mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Claude cannot write code before you approve the intent. Gated plan, TDD, review and check for AI written code.
Plugin temper from marketplace temper in galando/temper. Commands read from the repo's manifest — yesterday.
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.
context-engineeringHierarchical context loading for AI coding agents — load what you need, defer what you don't
grill-meSocratic challenge mode — stress-test plans and designs with adversarial questions, one at a time
source-driven-developmentVersion-aware, source-driven development — fetch official docs before writing framework code
teach-meComprehension companion — incrementally teach the user every change, confirm mastery before advancing, and quiz to close gaps. Keeps the human engaged across all phases.
temper-coreTemper core: stack detection, quality gates, blast radius, review memory
/temper:buildBuild an approved plan: starts /temper, or takes up the active run, at Build
/temper:checkValidate the changes: starts /temper, or takes up the active run, at Check
/temper:designDesign a medium or complex feature: starts /temper, or takes up the active run, at Design
/temper:fixRoot cause analysis + structured fix
/temper:initOne-command setup: config + .temper/ scaffold + the commit gate (idempotent)
/temper:intentCapture an idea as a draft intent.md — the artifact that starts the pipeline, without starting it
/temper:packManage quality packs: view, toggle, quick-create launchers, configure links & phases, print the guardrails hooks to add or remove
/temper:planPlan a feature: starts /temper (Intent comes first), or takes up the active run
/temper:reviewReview the changes: starts /temper, or takes up the active run, at Review
/temper:statusShow quality metrics, learning loop, and observability dashboard
/temper:temperUnified SDLC command: intent → plan → design? → build → review → check → commit, gated by the temper CLI
temper-acceptanceTemper's acceptance tests, written from the approved intent before Build, by an agent that writes no code. Invoked by the /temper orchestrator, never directly by a user.
temper-build-taskTemper's grouped Build task agent — implements one task, or a chain of tasks in order, with TDD, each inside its own task worktree. Launched by the /temper orchestrator, never directly by a user.
temper-buildTemper's Build brief — the fix pass after the grouped Build, when Review or Check loops back to Build. Invoked by the /temper orchestrator, never directly by a user.
temper-checkTemper's Check stage — stack-aware validation pipeline (compile, test, coverage, lint, security). Invoked by the /temper orchestrator, never directly by a user.
temper-designTemper's Design stage — system design for medium/complex features. Invoked by the /temper orchestrator, never directly by a user.
temper-fixTemper's Fix stage — regression test (RED) → minimal fix (GREEN) → blast radius, for /temper:fix. Invoked by the /temper:fix orchestrator, never directly by a user.
temper-intentTemper's Intent stage — state the problem, success criteria, and constraints BEFORE any exploration or architecture spends tokens. Invoked by the /temper orchestrator, never directly by a user.
temper-pipelineTemper's Pipeline stage — reads the pull request's checks after Commit, records the result and proposes a fix; it never pushes. Invoked by the /temper orchestrator, never directly by a user.
temper-plan-reviewTemper's fresh review of a plan, before the plan gate. A reader with no context checks that each task can be built as written. Invoked by the /temper orchestrator, never directly by a user.
temper-planTemper's Plan stage — full codebase exploration, intent + BDD scenarios + blast radius. Invoked by the /temper orchestrator, never directly by a user.
temper-rcaTemper's RCA stage — multi-hypothesis root cause analysis for /temper:fix. Invoked by the /temper:fix orchestrator, never directly by a user.
temper-reviewTemper's Review stage — confidence-scored defect + intent review of changed files. Invoked by the /temper orchestrator, never directly by a user.
bash "${CLAUDE_PLUGIN_ROOT}/scripts/guards/stage-marker.sh"
python3 -I "${CLAUDE_PLUGIN_ROOT}/scripts/guards/block_stdin_wait.py"
bash "${CLAUDE_PLUGIN_ROOT}/scripts/guards/verify-stage-gate.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
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.
25 skills · 4 agents
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Use the JFrog Platform from Claude Code: Artifactory repos and artifacts, security findings and exposures, Catalog package safety and downloads, workflows across the SDLC, and platform administration.
7 skills · 1 MCP server · 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.