mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Duo skills (design, discuss, forge, prod-ready, research, review, testplan) for symmetric Claude+Codex convergence. Solo skills (Claude-only, explicit `solo` keyword): solo-testplan authors an e2e test plan tree; solo-runtestplan executes one or more test plan trees against a generated no-external-ports docker stack with append-only Bugs.md / Log.md ledgers and autonomous infra+observation recovery. linked-testplan is the shared rulebook for both testplan skills.
Plugin yd from marketplace yd in yuridevx/yd-skills. Commands read from the repo's manifest — 1 month ago.
duo-designSymmetric Claude+Codex convergence on a system/architecture design, producing Duo/Design-<slug>/Result.md. Direct codex CLI only - no /codex:rescue, no plugin internals; depends only on `codex` on PATH. Pins gpt-5.5 + xhigh reasoning + live web search + yolo (--dangerously-bypass-approvals-and-sandb
duo-discussSymmetric Claude+Codex open-ended convergence catch-all - decisions, brainstorming, tradeoff analysis, planning conversations, post-mortems, or questions that don't fit duo-design / duo-research / duo-review / duo-forge. Produces Duo/Discussion-<slug>/Result.md. Direct codex CLI only - no /codex:res
duo-forgeMeta-skill - uses the duo convergence protocol to design a new duo-<name> skill for a requested domain. R1 evaluates three gating criteria (pattern recurs across missions / artifact has stable shape / domain has definable investigation procedure); if both sides converge on REJECT, writes only a reje
duo-prod-readyProduction-readiness refactoring through Claude+Codex convergence that WRITES CODE. Modifies the working tree. Runs build+test. Commits per cycle. Direct codex CLI only - no /codex:rescue, no plugin internals; depends only on `codex` on PATH. Pins gpt-5.5 + xhigh reasoning + live web search + yolo.
duo-researchSymmetric Claude+Codex convergence on a research deliverable, producing Duo/Research-<slug>/Result.md. Web access central on both sides. Direct codex CLI only - no /codex:rescue, no plugin internals; depends only on `codex` on PATH. Pins gpt-5.5 + xhigh + live web + yolo. TRIGGERS ONLY on explicit "
duo-reviewSymmetric Claude+Codex code-review convergence on a branch, PR, diff, commit, or paths, producing Duo/Review-<slug>/Result.md with file:line-grounded findings + verdict (PASS / PASS_WITH_GAPS / FAIL / BLOCKED). Read-only - no code edits. Direct codex CLI only - no /codex:rescue, no plugin internals;
duo-testplanSymmetric Claude+Codex authoring of an e2e test plan tree for multi-repo workspaces using per-unit duo authoring plus step-by-step structured diff convergence. Six phases - P1a scope file discovery, P1b per-service scope, P2 local flow refinement, P3 cross-app discovery, P4 cross-app flow refinement
linked-testplanRulebook for e2e flow-grain test plan authoring. Owns page shape, coverage vocabulary, scenario policy, mocks policy, and the 21-rule refinement checklist. Companion to the `duo-testplan` (Claude+Codex) and `solo-testplan` (Claude-only) orchestrators, which both load this rulebook into every authori
solo-runtestplanClaude-only executor for e2e test plan trees authored by `solo-testplan` / `duo-testplan` (or any tree following the `linked-testplan` page shape). Aggregates one or more test plan trees, generates a no-external-ports docker-compose stack, brings it up, and runs every HAPPY/NEGATIVE scenario via CLI
solo-testplanClaude-only counterpart to `duo-testplan` — same e2e test plan tree (`Solo/TestPlan-<slug>/Result.md` plus `test-plan/.../flows/<flow-id>.md`) authored by Claude alone, no codex peer. Five named phases: service-scope, local-flows, cross-app-survey (in-session mechanical reconciliation), cross-app-fl
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
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
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
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.