to ensure they are fully aligned with the current skill inventory. Documentation drift is the most common source of user confusion in Lattice — a skill exists in the codebase but not in the docs, or a renamed skill leaves a stale reference in the bug report template. If you've made any change to skills/ and haven't run this, run it now. Use when the user says 'align docs', 'audit docs', 'update documentation', 'skill align', 'check docs are in sync', 'audit skill inventory', 'ensure docs are aligned', 'are the docs up to date', or 'what needs updating'. Standalone — does not call other skills.
Facilitate a structured conversation to define architecture principles for a repository. Supports multiple architecture styles: clean architecture (default), hexagonal / ports & adapters, modular monolith, or custom. Produces a formal architecture document that the corresponding atom will use. Use when setting up a new project, defining architecture standards, or when the user says 'setup architecture', 'define layers', 'architecture principles', 'help me define my architecture', 'hexagonal architecture', 'modular monolith', 'ports and adapters', or 'define my architecture style'.
Create a new Lattice skill — atom, molecule, or refiner — following all framework conventions. Writing skill files manually almost always produces convention violations: wrong section order, missing confirmation gates, defaults.md without the right structure. This skill knows all of that and guides you through it. Use whenever adding any new atom, molecule, or refiner to Lattice, or when the user says 'create a new skill', 'add an atom', 'add a molecule', 'add a refiner', 'build X for Lattice', 'new lattice skill', or 'skill forge'. Does not validate, align docs, or deploy — those are separate skills you run after.
Audit any Lattice SKILL.md for language compliance — removes rationale prose, converts soft language to imperatives, adds STOP: gates on hard rules, and cuts redundant repetition. Complements skill-review (which finds behavioral gaps) by fixing phrasing that causes agents to skip or underweight instructions at runtime. Use after writing or significantly changing any skill, or when the user says 'tighten this skill', 'clean up the language', 'make this more effective', 'reduce the bloat', 'tighten the language', or 'skill tighten'. Standalone — does not call other skills.
Deep behavioral audit of a Lattice skill — proposes 3 review personas relevant to the skill, runs independent scenario analysis from each persona's perspective, then merges only the high-confidence, practical findings into a severity-ordered gap report with proposed fixes. Structural validation (conventions, cross-references) is skill-validate's job — this skill finds gaps that would realistically surface when someone actually uses the skill: missing scenario handling, ambiguous instructions, silent failure cases, and behavioral inconsistencies. Filters out theoretical edge cases, low-likelihood speculation, and findings owned by other skills. Use after writing or significantly changing any skill, or when the user says 'review this skill', 'deep review', 'does this skill work', 'find gaps in this skill', 'stress test this skill', 'review from different angles', or 'skill review'. Standalone — does not call other skills.
Run a complete design workflow -- from establishing context through 5 progressive design levels to an approved blueprint. Composes context anchoring, design-first methodology, architecture, and DDD into a unified process. Handles both new features (create context doc) and resuming existing work (load context doc). Use when starting a design, planning architecture, or when the user says 'design a feature', 'blueprint', 'start designing', 'plan the architecture', or 'let's design before coding'.
Apply clean code principles when generating or modifying implementation code. Enforces function focus, naming clarity, complexity management, error handling, and self-documenting style. Use during code generation, refactoring, or when the user mentions 'clean code', 'code quality', 'refactor this', 'simplify this', 'improve this', 'make this cleaner', 'clean this up', 'tidy this', 'coding guidelines', or 'implementation quality'. This skill governs the craft of writing individual code units -- not architecture (see architecture), not security posture (see secure-coding), and not test structure (see test-quality).
Protocol for handling ambiguous decisions and missing/conflicting knowledge during code generation, design, and review. Ensures AI surfaces genuine judgment calls with structured options and stops on hallucination risk instead of silently assuming. Use when a decision has multiple valid approaches, when facts are missing or contradictory, when the user asks 'what should we do here?', 'is this a judgment call?', 'should I ask about this?', 'am I guessing here?', 'what are the tradeoffs?', or when deciding between two reasonable architectural or design options. Also composed by molecules to define how judgment calls and clarification requests are surfaced and resolved.
Facilitate a structured conversation to define DDD guardrails for domain design within a repository. Produces a formal ddd-principles.md document that the domain-driven-design atom will use as its override. Use when setting up domain design principles, defining aggregate rules, or when the user says 'setup DDD', 'define domain rules', 'DDD principles', or 'help me define my domain patterns'.
Generate implementation code from an approved design blueprint or verbal requirements. Composes context anchoring, architecture, clean code, DDD, security, and test quality into an inside-out implementation workflow. Use when moving from design to code, implementing approved contracts, or when the user says 'implement', 'code this', 'build it', 'forge the code', or 'generate the code'.
Investigate, reproduce, and safely fix a bug with regression protection. Composes context, diagnosis, architecture, code quality, and testing guardrails into a reproduce-first repair workflow. Use when the user says 'fix this bug', 'debug this', 'investigate this failure', 'patch this regression', 'repair this issue', or 'why is this broken'.
Facilitate a structured conversation to define clean code principles for a repository. Produces a formal clean-code.md document that the clean-code atom will use as its override. Use when setting up coding standards, defining code quality rules, or when the user says 'setup clean code', 'define coding standards', 'code quality principles', 'coding guidelines', or 'help me define my code standards'.
Manage per-feature living documents that capture decisions, constraints, and reasoning across AI sessions during active development. Scoped to feature-level work — design, implementation, bugfix, refactor — not for codebase-wide assessments or product-wide specifications (those define their own document lifecycles). Handles creating new context documents, loading existing ones, and enriching them with new decisions. Use when starting a new feature, resuming work, making technical decisions, resolving questions, or when context needs to persist across sessions. Use this skill whenever the user mentions 'load context', 'update context', 'context doc', 'decisions', 'continue where we left off', 'what did we decide', or 'capture this decision'.
Guide structured design thinking through 5 progressive levels before any code is written. Levels: Capabilities, Components, Interactions, Contracts, Implementation. Use when building new features, refactoring significant code, designing modules, or when the user says 'design this', 'architect this', 'let's think before coding', 'walk me through the design', or 'whiteboard this'. For simple utilities or single-component tasks, enter at Level 4 (Contracts). Do not use for quick bug patches.
Apply DDD tactical patterns when working with domain code. Enforces aggregate design, value objects over primitives, entity identity rules, and bounded context boundaries. Use when creating or modifying domain models, designing aggregates, working in the domain layer, or when the user mentions 'domain', 'aggregate', 'value object', 'entity', 'bounded context', or 'DDD'.
Load project-specific context -- tech stack, architecture overview, directory layout, trusted sources, and conventions -- so that all skills operate with awareness of what this project actually is. Use when a knowledge base document exists, or when the user asks about the project's tech stack, architecture, conventions, framework, directory layout, or says 'tell me about this project', 'what are we using?', 'what's our stack?', or 'what framework is this?'. Use the knowledge-priming-refiner to create a knowledge base document.
Facilitate a structured conversation to create a project-specific knowledge base document. Produces a knowledge-base.md that primes AI with the project's tech stack, architecture, trusted sources, and project structure. Use when the user says 'set up knowledge base', 'prime the project', 'onboard AI', 'create knowledge base', 'set up project context', or 'configure AI context'.
Guided setup and upgrade-check experience for Lattice projects -- scans the repository, detects existing configuration and outdated conventions, suggests refiners and available upgrades in priority order, and creates or reconciles the .lattice/ config. Bridges the gap between installing skills and getting first value, and between upgrading Lattice and adopting its newest conventions. Use when the user says 'lattice init', 'set up lattice', 'initialize lattice', 'get started with lattice', 'configure lattice for this project', 'check for lattice upgrades', or 'upgrade lattice conventions'.
Facilitate a structured conversation to define language-specific idioms and patterns for a repository. Produces a language-idioms.md document consumed by multiple atoms to adapt pseudocode defaults to the project's language. Use when setting up a new project, switching languages, or when the user says 'setup language', 'define language idioms', 'configure language', 'language patterns', or 'adapt for Go/Rust/Python'.
Manage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns worth preserving, and keep the document tight over time. Provides a protocol for accumulating actionable patterns from practice that complement standards and defaults. Use when a workflow session completes and produced insights worth persisting, when starting a session that should benefit from prior patterns, or when the user says 'harvest learnings', 'what have we learned', 'capture this pattern', 'tighten learnings', 'compress learnings', or 'operational learnings'.
Restructure existing code safely without changing externally observable behavior. Composes context, design, architecture, code quality, and testing guardrails into a characterization-first refactoring workflow. Use when the user says 'refactor this', 'clean this up', 'untangle this module', 'move this to the right layer', 'simplify this code', or 'improve this structure'.
Update existing Lattice standards after a significant change — the update-mode counterpart to lattice-init. Scans .lattice/standards/, asks what changed, and routes each affected standard to its refiner's revise mode, recording a git-native change note. Use when the user says 'update refiners', 'refiners update', 'our standards changed', 'update our standards', 'the architecture changed, update the standards', 'we switched languages, update the standards', 'revise standards after a big change', or 're-run the refiners'.
Apply requirement quality principles when generating or validating feature specifications. Enforces feature completeness, scenario structure, AC verifiability, feature independence, and implementation slice quality. Use when writing feature specs, validating existing requirements, or when the user mentions 'validate this spec', 'check this feature', 'requirement quality', 'is this spec complete', or 'requirement-quality'. This skill governs the craft of writing individual feature specifications — not technical design (see design-blueprint), not implementation (see code-forge).
Generate structured feature specifications through a collaborative product interview. Acts as a senior PM and business analyst pair — arrives with a point of view, challenges scope, proposes options at every decision. Composes the requirement-quality atom for spec quality enforcement and collaborative-judgment for surfacing genuine decisions. Produces an epic/feature hierarchy in .lattice/requirements/ that serves as direct input to design-blueprint. Use when the user says 'forge requirements', 'write requirements', 'spec this feature', 'create a feature spec', 'define this epic', 'write a PRD', 'spec out what we are building', or 'requirement forge'.
Apply security-conscious thinking when generating or modifying code. Enforces trust boundary awareness, input validation, injection prevention, secrets management, and defense-in-depth authorization. Use when generating code that handles user input, authentication, authorization, database queries, external APIs, file operations, or when the user mentions 'security review', 'secure this', 'check for vulnerabilities', 'trust boundary', 'input validation', or 'OWASP'. This skill governs the security posture of generated code -- not architecture (see architecture) and not code craft (see clean-code).
Facilitate a structured conversation to define requirement standards for a project — epic and feature definitions, scenario structure, AC format, priority notation, status workflow, and naming conventions. Produces a formal requirement-standards.md that the requirement-quality atom reads via config resolution, customising its embedded defaults for the team's product process. Use when setting up a new project, defining product standards, or when the user says 'set up requirement standards', 'define feature standards', 'configure requirement forge', 'define how features should be structured', or 'requirement forge refiner'.
Perform a structured code review by composing validation checklists from relevant atoms based on what code changed. Loads atoms conditionally -- clean-code always, architecture/DDD/security/tests only when the delta touches their domain. Produces a severity-ordered report with specific locations and fixes. Use when the user asks to 'review this', 'code review', 'quality check', 'validate the code', 'check my code', 'review the delta', or 'review this PR'.
Facilitate a structured conversation to customize how the review molecule works -- atom loading rules, severity classification, report format, scope rules, insight capture, and health logging. Produces a formal review-standards.md document that the review molecule will use as its process configuration. Use when the user says 'customize review', 'configure review', 'review preferences', 'review settings', 'change review process', or 'set up review'.
Apply test quality principles when generating or reviewing test code. Enforces Arrange-Act-Assert structure, one behavior per test, assertion quality, test isolation, meaningful naming, and test data management. Use when writing tests, reviewing test code, or when the user mentions 'write tests', 'test this', 'test quality', 'test review', 'improve tests', or 'test structure'. This skill governs the craft of writing individual test cases -- not what to test (that is driven by the code being implemented) but how to write tests that are reliable, readable, and maintainable.
| Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
>- Remove the discourse-level (structural) signs of AI writing that survive surface embodied-emotion performance ("chest tightened"), vague allusions instead of named references, unbroken linear structure, and shape convergence across pieces. Grounded text at 93.2% F1, and professional stylistic rewriting moved detection only 1.6 points. Use as the SECOND pass after the humanizer skill (which handles words and phrasing) whenever writing or revising LinkedIn posts, course lessons, blog posts, "de-slop", "AI tells", "make this sound human", "structural pass", "deep humanize".
MiniQMT 迅投量化交易接口，基于 XtQuant Python 库，支持 A 股/期货/期权的行情数据获取（K线、分笔、财务数据等）和交易下单（报单、撤单、查询资产/委托/持仓）。当用户提及 miniqmt、xtquant、迅投、获取实时行情、量化交易下单、回测数据获取，或需要连接 MiniQMT 客户端进行程序化交易时使用
Backtrader 开源量化回测框架，支持多数据源、多策略、多周期回测与实盘交易，纯Python实现。当用户需要开发量化策略、进行回测分析、编写交易逻辑、回测参数优化，或提及 backtrader、量化回测框架时使用。若用户仅需数据获取而无回测需求，引导使用 baostock/akshare/tushare 等数据 Skill。
聚宽（JoinQuant）本地数据 SDK，提供 A 股行情、历史K线、财务数据、指标数据等，与聚宽官网数据同源。当用户提及 jqdatasdk、聚宽数据、需要获取A股数据，或已注册聚宽账号时使用。与 baostock（免费）和 tushare（数据最全）不同，jqdatasdk 需注册聚宽账号获取 Token，适合已在使用聚宽平台的用户。本地数据获取请用本技能，聚宽官网策略开发请用 joinquant-docs 技能。
机构级投研报告生成技能。覆盖中国A股、港股、美股上市公司。输出模式：1）投资速览：3-5页，含公司概览、核心财务指标、估值倍数、投资逻辑与风险因素；2）深度研报：≥25页，含行业分析、产业链图谱、三表模型、DCF估值、情景分析与敏感性测试。触发条件：1）直接请求：分析/看看/研究/调研/介绍一下 + 公司名或股票；2）投资询问：你怎么看/能不能买/值得投吗/帮我看看/扒一扒 + 公司或股票；3）关键词：研报、投资简报、投资速览、公司一页纸、深度研报、深度研究、深度分析、个股分析、一页纸、速览、公司速览、投研报告；4）股票代码：标准格式（如 600519.SH、0700.HK、AAPL、TSLA、BYD）。意图不明确时主动询问输出模式，禁止默认推断。
聚宽（JoinQuant）官网策略开发指南，涵盖回测、模拟交易、数据 API、交易函数、因子与技术指标。当用户编写聚宽策略、回测、模拟盘、查询聚宽 API、get_price/order/run_daily、Alpha 因子、技术指标，或提及 joinquant、聚宽、jqdata 策略时使用。本地数据获取请用 jqdatasdk 技能。
AKShare 开源金融数据接口库，提供股票、期货、期权、基金、外汇、债券、指数、加密货币等全品类金融数据；当用户需要获取各类金融市场数据时使用
生成 akquant 框架的可执行量化策略代码，涵盖数据接口、事件驱动、风控与优化。当用户需要开发量化策略、配置回测环境、设置风控规则、进行参数优化、实现横截面轮动策略，或提及 akquant 时使用
BaoStock 免费开源 A 股数据平台，无需注册、无需 API Key，支持股票行情、K线、财务数据、行业分类、指数成分股查询。当用户提及 baostock、需要获取A股历史行情、财务报表、交易日历，或需要**免费、免注册**的A股数据时使用。与 tushare（数据更全但需注册）和 jqdatasdk（聚宽数据）不同，baostock 完全免费无限制，适合快速入门和低成本数据需求。
QMT（迅投极速策略交易系统）Python 策略开发完整指南。涵盖策略编写、回测、实盘交易、API参考和代码示例。当用户需要开发 QMT 量化策略、查询 QMT API、从聚宽迁移至 QMT、编写实盘交易程序，或提及 QMT、迅投策略、QMT 回测时使用。
同花顺问财数据查询：使用中文自然语言查询A股、指数、基金、港美股、可转债等市场数据；当用户需要通过自然语言从问财获取选股、财务、资金流、技术指标等数据时使用。
通达信量化数据获取技能。当用户提及 tdxquant、通达信、TdxQuant、tqcenter，并且需要获取A股数据（行情快照、K线、财务、板块、可转债、新股、交易数据等）、查询交易日历、执行通达信公式、订阅行情、交易下单时使用
Tushare 专业金融数据平台，提供A股行情、历史K线、财务数据、宏观数据、指数数据等，覆盖全面、数据质量高。当用户提及 Tushare、获取A股数据、查询财务报表、下载宏观数据，或需要高质量、多维度金融数据时使用。与 baostock（免费但功能有限）和 jqdatasdk（需注册但有积分门槛）不同，tushare 数据最全但需注册获取 Token。免费替代方案可用 baostock 或 akshare。
RQAlpha 米筐开源事件驱动回测框架。支持A股和期货，模块化架构，可自由扩展；当用户需要快速回测A股/期货策略、使用内置数据（download-bundle）、开发Mod插件，或提及 rqalpha、米筐时使用。与 backtrader 相比，rqalpha 内置A股日线数据、安装更简便，适合快速验证；backtrader 更灵活、社区更大。若用户仅需数据获取而无回测需求，引导使用 baostock/akshare/tushare 等数据 Skill。
Use this skill to perform actions inside an Unreal Engine project via a live-editor MCP connection. Trigger when the user wants to change, query, or run something in their Unreal Engine project, not for conceptual or docs questions. Concrete triggers: spawn/move/duplicate/transform actors in a level, open a `.uproject`, add things around a PlayerStart, create or edit a Blueprint/Widget/Material/Niagara/Control Rig/Sequencer/Behavior Tree/GAS ability, read or write properties on actors (e.g. `bIsLocked` on `BP_DoorActor`), Live Coding recompile after editing C++ (`AActor`, `UMyComponent::Method`, `UPROPERTY`), or modify Static/Skeletal Mesh assets. Treat as Unreal context even without the word \"Unreal\": asset prefixes `BP_`, `WBP_`, `M_`, `MI_`, `NS_`, `CR_`, `SK_`, `SM_`, `ABP_`; UE C++ types/macros; `.uproject`; Content Browser; Outliner; PlayerStart; \"in my game\" plus UE signals. Skip for: pure conceptual/docs questions, Unity, Godot, or unrelated uses of \"blueprint\"/\"sequencer\"/\"widget\".
Use this skill when authoring or extending an Unreal Engine toolset, a class of static, AI-callable functions registered with `ToolsetRegistry` and exposed through the unreal-mcp server. Trigger when the user wants to add, expose, or register a new tool method, create a new toolset, or extend an existing one such as `BlueprintTools`, `StaticMeshTools`, `ObjectTools`, `LevelTools`, or `MaterialTools`. Concrete triggers: 'add a tool to X', 'expose this via MCP', 'register a function so Claude/the agent can call it', 'wire this into the toolset registry', 'create a new toolset for Y', 'add a Python toolset', 'make this AI-callable'; adding a `static` method to a `*Tools.cpp/.h/.py` file; editing files under a `Toolsets/` folder; designing tool parameters, return types, or struct schemas for a toolset. SKIP for: invoking existing tools at runtime (use unreal-mcp instead), authoring an Agent Skill (use unreal-skill), generic refactors that happen to touch a toolset file but don't add or redesign a tool, or unrelated uses of the word 'toolset'.
Use this skill when creating, editing, or reviewing an Unreal Engine Agent Skill, a named bundle of instructions registered with the unreal-mcp server (distinct from Claude Code's harness skills under `.claude/skills/`). Trigger when the user wants to add or change a skill that the in-editor agent will load. Concrete triggers: 'create a new Agent Skill', 'add a skill for X workflow', 'edit/update this skill', 'review my skill', 'make a Python skill class', 'create a skill UAsset', 'register a skill so Claude picks it up'; writing or editing a `SKILL.md` inside a UE plugin's `Skills/` or `Python/skills/` folder; defining a Python skill class registered with the skill registry; calling `CreateSkill`, `ListSkills`, or `GetSkills` MCP tools; designing a skill's name, description, or instruction body. SKIP for: authoring a toolset (use create-toolset), invoking an existing skill at runtime (use unreal-mcp), editing harness-level Claude Code skills under `.claude/skills/` or `~/.claude/skills/`, or generic uses of the word 'skill'.
Description
Description 1
Name field does not match the directory name.
Description 2
Claude Skills — questions
Answers built from the skills we actually parsed.