mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Lean, opinionated workflow plugin. Confirm-only-when-ambiguous routing. Replaces obra/superpowers.
Plugin developersDevelopers from marketplace vrennat in vrennat/developersDevelopers. Commands read from the repo's manifest — 1 month 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.
onboardingUse when user mentions installing, configuring, or starting a project with developersDevelopers, or asks how to migrate from obra/superpowers. Surfaces the /bootstrap bootstrap command.
plan-hunterTournament-style planning that produces one polished plan from an idea by drafting from four lenses (MVP-first, risk-first, dependency-first, user-first) in parallel, scoring with four judges, and synthesizing the winner with grafted moves from runner-ups. Use when the user asks for a substantive im
systematic-debuggingUse when Claude observes a real error, test failure, or unexpected runtime output during execution. Forms hypothesis, runs minimal experiment, iterates to root cause before any fix.
verification-before-completionUse when about to claim work is complete, fixed, passing, or ready. Requires running the verification command and showing its output before any success claim.
/developersdevelopers:bootstrapBootstrap a project to use developersDevelopers. Creates docs/specs and docs/plans, detects legacy obra/superpowers paths, prints copy-paste commands for migration and templates. Idempotent. Named bootstrap (not init) to avoid colliding with Claude Code's built-in /init.
/developersdevelopers:brainstormIdea -> spec doc. Lean: clarifying questions only when ambiguous, default to recommendation, no per-section approval gates. Output to docs/specs/.
/developersdevelopers:debtAudit the repo for `dD:` routing-decision markers and print a ledger grouped by file, flagging entries that name no upgrade trigger. Use to review accumulated deliberate-shortcut debt left by /impl. Read-only; never edits or removes markers.
/developersdevelopers:implWorkhorse command. Spec file, ticket ID, or freeform description -> classified, routed, executed work. Confirms only when ambiguous. Auto-detects Linear MCP for ticket flows.
/developersdevelopers:modeSet how aggressively the workflow confirms before acting — cautious, default, or autonomous. Stored at .claude/dd-mode and read by the SessionStart hook and /impl. With no argument, reports the current mode.
/developersdevelopers:planSpec -> written implementation plan. Opt-in. Use only when you want to review a plan before executing. Most work skips this and goes straight to /impl.
/developersdevelopers:researchOpt-in, explicit /research invocation only. Measurable experimentation loop that sets up a .lab/ directory and runs THINK -> TEST -> REFLECT iterations. Does not auto-trigger on experimentation-shaped asks; use only when the user types /research.
/developersdevelopers:tddStrict RED-GREEN-REFACTOR scaffold. Opt-in. Use when you want full TDD discipline. Not an always-on behavior.
/developersdevelopers:trimDeletion-focused code review. Hunts only what to remove — over-engineering, dead flexibility, reinvented stdlib, speculative abstraction. Not correctness, not security (those are brutal-code-reviewer and adversarial-reviewer). Outputs one line per finding plus a net line-savings total.
adversarial-reviewerIndependent break-it review for high-stakes changes (auth, money, data, security, privacy, hard-to-undo). Reads source fresh and hunts the traps self-review misses. Use when /impl flags a change high-stakes, regardless of file count.
brutal-code-reviewerThorough code review for risky or architectural changes. Use when /impl touches >5 files, security-sensitive code, or shared infrastructure. Identifies real problems; does not nitpick style.
debug-geniusDeep bug investigation when validator fails or behavior is unexplained. Forms hypotheses, runs minimal experiments to verify, identifies root cause. Use when fast-impl's first attempt didn't work and the cause is not obvious.
fast-implExecute well-defined implementation tasks quickly and without deliberation. No architectural judgment, no scope expansion.
validatorRun quality gates after implementation. Typecheck, tests, lint. Verify requirements are met and check for obvious issues. Fast and mechanical. Use after fast-impl completes work, before any code review.
node "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.js"
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
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
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Claude Skills for Obsidian
6 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.