mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Curated agent skills for the local orchestrator. Original work, MIT-licensed, harness-agnostic.
Plugin agent-foundry from marketplace agent-foundry in youcisla/Agent-Foundry. Commands read from the repo's manifest — 12 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
agent-foundryAgent Foundry skills — MIT-licensed, original, quality-gated.
npm-publishPublish the Agent Foundry package to npm. Use when finishing a feature that should ship a new version, when scripts/install.js, skills/, agents/, or harness adapter files change, or when running the release flow.
npm-publish-automationCI/CD pipeline for npm publishing. Wires GitHub Actions to auto-detect npm-relevant changes and optionally publish on workflow_dispatch. Use after shipping features that touch the package/install/skills surface.
anti-slopKill generic AI patterns before they ship — filler prose, over-commenting,
api-designDesign REST or GraphQL APIs: resource modeling, URL conventions, error
automation-pickBefore automating a task, decide whether to automate. Decision tree based
bottleneck-gatingPhase plans by measured bottleneck, not by requested order. Each phase
budget-guardSet a hard spend ceiling before a paid loop starts, measure each call,
cache-identityUse when caching model results, latency, or artifacts: build a versioned key, bound the store, publish atomically, and never trust an unvalidated cache path.
constraint-then-solveBefore solving, restate the problem, list unknowns, and catalog every
context-optimizationKeep tool outputs small, sandbox large files, reference not repeat. Use
cron-troubleshootDebug a cron job that failed or didn''t run: timezone, drift, overlap,
e2e-test-strategyPlan an end-to-end test pyramid: which flows to E2E, which to integration,
engram-routingUse an approved, hash-keyed routing instinct to annotate a repeated prompt before the planner ranks skills. Use when a prompt pattern recurs and routing should reuse prior evidence.
execution-observabilityLog what ran, on which model, with which skill, at what cost, and whether
fallback-model-routingRoute around provider overload, rate limits, and timeouts without hiding
feedback-loopAfter shipping, set up the loop: instrument → measure → review weekly
judge-integrityUse when a model judges model output: separate judge failure from a low score, run deterministic checks first, gate escalation, and keep scoring separate from generation.
knowledge-extractTurn a repeatedly observed behavior into a skill draft with a trigger, procedure, anti-patterns, and checks. Use when the same correction or workflow has appeared at least three times.
landscape-firstBefore building anything in a competitive space, research 5-10 competitors:
measure-firstBefore planning any change, query live data (DB, API, analytics, logs)
plan-before-codeNo implementation without an agreed spec for non-trivial work. Brainstorm,
plan-then-actPlan first, then act. State the plan in one sentence before making the
prompt-disciplineEnforce the four coding rules — think before acting, minimum viable change,
pushback-when-wrongWhen the brief contradicts verified reality, push back with evidence.
quality-protocolThe routing protocol for non-trivial work: restate, catalog constraints, choose one discipline, execute in verified increments. Use before declaring a non-trivial task complete.
re-verify-findingsBefore executing any audit finding, claimed bug, or reported issue, re-verify
read-before-buildA plan or design document is an aspiration, not a specification. Before
session-closeoutBefore ending a session: reconcile changed files, update docs and changelog,
session-distillTurn a working session into a structured artifact covering changes, decisions, open questions, and reusable patterns. Use when wrapping up a session or handing work to another agent.
show-your-workPublish the evidence, rejected alternatives, and open uncertainties behind a non-obvious decision without exposing private reasoning. Use when explaining a decision or defending a result.
structured-output-contractWhen output feeds a program, define the schema before calling the model.
verify-firstEvery assertion about the codebase, product, or market is a hypothesis.
workflow-decomposeDecompose any workflow into a DAG: trigger → conditions → actions →
agent-memory-vaultStructured, file-backed memory for autonomous agents that must recall decisions and preferences across runs. Use when a workflow needs durable facts that outlive a single session.
agent-team-standardsLock a project's agent skill names and versions in a manifest, then report drift against that manifest. Use when a team needs reproducible skill versions across CI, cron, and developer machines.
autonomous-briefingAssemble a dated briefing from external research and dataset scripts, labeling unavailable sections instead of inventing content. Use when you want a repeatable morning scan rather than an open-ended research session.
book-to-skillTurn a book, PDF, or long article into a skill draft with reference chapters and a glossary. Use when converting long-form source material into a reviewable draft rather than a finished skill.
chrome-devtools-mcp-bridgeDrive a Chrome DevTools MCP server for browser automation, network traces, console capture, and performance audits. Use when a web page must be inspected or exercised through the DevTools Protocol instead of a headless script.
design-languageApply Apple-grade UI polish principles — restraint, coherence, intention,
funnel-pr-guardEvery PR that touches the front door must state which funnel step it
persistent-memoryDecide when a cross-session memory backend is worth adopting, then set capture, retention, redaction, and injection limits before enabling it. Use when an agent must recall decisions across sessions and the harness has no built-in memory.
sql-migration-trioEvery SQL migration = three files: up (forward DDL), down (reverse DDL),
token-compressionCompress large tool outputs, logs, and retrieved chunks before they crowd out context, while preserving the lines that carry decisions. Use when one tool result is large enough to dominate the working context.
bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh"
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
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
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
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.