architecture
claudeDesign interfaces, record decisions, review structure, and plan migrations.
7 skills
Turn ideas into specs, test assumptions, and anticipate failure.
Plugin planning from marketplace skillsmith-marketplace in smithdak/skillsmith. Commands read from the repo's manifest — 17 days ago.
falsification-reviewFalsifies a consequential conclusion before it is presented: strongest counterargument first, the crux, and what evidence would overturn it. Use when about to endorse a recommendation, estimate, or plan, or the user asks "should we", "is this the right call", or "sanity check this decision". Not for
feature-specSynthesizes the conversation so far into a build-ready feature spec or PRD, never by re-interviewing. Use when the user says "turn this into a spec", "write up what we discussed as a PRD", "capture this thread as a spec", or wants a feature discussion made buildable. Not for architecture documents (
grillingInterrogates a half-formed idea or plan until every branch resolves into a decision or an explicit open item, before building starts. Use when the user says "grill me on this", "poke holes in this idea", "ask me the hard questions", or has a vague idea they are about to act on. Not for testing a con
premortemRuns a premortem on an agreed plan: assumes it failed, narrates why, and turns the top risks into warning signals and kill triggers. Use when the user says "run a premortem", "stress-test this rollout", "imagine it's a year on and this went badly", or is about to start a migration. Not for testing a
second-order-effectsTraces a proposed policy, pricing, or product rule past its first-order intent: how affected actors adapt, who games it, and where the equilibrium settles. Use when the user says "unintended consequences", "play this out", "who will game this", or is about to ship a rule people will adapt around. No
falsification-reviewerAdversarial reviewer for document-scale deliverables: specs, estimates, plans, statements of work. Use proactively before presenting any deliverable the user will act on — maker-checker separation, so the author's own framing does not survive review unexamined.
Design interfaces, record decisions, review structure, and plan migrations.
7 skills
Understand code, diagnose bugs, and develop with meaningful tests.
6 skills
Write agent instructions and skills with clear scope and triggers.
4 skills · 1 command
Write work items, check handoffs, and guide manual setup.
4 skills · 1 agent
Write READMEs, clarify diagrams, and organize technical documentation.
4 skills
Build, critique, and refine interfaces; verify behavior in a browser.
4 skills
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
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.