mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
An agent swarm, Oracle, Manager, Lead, Coder, and an optional Driver, that takes a PRD to built, tested, reviewed code. Enforced reviews, a shared ledger, and a scoring rubric hold every role accountable.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin sentinel-swarm in Alexk413x/sentinel-swarm. Commands read from the repo's manifest — 9 days ago.
sentinel-swarmCopilot companion for Sentinel Swarm. Use for swarm status, setup, run, or resume requests in Copilot. Reads Claude run records and reports unsupported native workers without starting a swarm.
resumeContinues an unfinished sentinel-swarm run from its ledger records, after a pause or a crash. Use for "resume the swarm run", "continue the last run", "pick the swarm back up", or "a swarm session died".
runHow to start a sentinel-swarm run that takes a PRD to built, tested, reviewed code. Use for "run the swarm", "start sentinel-swarm on this PRD", "build this PRD with the swarm", or "take this PRD to done".
setupPrepares a host repo for sentinel-swarm. It writes .claude/sentinel-swarm.local.md, detects the test, build, and lint commands, builds the code graph, writes the role files in .claude/agents/, and checks that the repo is trusted. Use for "set up sentinel-swarm here", "prepare this repo for the swarm
statusPrints a sentinel-swarm run's phases, files, agents, locks, and open issues by reading .sentinel-swarm/ledger.db read-only. Use for "swarm status", "what is the swarm doing", "show the run tree", or "what is still open on this run".
swarm-protocolReference for sentinel-swarm. Loads when the conversation mentions sentinel-swarm, the swarm, or its roles (Oracle, Manager, Lead, Coder), and when the user asks what the swarm is, how it works, what the rubric dimensions are, what order a role calls the ledger in, or how to send a live run an instr
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives
1 command
Tenant-isolated AI teams that plan work, coordinate tasks, recall approved context, and return evidence-backed results
6 skills · 6 commands · 4 agents · 1 MCP server
Use Alibaba Open Code Review from local Codex.
2 skills
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
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.