mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Full lifecycle plugin: specs, TDD plans, forge loop, lint gates, and coverage matrix.
Plugin superspec from marketplace superspec-dev in anupam20sep/IRA. Commands read from the repo's manifest — 27 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
superspec-architectUse when designing the technical solution architecture, translating requirements into decisions, data models, and contracts. Follows SuperSpec's unified design template (Technical Context, Architecture, Decisions, Data Model, Contracts) and produces design.md.
superspec-exploreUse when exploring ideas, requirements and design before implementation. Helps turn ideas into fully formed designs and specs through natural collaborative dialogue.
superspec-fixUse for targeted bug fixes that do not need a full spec lifecycle. Reproduces with a failing regression test, applies a minimal patch, skips spec.md/design.md/plan.md, and hands off to superspec-ship for validation.
superspec-forgeUse when you have an execution map or task plan ready to implement — runs the autonomous forge loop that dispatches fresh implementer and reviewer subagents per task, tracks state via the forge-loop state machine (next-task/record-task-result/forge-status), and escalates stuck tasks instead of retry
superspec-ingestUse when bootstrapping a spec from existing documentation or code rather than greenfield exploration. Extracts functional requirements with provenance, flags source conflicts, writes sources.lock, and hands off to superspec-scope.
superspec-initUse once per repository to bootstrap SuperSpec. Runs the init CLI, asks lite vs full mode, and creates constitution.md, specs/, and .superspec/ at the repository root.
superspec-planUse when you have a spec or requirements for a multi-step task, before touching code — writes comprehensive TDD plans with full task decomposition and FR traceability
superspec-programUse when coordinating multiple spec workstreams in one repository. Maintains program.md at the repo root with a backlog table and Open Decisions, with per-row ownership for safe concurrent edits.
superspec-refineUse when your specification contains open questions or [NEEDS CLARIFICATION] markers. Asks up to 5 targeted clarifying questions, collects answers, and writes them back into spec.md to resolve ambiguities before moving to architecture.
superspec-routeUse when transforming a task plan into a parallelizable execution schedule with model routing, windowing, and verification gates
superspec-scopeUse when you have a brainstormed design and need to formalize it into a numbered, testable specification. Generates a spec.md with functional requirements (FR-###), success criteria (SC-###), and prioritized user stories with acceptance scenarios.
superspec-shipUse when implementation is complete, validation has passed, and you need to decide how to integrate the work - runs SuperSpec's clean-validation gate, then guides completion of development work by presenting structured options for merge, PR, or cleanup
superspec-statusUse to get a program-wide or repo-wide status view. Reads program.md, infers lifecycle stage per spec from artifacts, calls forge-status for in-flight specs, and renders a single consolidated status table.
superspec-validateUse when about to claim a feature is complete and ready for release — runs the actual verification commands (coverage matrix, plan linting, constitution compliance, execution gates) and confirms output before allowing completion claims; evidence before assertions always.
superspec-worktreeUse when starting plan or forge work that needs isolation from the current workspace — creates isolated git worktrees with smart directory selection, safety verification, and baseline tests; pairs with superspec-ship for cleanup
using-superspecUse when starting any conversation - establishes how to find and use SuperSpec skills, requiring skill invocation before ANY response including clarifying questions
implementerUse when dispatching a fresh subagent to implement exactly one task from a SuperSpec plan.md, with zero prior context, following red-green-refactor TDD.
spec-reviewerUse when reviewing a SuperSpec spec.md for quality — every FR testable, every user story independently demonstrable, no lingering ambiguity.
task-reviewerUse when reviewing one completed SuperSpec task's implementation against its brief and the constitution — spec compliance and code quality verdicts.
superspecruns: npx -y @superspec-dev/[email protected] mcp
echo 'SuperSpec: invoke the using-superspec skill before any task — explore/ingest → scope → refine → architect → plan → route → forge → validate → ship.'
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.