mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Complete collection of agents, skills, hooks, commands, and rules evolved over 10+ months of intensive daily use
Plugin everything-claude-code from marketplace everything-claude-code in codelably/harmony-claude-code. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
oneskill发现技能 (Skill),迭代查询,并在任何环境中自动安装技能。
backend-patternsBackend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
clickhouse-ioClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
coding-standardsUniversal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
continuous-learning-v2Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
continuous-learningAutomatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
eval-harnessFormal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
frontend-patternsFrontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
golang-patternsIdiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.
golang-testingGo testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.
iterative-retrievalPattern for progressively refining context retrieval to solve the subagent context problem
postgres-patternsPostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.
project-guidelines-examplesecurity-reviewUse this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
strategic-compactSuggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
tdd-workflowUse this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
verification-loopdjango-patternsDjango 架构模式、使用 DRF 的 REST API 设计、ORM 最佳实践、缓存、信号(Signals)、中间件(Middleware)以及生产级 Django 应用。
django-securityDjango 安全最佳实践,涵盖身份认证、授权、CSRF 防护、SQL 注入预防、XSS 预防以及安全的部署配置。
django-tdd使用 pytest-django、测试驱动开发(TDD)方法论、factory_boy、Mock 模拟、覆盖率统计以及 Django REST Framework API 测试的 Django 测试策略。
django-verificationDjango 项目的验证循环(Verification loop):包含数据库迁移、代码检查、带覆盖率的测试、安全扫描,以及在发布或 PR 前的部署就绪检查。
java-coding-standardsSpring Boot 服务的 Java 编码规范:命名、不可变性(Immutability)、Optional 使用、流(Streams)、异常处理、泛型(Generics)和项目布局。
jpa-patternsSpring Boot 中用于实体设计、关联关系、查询优化、事务、审计、索引、分页和连接池的 JPA/Hibernate 模式。
python-patternsPythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
python-testing使用 pytest、TDD 方法论、fixtures、mocking、参数化和代码覆盖率要求的 Python 测试策略。
springboot-patternsSpring Boot 架构模式、REST API 设计、分层服务、数据访问、缓存、异步处理和日志记录。适用于 Java Spring Boot 后端开发工作。
springboot-securitySpring Boot 服务中关于身份认证/授权(authn/authz)、校验、CSRF、密钥管理、响应头、限流及依赖安全的 Spring Security 最佳实践。
springboot-tdd使用 JUnit 5、Mockito、MockMvc、Testcontainers 和 JaCoCo 进行 Spring Boot 的测试驱动开发(TDD)。在添加功能、修复 Bug 或进行重构时使用。
springboot-verificationSpring Boot 项目的验证循环(Verification loop):包含构建、静态分析、带覆盖率的测试、安全扫描,以及在发布或 PR 前的差异评审(diff review)。
/everything-claude-code:build-fix/everything-claude-code:checkpoint/everything-claude-code:code-review/everything-claude-code:e2e使用 Playwright 生成并运行端到端测试。创建测试旅程、运行测试、捕获截图/视频/追踪,并上传产物。
/everything-claude-code:eval/everything-claude-code:evolve将相关的直觉(Instincts)聚类为技能(Skills)、命令(Commands)或智能体(Agents)
/everything-claude-code:go-build增量修复 Go 构建错误、go vet 警告和 linter 问题。调用 go-build-resolver 智能体(Agent)进行最小化、外科手术式的修复。
/everything-claude-code:go-review针对地道模式、并发安全、错误处理和安全性的全面 Go 代码审查。调用 go-reviewer 智能体 (Agent)。
/everything-claude-code:go-test强制执行 Go 的测试驱动开发(TDD)工作流。先编写表驱动测试(Table-Driven Tests),然后进行实现。使用 go test -cover 验证 80% 以上的覆盖率。
/everything-claude-code:instinct-export导出直觉(Instincts)以便与团队成员或其他项目共享
/everything-claude-code:instinct-import从团队成员、技能创建者(Skill Creator)或其他来源导入直觉(Instincts)
/everything-claude-code:instinct-status显示所有已学习的本能及其置信度
/everything-claude-code:learn/everything-claude-code:orchestrate/everything-claude-code:plan重述需求、评估风险并创建分步实施计划。在修改任何代码之前,必须等待用户确认(CONFIRM)。
/everything-claude-code:python-review针对 PEP 8 标准、类型提示、安全性及 Pythonic 惯用写法的 Python 代码全面审查。调用 python-reviewer 智能体(Agent)。
/everything-claude-code:refactor-clean/everything-claude-code:setup-pm配置你偏好的包管理器 (npm/pnpm/yarn/bun)
/everything-claude-code:skill-create分析本地 Git 历史以提取编码模式并生成 SKILL.md 文件。Skill Creator GitHub App 的本地版本。
/everything-claude-code:tddEnforce test-driven development workflow. Scaffold interfaces, generate tests FIRST, then implement minimal code to pass. Ensure 80%+ coverage.
/everything-claude-code:test-coverage/everything-claude-code:update-codemaps/everything-claude-code:update-docs/everything-claude-code:verifyarchitect用于系统设计、可扩展性及技术决策的软件架构专家。在规划新功能、重构大型系统或做出架构决策时请主动(PROACTIVELY)使用。
build-error-resolver构建与 TypeScript 错误修复专家。当构建失败或出现类型错误时主动使用。仅以最小差异修改(minimal diffs)修复构建/类型错误,不进行架构层面的编辑。专注于快速恢复绿色构建状态。
code-reviewer专家级代码审查专家。主动审查代码的质量、安全性与可维护性。在编写或修改代码后立即使用。所有代码变更必须(MUST)使用此工具进行审查。
database-reviewerPostgreSQL 数据库专家,专注于查询优化、模式设计、安全性和性能。在编写 SQL、创建迁移、设计模式或排查数据库性能问题时主动使用。包含 Supabase 最佳实践。
doc-updater文档与代码图谱(Codemap)专家。主动用于更新代码图谱和文档。运行 /update-codemaps 和 /update-docs,生成 docs/CODEMAPS/*,更新 README 和指南。
e2e-runner使用 Vercel Agent Browser(首选)及 Playwright(备选)的端到端(E2E)测试专家。主动用于生成、维护和运行 E2E 测试。管理测试旅程(test journeys)、隔离不稳定测试(quarantines flaky tests)、上传产物(截图、视频、追踪记录),并确保关键用户流程正常工作。
go-build-resolverGo 构建、vet 检查及编译错误修复专家。以最小化改动修复构建错误、go vet 问题及 Linter 警告。适用于 Go 构建失败的场景。
go-reviewer资深 Go 代码审查专家,专注于地道的 Go 编程风格(idiomatic Go)、并发模式、错误处理和性能。适用于所有 Go 代码变更。对于 Go 项目,**必须使用**此智能体(Agent)。
harmonyos-app-resolverplanner复杂功能与重构的规划专家。当用户请求功能实现、架构变更或复杂重构时,请“主动(PROACTIVELY)”使用。规划任务时会自动激活。
python-reviewerExpert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.
refactor-cleaner冗余代码清理与合并专家。主动(PROACTIVELY)用于删除未使用代码、重复代码并进行重构。运行分析工具(knip, depcheck, ts-prune)来识别冗余代码并安全地将其删除。
security-reviewer安全漏洞检测与修复专家。在编写处理用户输入、身份验证、API 端点或敏感数据的代码后,应主动(PROACTIVELY)使用。标记密钥泄露、SSRF、注入、不安全的加密以及 OWASP Top 10 漏洞。
tdd-guide测试驱动开发(Test-Driven Development)专家,强制执行“先写测试”的方法论。在编写新功能、修复 Bug 或重构代码时请主动使用。确保 80% 以上的测试覆盖率。
node -e "console.error('[Hook] BLOCKED: Dev server must run in tmux for log access');console.error('[Hook] Use: tmux new-session -d -s dev \"npm run dev\"');console.error('[Hook] Then: tmux attach -t
node -e "if(!process.env.TMUX){console.error('[Hook] Consider running in tmux for session persistence');console.error('[Hook] tmux new -s dev | tmux attach -t dev')}"
node -e "console.error('[Hook] Review changes before push...');console.error('[Hook] Continuing with push (remove this hook to add interactive review)')"
node -e "const fs=require('fs');let d='';process.stdin.on('data',c=>d+=c);process.stdin.on('end',()=>{const i=JSON.parse(d);const p=i.tool_input?.file_path||'';if(/\.(md|txt)$/.test(p)&&!/(README|CLAU
node "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/suggest-compact.js"
node "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/pre-compact.js"
node "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/session-start.js"
node -e "let d='';process.stdin.on('data',c=>d+=c);process.stdin.on('end',()=>{const i=JSON.parse(d);const cmd=i.tool_input?.command||'';if(/gh pr create/.test(cmd)){const out=i.tool_output?.output||'
node -e "let d='';process.stdin.on('data',c=>d+=c);process.stdin.on('end',()=>{console.error('[Hook] Build completed - async analysis running in background');console.log(d)})"
node -e "const{execFileSync}=require('child_process');const fs=require('fs');let d='';process.stdin.on('data',c=>d+=c);process.stdin.on('end',()=>{const i=JSON.parse(d);const p=i.tool_input?.file_path
node -e "const{execSync}=require('child_process');const fs=require('fs');const path=require('path');let d='';process.stdin.on('data',c=>d+=c);process.stdin.on('end',()=>{const i=JSON.parse(d);const p=
node -e "const fs=require('fs');let d='';process.stdin.on('data',c=>d+=c);process.stdin.on('end',()=>{const i=JSON.parse(d);const p=i.tool_input?.file_path;if(p&&fs.existsSync(p)){const c=fs.readFileS
node "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/check-console-log.js"
node "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/session-end.js"
node "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/evaluate-session.js"
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.