mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
GraphyLoop Workflow v3 for Claude Code: the /graphyloop:chadi-* commands, the agent squad, core workflow skills and the graphyloop MCP server (wave planner, persistent memory, secrets, preflight).
Plugin graphyloop from marketplace graphyloop in chadixearth/graphyloop. Commands read from the repo's manifest — 11 days ago.
This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.
graphyloop-wavesUse this skill when a request spans more than one layer (database + backend + frontend, or a feature plus a data pipeline). Turns the request into contract-first parallel waves with enforced dependencies, exclusive file ownership and per-lane acceptance checks, using the graphyloop planner and swarm
graphyloop-workflowUse this skill at the start of any non-trivial coding task, build or multi-file change to follow GraphyLoop Workflow v3 - recall, goal and proof up front, inline first (up to 8 files), fan out only for 2+ independent slices, context pack, frozen contract, no polling, proof not claims, review by blas
swarm-memoryUse this skill at the start and end of every non-trivial task to recall and record durable project knowledge through graphyloop memory - what to search before planning, what is worth storing, what must never be stored, and how to correct a wrong memory.
/graphyloop:chadi-auditRun testing, security, performance, and final code review without broad implementation.
/graphyloop:chadi-confusingFor confusing/current questions, research first using last30days, then answer.
/graphyloop:chadi-dbSet up or migrate the database (Supabase-first): check credentials, plan migrations, dry-run before apply.
/graphyloop:chadi-deployShip to Vercel safely: preflight, mirror env keys, preview deploy, then gated production.
/graphyloop:chadi-discussDiscuss-first mode: parallel discovery then present plan, wait for approval before implementing.
/graphyloop:chadi-fastDEFAULT mode. Main-agent-first workflow. Standard work auto-proceeds; Heavy work waits for approval unless pre-approved.
/graphyloop:chadi-goSkip discuss gate, straight to main-agent implementation.
/graphyloop:chadi-initInitialize or refresh the current repo with agent-chadi workflow files.
/graphyloop:chadi-planCreate an industry-style plan with risk classification and parallel execution plan.
/graphyloop:chadi-recallMemory recall — search graphyloop memory for facts, lessons, decisions and past activity.
/graphyloop:chadi-releasePrepare release notes, rollback plan, and final verification summary.
/graphyloop:chadi-researchUse last30days for fresh public internet/community research before answering.
/graphyloop:chadi-reviewRun final testing, security review, and code review.
/graphyloop:chadi-skillsCheck which bundled and referenced skills are installed for this harness.
/graphyloop:chadi-wavesPlan a multi-layer feature as parallel waves (contract -> builders -> integration -> verify -> deploy) and dispatch wave 0.
agent-chadiPrimary all-rounder and squad driver for any harness. GraphyLoop Workflow v3: recall, goal and proof up front, inline first (up to 8 files), fan out only for 2+ independent slices while keeping one, context pack, frozen contract, no polling, proof not claims, review by blast radius, evidence report.
chadi-agent-writerAgent/command/skill builder. Reads existing agent patterns, scaffolds new agents, validates agent files against schema. Meta-capability — agent-chadi uses this to build its own team.
chadi-architectArchitecture and integration planning subagent for medium/high-risk changes.
chadi-backendBackend/API implementation helper for routes, services, validation, auth, and server behavior.
chadi-councilDedicated decision council subagent. Four voices (Architect, Skeptic, Pragmatist, Critic) deliberate ambiguous decisions internally. Uses graphyloop memory results, when the driver passes them, for consistency across sessions.
chadi-dataDatabase and data-flow helper for schema, migrations, queries, indexes, Prisma/Supabase/Postgres/MySQL/Redis, and data integrity.
chadi-devopsDevOps/release helper for environment variables, deployment config, CI checks, build commands, release notes, and rollback planning.
chadi-docsDocumentation subagent for README, API docs, inline comments, CHANGELOG, migration guides, and project documentation writing.
chadi-explorerRead-only repo explorer for architecture, affected files, dependencies, route maps, and codebase context.
chadi-frontendFrontend/UI implementation and verification helper for layout, forms, routing, responsiveness, and client behavior.
chadi-integratorWave 2 integration specialist — joins parallel lanes: swaps frontend mocks for real API calls, wires env/credentials, applies local migrations, boots the app and walks the happy path end to end. Resolves contract drift instead of hiding it.
chadi-memoryMemory subagent. Graphyloop memory is the store. Recall before work, store after.
chadi-performancePerformance and reliability review subagent for render performance, bundle size, API latency, database queries, caching, retries, loading states, and reliability.
chadi-qualityCode quality subagent for linting, formatting, type checking enforcement, and code convention audits. Runs linters, formatters, and type-checkers; fixes violations; enforces project code standards.
chadi-refactorSafe cross-file refactoring agent. Renames, symbol extraction, module restructuring, pattern-based code transformation. Uses ast-grep for structural search/replace and impact analysis. Dry-run first, verify no breakage. Hard refuses new features or behavioral changes — refactor only.
chadi-reviewerFinal code reviewer for correctness, maintainability, regressions, config validity, security gaps, missing tests, and accidental unrelated changes.
chadi-securitySecurity review subagent for auth, RBAC, inputs, uploads, secrets, APIs, database access, XSS, CSRF, CSP, dependencies, and deployment exposure.
chadi-testTesting and verification subagent for unit, integration, e2e, build, lint, typecheck, and regression checks. Follows browser-last discipline — vitest+jsdom first, browser tools only for critical E2E.
chadi-thinkDeep thinking/planning subagent. Spawned by agent-chadi when task needs complex reasoning, architecture design, or hard problem-solving. Returns plan — does not code.
chadi-visionVision subagent for image processing. Read-only. Describes images, screenshots, sketches and diagrams as text. The driver dispatches it when the user attaches an image or asks about visual content and the main model cannot see images.
graphcrew-builderSurgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns a terse diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors
graphcrew-fixerMinimal fix agent. Reads error output, makes 1-file surgical fix. No discovery, no exploration, no context beyond the error itself. Use when test fails, build breaks, or lint error needs fixing. Hard refuses multi-file changes, new features, or speculative refactors. Faster than graphcrew-builder fo
graphcrew-investigatorRead-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is compressed so the main thread eats ~60% fewer tokens than vanilla Explore. Refuses to suggest fixes.
graphcrew-reviewerDiff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format `path:line: <emoji> <severity>: <problem>. <fix>.` Use for \"review this PR\", \"review my diff\", \"audit this file\". Skips formatting nits unless they change meaning.
operating-rulesUniversal guardrails for all agents. A per-project operating-rules file (for example `.opencode/agents/operating-rules.md`) overrides with project-specific facts.
story-video-automatorCreate real-based short stories and ~1-minute AI videos: storyline, script, beat sheet, scenes, voiceover plan, render. Separate media-automation agent — NOT the coding agent.
graphyloopruns: npx -y [email protected] mcp
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
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 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.