mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Comprehensive AI agent capability expansion toolkit for Claude Code: 22 specialist agents, 80 skills, and 29 slash commands — including a full blockchain/smart-contract domain (EVM + Solana) with a dedicated contract security auditor. Designed to coexist with superpowers and similar workflow plugins.
Plugin rain-skill from marketplace rain-skill in UtsavSavani08/rain-skill-main. 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.
api-patternsAPI design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination.
app-builderMain application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
architectureArchitectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.
bash-linuxBash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.
batch-operationsApply operations across multiple files simultaneously. Pattern-based bulk modifications, search-and-replace across codebases, consistent changes to many files at once.
behavioral-modesAI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
blockchain-fundamentalsBlockchain & web3 orientation and chain-selection decision tree. Use when a request mentions blockchain, web3, smart contract, dapp, on-chain, crypto, wallet, or token but the target chain/stack is not yet decided. Covers EVM vs Solana trade-offs, accounts model, gas/fees, wallets & keys, testnets/R
clean-codePragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments
code-review-checklistCode review guidelines covering code quality, security, and best practices.
code-review-graphToken-efficient code review using Tree-sitter AST graphs and MCP. Cuts AI token usage on large codebases by computing the blast radius of changes instead of reading entire codebases. Uses a SQLite graph database for structural analysis.
context-compressionManage and compress conversation context in long sessions. Detect when context is growing large, summarize completed work phases, archive old findings while preserving key decisions. Prevents context degradation.
database-designDatabase design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases.
defensive-editingMUST auto-load whenever the user asks to edit, change, modify, rename, refactor, or update a model, shared helper, common util, service file, base class, or any file under lib/models/, utils/, services/, common/, shared/, helpers/. Also fires on regression-style follow-ups — "still same", "still bro
defi-patternsDeFi protocol building blocks and their attack surface. Use when building or integrating AMMs/DEXes, lending, staking, vaults, oracles, or tokenomics, or on requests mentioning swap, liquidity, yield, staking, lending, oracle, or flash loan. References token-standards and smart-contract-security.
deployment-proceduresProduction deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts.
documentation-templatesDocumentation templates and structure guidelines. README, API docs, code comments, and AI-friendly documentation.
flutter-add-integration-testFlutter integration testing expert. Load for end-to-end Flutter integration tests — Flutter Driver, integration_test package, real device/emulator testing, Firebase Test Lab, pumpAndSettle debugging, and scrollable list testing. Deeper than flutter-expert's basic testWidgets coverage. Triggers on: i
flutter-add-widget-previewFlutter widget preview expert. Load for adding interactive widget previews using the @Preview annotation and previews.dart system — IDE-integrated visual testing without running the full app. Triggers on: widget preview, @Preview, flutter widget-preview, previews.dart, preview annotation, MultiPrevi
flutter-add-widget-testFlutter widget testing expert. Load for component-level Flutter widget tests — WidgetTester, Finder, Matcher, pump/pumpAndSettle, find.byKey/byType/text, Riverpod/Provider overrides, golden tests, and the full 9-step test lifecycle. Deeper than flutter-expert's basic testWidgets coverage. Triggers o
flutter-apply-architecture-best-practicesFlutter architecture expert. Load for structuring Flutter apps with layered MVVM architecture — UI layer (widgets + ChangeNotifier ViewModels), Domain layer (use cases, entities), Data layer (repositories + services), dependency injection, and the 8-step feature checklist. Deeper than flutter-expert
flutter-build-responsive-layoutFlutter responsive layout expert. Load for building adaptive layouts that work across phone, tablet, desktop, and foldable screens — LayoutBuilder, MediaQuery, Expanded/Flexible, breakpoints, and orientation handling. Triggers on: responsive, adaptive layout, LayoutBuilder, MediaQuery, breakpoint, s
flutter-expertFlutter and Dart expert. Load for any Flutter app work — widget trees, state management (Riverpod, BLoC, Provider, GetX), navigation (GoRouter, AutoRoute), platform channels, Firebase integration, performance tuning, and app store submission. Complements mobile-design (touch/UX) which should also be
flutter-fix-layout-issuesFlutter layout debugger. Load when fixing layout errors — RenderFlex overflow, unbounded constraints, viewport height errors, ParentData violations, and constraint negotiation failures. Triggers on: overflow, RenderFlex overflowed, unbounded height, unbounded width, layout error, constraints, viewpo
flutter-implement-json-serializationFlutter JSON serialization expert. Load for any Flutter JSON work — manual fromJson/toJson models, dart:convert, json_serializable, nested objects, list parsing, large payload background parsing, and API response mapping. Triggers on: json, fromJson, toJson, serialization, dart:convert, jsonDecode,
flutter-setup-declarative-routingFlutter routing and deep linking expert. Load for go_router setup, deep linking (Android intent filters + iOS Info.plist + assetlinks), StatefulShellRoute persistent shells, named routes, path/query parameters, route guards, and nested navigation. Deeper than flutter-expert's basic GoRouter coverage
flutter-setup-localizationFlutter localization and internationalization (i18n/l10n) expert. Load for any Flutter localization work — ARB files, flutter_localizations, intl package, plurals, placeholders, language switching, and locale configuration. Triggers on: localization, localizations, intl, arb, flutter_localizations,
foundry-hardhat-testingTesting EVM smart contracts with Foundry and Hardhat. Use when writing contract tests, fuzz/invariant tests, fork tests, gas snapshots, or coverage for .sol code. Covers forge test, cheatcodes, fuzzing, invariants, mainnet forking, and Hardhat (mocha/chai/ethers).
frontend-designDesign thinking and decision-making for web UI. Use when designing components, layouts, color schemes, typography, or creating aesthetic interfaces. Teaches principles, not fixed values.
game-developmentGame development orchestrator. Routes to platform-specific skills based on project needs.
gas-optimizationgeo-fundamentalsgit-workflowi18n-localizationintelligent-routinglint-and-validatemcp-buildermemory-systemmobile-designmock-data-seedingnextjs-react-expertnodejs-best-practicesnpm-supply-chain-protectionparallel-agentsperformance-profilingplan-writingpost-task-reviewpowershell-windowsproject-wikipython-patternsrain-skill-protocolred-team-tacticsroot-causingrust-prosecurity-gateseo-fundamentalsserver-managementsession-startsmart-brainstormsmart-contract-deploymentsmart-contract-securitysmart-contract-upgradessmart-flowsolana-anchorsolidity-smart-contractstailwind-patternstdd-workflowtesting-patternstoken-standardsverifying-completionvulnerability-scannerweb-design-guidelinesweb3-frontendwebapp-testingworkflow-add-featureworkflow-bug-fixworkflow-documentationworkflow-new-projectworkflow-refactorworkflow-small-taskwriting-skills/rain-skill:add-featureAdd a feature to an existing project. Forces the FEATURE flow — concise brainstorm, quick plan, TDD implementation, integration security gate, full review, wiki update. Use instead of /smart-flow when you know the task is a feature addition.
/rain-skill:audit-contractRun a dedicated smart-contract security audit on the project or a specific contract/path. Invokes the smart-contract-auditor agent + smart-contract-security skill (reentrancy, access control, oracle manipulation, MEV, Slither/Mythril/Echidna). Use before any mainnet deploy or any time you want an ou
/rain-skill:batchMulti-file find-and-replace with the Plan → Preview → Apply → Verify discipline. Previews changes via `grep`, applies via `sed` / PowerShell / Edit, then re-greps and runs lint + tests. Refuses to run on a dirty git tree (rollback = `git restore .`).
/rain-skill:brainstormStructured brainstorming for projects and features. Explores multiple options before implementation.
/rain-skill:createCreate new application command. Triggers App Builder skill and starts interactive dialogue with user.
/rain-skill:debugDebugging command. Activates DEBUG mode for systematic problem investigation.
/rain-skill:deployDeployment command for production releases. Pre-flight checks and deployment execution.
/rain-skill:docsWrite or update documentation. Forces the DOCUMENTATION flow — reads actual code first, drafts accurate docs, reviews for accuracy and completeness, syncs the project wiki. Covers README, API docs, JSDoc/docstrings, changelogs, architecture docs, and onboarding guides.
/rain-skill:doneClose the current in-progress task. Runs the final gate sequence — security-gate, post-task-review, and verifying-completion — then closes the task record and files knowledge into the project wiki. Use when implementation is complete and you want to finalize the task.
/rain-skill:enhanceAdd or update features in existing application. Used for iterative development.
/rain-skill:fixFix a bug. Forces the BUG_FIX flow — root cause analysis, failing test (RED), minimal fix (GREEN), bug security impact check, review, verification, and wiki entry in bugs-fixed.md. No code before root cause is named.
/rain-skill:new-projectStart a new project from scratch. Forces the NEW_PROJECT flow — brainstorm, architecture plan, TDD implementation, full OWASP security gate, wiki seeding. Use instead of /smart-flow when you know the task is a new project and want to skip flow detection.
/rain-skill:npm-protectHarden this machine and/or current project against npm supply-chain attacks with a 4-layer defense — (1) 7-day install cooldown, (2) ignore-scripts to block install-script malware (THE most important layer — blocks 90% of real attacks), (3) audit-level=high so npm audit fails on real findings, (4) s
/rain-skill:orchestrateCoordinate multiple agents for complex tasks. Use for multi-perspective analysis, comprehensive reviews, or tasks requiring different domain expertise.
/rain-skill:planCreate project plan using project-planner agent. No code writing - only plan file generation.
/rain-skill:previewPreview server start, stop, and status check. Local development server management.
/rain-skill:project-initInitialize rain-skill project infrastructure in the current directory. Creates docs/rain-skill/ folder structure (tasks/, wiki/), seeds the project wiki from the existing codebase, and creates a CLAUDE.md if one doesn't exist. Run once per project when starting to use rain-skill.
/rain-skill:rememberSave information to persistent memory for cross-session recall. Stores preferences, conventions, decisions, and context.
/rain-skill:review-graphToken-efficient code review using the external `code-review-graph` tool (Tree-sitter + MCP server, 19 languages). Builds/refreshes a SQLite graph of the repo and reviews via scoped MCP queries instead of full-file reads. Requires `pipx install code-review-graph` + one-time `code-review-graph install
/rain-skill:securityRun a standalone security audit on the project or a specific file/module. Invokes both the security-auditor agent (OWASP analysis) and the vulnerability-scanner skill (dependency + code scan). Use any time you want a dedicated security pass outside of a normal smart-flow task.
/rain-skill:seedSeed mock/demo data into the project database. Detects the stack, writes an idempotent seed script, runs it, and verifies row counts.
/rain-skill:smart-flowForce-run the rain-skill proportional workflow (smart-flow). Detects task type, creates a task record, runs the right flow + mandatory security-gate + post-task-review.
/rain-skill:startStart a new working session. Reads project wiki, surfaces in-progress tasks, summarizes recent git activity, detects the tech stack, and loads domain skills — all in one brief. Use at the beginning of every session to hit the ground running.
/rain-skill:statusDisplay agent and project status. Progress tracking and status board.
/rain-skill:task-routerExplicitly classify a request and route it to the correct flow without starting implementation. Shows the detected flow, matching domain skills, and step-by-step pipeline — then stops and asks for confirmation before proceeding. Use when you want to inspect what smart-flow would do before committing
/rain-skill:testTest generation and test running command. Creates and executes tests for code.
/rain-skill:ui-ux-pro-maxAI-powered design intelligence with 50+ styles, 95+ color palettes, and automated design system generation
/rain-skill:wiki-updateManually trigger a project wiki update. Use to ingest a new source, update specific pages, sync the wiki with current code, or run a wiki health check. Subcommands - ingest | update | sync | lint | query.
/rain-skill:wikiPer-project knowledge base. Subcommands - init | ingest <path-or-url> | query <question> | lint. Wiki lives at docs/rain-skill/wiki/ in the user's project root and accumulates knowledge across sessions.
backend-specialistExpert backend architect for Node.js, Python, and modern serverless/edge systems. Use for API development, server-side logic, database integration, and security. Triggers on backend, server, api, endpoint, database, auth.
blockchain-developerExpert blockchain & smart-contract engineer for EVM (Solidity) and Solana (Anchor/Rust). Use for smart contracts, dapps, DeFi, tokens/NFTs, and on-chain logic. Triggers on smart contract, solidity, evm, ethereum, web3, dapp, foundry, hardhat, solana, anchor, erc20, erc721, nft, defi, on-chain, token
code-archaeologistExpert in legacy code, refactoring, and understanding undocumented systems. Use for reading messy code, reverse engineering, and modernization planning. Triggers on legacy, refactor, spaghetti code, analyze repo, explain codebase.
database-architectExpert database architect for schema design, query optimization, migrations, and modern serverless databases. Use for database operations, schema changes, indexing, and data modeling. Triggers on database, sql, schema, migration, query, postgres, index, table.
debuggerExpert in systematic debugging, root cause analysis, and crash investigation. Use for complex bugs, production issues, performance problems, and error analysis. Triggers on bug, error, crash, not working, broken, investigate, fix.
devops-engineerExpert in deployment, server management, CI/CD, and production operations. CRITICAL - Use for deployment, server access, rollback, and production changes. HIGH RISK operations. Triggers on deploy, production, server, pm2, ssh, release, rollback, ci/cd.
documentation-writerExpert in technical documentation. Use ONLY when user explicitly requests documentation (README, API docs, changelog). DO NOT auto-invoke during normal development.
explorer-agentAdvanced codebase discovery, deep architectural analysis, and proactive research agent. The eyes and ears of the framework. Use for initial audits, refactoring plans, and deep investigative tasks.
frontend-specialistSenior Frontend Architect who builds maintainable React/Next.js systems with performance-first mindset. Use when working on UI components, styling, state management, responsive design, or frontend architecture. Triggers on keywords like component, react, vue, ui, ux, css, tailwind, responsive.
game-developerGame development across all platforms (PC, Web, Mobile, VR/AR). Use when building games with Unity, Godot, Unreal, Phaser, Three.js, or any game engine. Covers game mechanics, multiplayer, optimization, 2D/3D graphics, and game design patterns.
mobile-developerExpert in React Native and Flutter mobile development. Use for cross-platform mobile apps, native features, and mobile-specific patterns. Triggers on mobile, react native, flutter, ios, android, app store, expo.
orchestratorMulti-agent coordination and task orchestration with coordinator mode. Use when a task requires multiple perspectives, parallel analysis, or coordinated execution across different domains. Invoke this agent for complex tasks that benefit from security, backend, frontend, testing, and DevOps expertis
penetration-testerExpert in offensive security, penetration testing, red team operations, and vulnerability exploitation. Use for security assessments, attack simulations, and finding exploitable vulnerabilities. Triggers on pentest, exploit, attack, hack, breach, pwn, redteam, offensive.
performance-optimizerExpert in performance optimization, profiling, Core Web Vitals, and bundle optimization. Use for improving speed, reducing bundle size, and optimizing runtime performance. Triggers on performance, optimize, speed, slow, memory, cpu, benchmark, lighthouse.
product-managerExpert in product requirements, user stories, and acceptance criteria. Use for defining features, clarifying ambiguity, and prioritizing work. Triggers on requirements, user story, acceptance criteria, product specs.
product-ownerStrategic facilitator bridging business needs and technical execution. Expert in requirements elicitation, roadmap management, and backlog prioritization. Triggers on requirements, user story, backlog, MVP, PRD, stakeholder.
project-plannerSmart project planning agent. Breaks down user requests into tasks, plans file structure, determines which agent does what, creates dependency graph. Use when starting new projects or planning major features.
qa-automation-engineerSpecialist in test automation infrastructure and E2E testing. Focuses on Playwright, Cypress, CI pipelines, and breaking the system. Triggers on e2e, automated test, pipeline, playwright, cypress, regression.
security-auditorElite cybersecurity expert. Think like an attacker, defend like an expert. OWASP 2025, supply chain security, zero trust architecture. Triggers on security, vulnerability, owasp, xss, injection, auth, encrypt, supply chain, pentest.
seo-specialistSEO and GEO (Generative Engine Optimization) expert. Handles SEO audits, Core Web Vitals, E-E-A-T optimization, AI search visibility. Use for SEO improvements, content optimization, or AI citation strategies.
smart-contract-auditorSpecialist smart-contract security auditor for EVM/Solidity and Solana. Use to audit contracts, review for vulnerabilities, or gate a deploy. Triggers on audit smart contract, contract security, solidity vulnerability, reentrancy, exploit, slither, mythril, defi security. Read-only — reports finding
test-engineerExpert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.
cat "${CLAUDE_PLUGIN_ROOT}/hooks/smart_flow_reminder.txt"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/npm_protect_check.sh"
cat "${CLAUDE_PLUGIN_ROOT}/hooks/session_close_reminder.txt"
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.