mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Repository context OS, AI agent harness, LLM evals, test governance, CI pipelines, and product readiness audit. Audit, plan, then apply.
Plugin skills from marketplace nagmudit in nagmudit/skills. Commands read from the repo's manifest — 1 month ago.
agent-harnessAudit the harness around an AI agent or LLM feature and then build what is missing — input validation, prompt registry, tool-call safety, output validation, tracing, guardrails, human-in-the-loop, cost controls. Use when the user says "audit my agent", "make my agent production ready", "my agent is
ci-pipelineRead a project, work out what its pipeline has to do, then write CI that actually runs green — jobs, caching, service containers, matrices, secrets, and branch protection, verified by running it rather than assumed. Use when the user says "set up CI", "add GitHub Actions", "my build is failing in CI
contextBuild and maintain a vendor-neutral context system inside a repository so any coding agent — Claude Code, Cursor, Copilot, Codex — can pick up the work without being re-briefed. Use when the user says "set up AGENTS.md", "document this repo for AI agents", "I keep re-explaining my project", "I'm swi
evalsBuild and run evals for anything an LLM produces — a golden set drawn from real failures, assertions that survive paraphrase, a judge only where cheaper checks cannot reach, and a CI gate that fires when a prompt, model, or tool schema changes. Use when the user says "add evals", "my prompts keep re
product-auditWork out what a product actually is from its code, then audit whether it can survive production — critical workflows traced end to end, security, data integrity, reliability, observability, and the gaps between what the code claims and what it does. Use when the user says "are we production ready",
test-governanceWork out what a repository actually needs to test, then build it — risk-ranked user and system journeys, a machine-readable test manifest, the missing suites, CI pipelines, and merge/release gates. Use when the user says "we have no tests", "what should I test", "set up a test strategy", "our tests
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
Long-term semantic memory for Claude Code, powered by OpenViking
5 skills · 1 command · 1 MCP server · hooks
Connect providers and targets, write eval suites, and set up or run red team scans with promptfoo
4 skills
Automates browser interactions for web testing, form filling, screenshots, and data extraction
1 skill
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.