mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
A light agent-team method: three tracks, thirteen roles, three human touchpoints per feature
Plugin gtm from marketplace gentleteam in MorganKryze/GentleTeaM. Commands read from the repo's manifest — 2 days ago.
brainstormBrainstorm a topic with the GTM team (three stances, methods, a roundtable) into a note for the spec. Use when the human has an idea, not yet a request.
brief-meRe-present a GTM artifact at the detail level the human picks, or dig into it with a method. Use when the human wants one explained or challenged.
deliverDeliver an approved GTM plan: tasks with reviews and correction rounds, then the final review. Use when /gtm:plan is done.
designGTM design loop: mockups scored against the design guideline, then shown for approval. Use when a Feature changes screens.
gtmGentleTeaM entry point: picks the track and routes, or proposes the next command. Use when starting GTM work or unsure what to do next.
initSet up GTM in a project: brief, config, team settings and guidelines from the codebase, after a short interview. Use when a project has no GTM root, or to refresh it.
pauseStop the current GTM run cleanly, keep its work, and write how to resume it.
planWrite the GTM task plan from an approved spec with the architect. Use when the spec is approved.
researchWrite a sourced state of the art of a domain with the researcher, and show its proposals as cards.
retroTurn a shipped GTM branch into ledger lessons and guideline proposals; close resolved minors. Use when a branch has shipped.
shipShip a GTM branch: gate, PR text, then push, merge, tag or release only on the human's go. Use when /gtm:deliver is ready.
specWrite a GTM spec with the architect and present its summary for approval. Use when a Feature or Milestone needs one.
statusShow where the current GTM run stands from NOW.md, rebuilt from the files when missing or stale.
tuneRe-tune GTM team settings (roles, effort, specialists, gates, companions, reflexes, stealth) from the ledger, as decision cards. Use when the team feels slow, costly or blind.
analystGTM analyst: clarifies a request and proposes the track; drafts the setup at init. Read-only on code.
architectGTM architect: writes the spec and the task plan, replaying risky tasks in a scratch clone.
art-directorGTM art director: gathers references and proposes three directions before any mockup.
data-reviewerGTM data-integrity reviewer for diffs on its configured paths. Read-only.
design-criticGTM design critic: scores a mockup against the design guideline. Read-only.
designerGTM designer: draws PNG mockups from a brief and the design guideline.
final-reviewerGTM whole-branch reviewer before the go; triages deferred minors. Read-only.
implementerGTM implementer: one plan task or one list of findings, test-first, gated, committed.
release-qaGTM release QA: runs the scripted journey on the live instance after deploy.
researcherGTM researcher: writes a sourced state of the art of a domain and proposes improvements as cards.
reviewerGTM code reviewer for one task: spec compliance, then quality. Read-only.
security-reviewerGTM security reviewer for diffs on its configured paths. Read-only.
ux-qaGTM UX and accessibility QA: captures touched screens and compares with the mockup.
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
Use Alibaba Open Code Review from local Codex.
2 skills
Investigate incidents, review code and execute UAT for release readiness, scan code for vulnerabilities, and run penetration tests with AWS DevOps Agent and AWS Security Agent.
13 skills · 9 commands · 1 MCP server
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 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.