mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Universal multi-domain agent orchestration framework. Your AI workforce: 60 specialized agents across 9 builder-role archetypes, coordinated by an intelligent pipeline. /act routes any task through controller + specialist agents (review/audit/optimize/improve modes via keyword router), /team runs parallel execution waves with Strategic Mode for cross-domain initiatives, /designer guides design exploration, /helper recommends commands.
Plugin cagents from marketplace cagents in CaelanDrayer/cAgents. Commands read from the repo's manifest — today.
actExecute any task through coordinated agents. Use for building, fixing, writing, or any single-domain work. TRIGGER: act, implement, fix, build, create. NOT for: parallel work or cross-domain strategy (use /team).
designerGuided design exploration that produces implementation-ready documents through structured Q&A. Use before building to clarify requirements. TRIGGER: design, plan this, think through, architecture. NOT for: implementation (/act) or review (/act review).
helperExplains cAgents commands and recommends the right one for your task. Use when choosing between skills or learning how they work. TRIGGER: help, which command, how do I, what can cAgents do. NOT for: executing tasks directly.
teamParallel multi-agent execution with wave-based quality gates. Use for complex tasks with 3+ parallelizable items, including cross-domain strategic work (via Strategic Mode). TRIGGER: team, parallel, swarm, complex multi-part, cross-domain, strategic. NOT for: simple single-domain tasks (/act).
academic-advisorAcademic research and tutoring consolidated agent. Modes: research (literature review, research design, academic writing, grant proposals), tutor (concept explanation, problem solving, study coaching, exam prep). Set metadata.mode or pass mode=<value> in the invocation.
ai-writing-editorUse when text needs to be checked for AI-writing tells, humanized, or both — detecting synthetic markers (delve, tapestry, em-dash overuse, low burstiness), rewriting generated prose into natural human voice, or running a one-pass detect-then-rewrite gate. Mode-flagged: set metadata.mode or pass mod
architectUse when making system design decisions, evaluating technical approaches, designing API contracts, or planning migrations. Provides architecture diagrams, tradeoff analysis, and pattern recommendations.
backend-developerImplements server-side systems — REST/GraphQL APIs, auth, caching, DB schema, migrations, and game-engine/gameplay systems (rendering pipelines, game logic, physics). Use for backend, database, or game-engine build work. Modes: api, database, engine, game. Set metadata.mode. NOT for: frontend/UI (us
ccoUse for creative vision, narrative strategy, artistic direction, tier 3-4 creative projects, or major creative decisions. Chief Creative Officer.
ceoUse for strategic decisions, major initiatives, and company direction. Chief Executive Officer providing strategic vision and stakeholder alignment.
cfoUse for budget requests, investment decisions, pricing strategy, financial risk assessment, and fundraising. Chief Financial Officer providing financial leadership.
chroUse for workforce planning, organizational design, talent strategy, culture initiatives, and major HR transformations. Chief Human Resources Officer.
cmoUse for marketing strategy, brand positioning, demand generation oversight, and growth channel optimization. CMO-level marketing leadership.
composerComposes original and adaptive music — game scoring, leitmotifs, thematic composition, orchestration, loop design, and interactive/dynamic audio systems (Wwise/FMOD, horizontal resequencing, vertical layering). Use for music composition and adaptive/interactive audio, especially for games and intera
cooUse for operational decisions, process coordination, cross-functional efficiency improvements, and scaling operations. Chief Operating Officer.
coord-log-writerAssembles final coordination_log.yaml from on-disk artifacts (task_list.yaml, per-wave EVT files, outputs/, gate_validations/). Reads everything; lead receives only a 1-line confirmation.
coordinatorParameterized controller for lightweight domains (health, education, personal, arts, trades). Reads domain_overrides.yaml at runtime to discover specialists. Use when the calling domain lacks a dedicated controller.
cpoUse for strategic planning oversight, cross-functional alignment, tier 3-4 strategic plans, or complex multi-domain planning. Chief Planning Officer.
croUse for revenue strategy, sales and marketing alignment, pipeline optimization, and go-to-market execution. CRO-level revenue leadership.
ctoUse for technology strategy, architecture decisions, tech stack evaluation, and engineering excellence. Chief Technology Officer providing technical leadership.
customer-success-managerDrives customer value realization and retention — onboarding, product adoption, health scoring, churn prevention, QBRs, and expansion through success. Use for proactive customer-success work: getting customers live, growing usage, and keeping renewals healthy. Modes: onboarding, adoption, retention.
data-leadLeads and executes data engineering — pipeline architecture, schema design, and data-quality standards (coordinate), plus hands-on ETL/ELT, SQL, dashboards, and BI (analyze). Use for data-platform coordination or data-analysis execution. Modes: coordinate, analyze. Set metadata.mode. NOT for: ML mod
data-scientistdevops-engineereditorexecution-monitorfilm-directorfrontend-developergame-designergeneral-counselhitlhr-managerlife-coachmarket-research-analystmarketing-analystmarketing-strategistmedical-advisornarrative-directoroperations-manageroptimizerorchestratorplannerproduct-ownerqa-leadreviewerroutersales-strategistscholarsecurity-engineerself-correctsocial-scientiststrategic-plannersupport-directortask-stateteam-bootstrapteam-leadtech-leadtechnical-writertranslatortriggervalidatorvisual-artistwave-reviewerworldbuilderMatt 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
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
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.