mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Expert AI agents (Architect, Backend, Frontend, QA, Code Reviewer, Debugger) and skills (TDD Orchestrator, Scope Refinement, Grumpy Tech Lead, Project Memory) implementing Harness Engineering for disciplined software development.
Plugin harness-kit from marketplace harness-kit in romabeckman/harness-kit. Commands read from the repo's manifest — 2 days ago.
adversarial-qaAutonomous Adversarial QA agent. Reads machine-readable specs and code to execute edge-case and security testing, returning a JSON verdict.
autonomous-orchestratorSovereign loop manager. Handles file initialization, feature lifecycle tracking, and recursive TDD-Validation-Optimization cycles. Strictly delegates all technical tasks to sub-agents.
harness-evaluatorHarness performance evaluator. Reads all execution traces in docs/harness-history/traces/, computes composite scores per skill_chain, identifies the Pareto frontier of best harness configurations, and recommends the optimal chain for the next session. Run periodically or on demand to guide harness o
harness-tracerExecution trace recorder. Captures what happened during a skill session and persists structured logs to docs/harness-history/traces/. Enables retrospective analysis and harness optimization via harness-evaluator and meta-harness.
memory-contextInitialize and maintain a local multi-project Harness Memory cache, then use Harness Memory MCP efficiently for evidence-backed context, relationships, environment comparisons, and change impact.
meta-harnessAutonomous Meta-Harness proposer. Reads the full harness history filesystem, diagnoses failure patterns, proposes a targeted improvement, stores the candidate, and outputs a JSON decision.
pbb-designDesigns a Product Backlog using the Product Backlog Building (PBB) methodology from an initial product or feature scope.
project-memoryOrchestrate sequential creation, updates, and evidence-backed consolidation of project documentation in docs/ and targeted root README.md edits. Use for documentation changes, scoped audits, and incremental memory maintenance.
qa-orchestratorPlan and run evidence-backed acceptance tests with the Harness Kit `hrns qa` CLI. Use when the user wants to install or use `@romabeckman/hrns`, define QA scope and scenarios, execute runtime QA against an application, or summarize a QA run. Do not use for unit-test-only requests or static code revi
read-ui-prototypeUI/UX prototype reader. Analyzes interface prototypes (screens, Figma links, images, frames) and translates them into a structured, semantic, LLM-actionable frontend specification — without writing any code or inventing visual values. Output targets the developer-frontend agent.
scope-refinementDDD Scope Refinement Orchestrator — coordinates all Domain-Driven Design phases from business discovery to test scenario specification and machine-readable exports. Supports both interactive and autonomous headless execution.
tdd-orchestratorOrchestrates development workflow using Test-Driven Development (TDD) methodology. Coordinates between testing and development skills to ensure quality implementation. Guides the process from test creation to implementation, validation, and documentation updates, strictly following the project-speci
the-grumpy-tech-leadSenior Tech Lead and Software Architect specialized in technical code review with a focus on systemic impacts, security, performance, scalability, etc. Acts as a mentor using Socratic questioning to identify N+1 risks, memory leaks, race conditions, SOLID/DRY violations, and production failures with
ctoChief Technology Officer for business design and autonomous delivery governance. Routes product discovery through pbb-design before technical refinement or implementation.
developer-backendSenior Backend Developer specialized in TDD, API design, database modeling, security, and performance. Use for writing backend code (APIs, services, workers), fixing server bugs, implementing business logic, and backend testing.
developer-debuggingSystematic Investigation and Debugging Specialist. Uses an evidence-driven workflow and the "5 Whys" to identify the root cause of bugs before implementation.
developer-devopsSenior DevOps/Platform Engineer specialized in CI/CD pipelines, infrastructure as code, containerization, observability, and release automation. Use for pipeline implementation, Dockerfile/Compose/Helm authoring, IaC (Terraform, Pulumi), and deployment automation tasks.
developer-frontendSenior Frontend Developer specialized in TDD, UI/UX implementation, accessibility, and performance. Use for writing frontend code (React, Vue, CSS, HTML), fixing UI bugs, implementing designs, and frontend testing.
developer-qaSenior QA Engineer specialized in test strategy, automation, exploratory testing, and quality gates. Use for implementing test suites, writing E2E/contract/load tests, auditing test coverage, and establishing quality standards across the pipeline.
harness-qaAdversarial QA specialist for autonomous or independent review. Identifies concrete security, boundary, concurrency, integration, and behavioral defects and returns a structured JSON verdict.
harness-tech-leadSenior Tech Lead and Software Architect specialist for the autonomous-orchestrator pipeline. Evaluates systemic risks, scalability, security design, resilience, architecture boundaries, and maintainability. Returns a structured JSON verdict for Phase C Decision Gate evaluation.
meta-harness-agentMeta-Harness proposer agent. Reads the harness history filesystem (docs/harness-history/traces/, candidates/, pareto-frontier.md), diagnoses failure patterns across sessions, and proposes targeted improvements to existing skills. Implements the automated harness search loop described in the Meta-Har
software-architectSenior Software Architect specialized in DDD, system design, technical refinement, and technical decision-making. Use for architecture decisions, scope refinement, design refinement, and technical quality gates.
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
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
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
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.