123 skills · sorted by relevance
Model component behaviour as explicit states, events, and transitions. Use when a component has many interacting states that must be exhaustive. For the feel and feedback of a single interaction, use `micro-interaction-spec`.
The English summary is being prepared. Showing the original description.
Design an A/B experiment — hypothesis, variants, primary metric, and sample size. Use when a change can be measured quantitatively at scale. For observing behaviour qualitatively, use `test-scenario`.
The English summary is being prepared. Showing the original description.
Design a diary study — prompts, cadence, duration, participant criteria, and analysis frame. Use when behaviour unfolds over days or weeks. For a single-session study, use `usability-test-plan`.
The English summary is being prepared. Showing the original description.
Read funnels, retention curves, and event data as a designer — separating a design problem from a tracking artefact. Use when handed product data you did not design and asked why people drop off. For choosing what to measure, use `metrics-definition` (ux-strategy); for running a controlled test, use `a-b-test-design` (prototyping-testing).
The English summary is being prepared. Showing the original description.
Build a Says, Thinks, Does, Feels map for one user or segment. Use when sharing user understanding quickly. For a composite archetype with goals and behaviours use `user-persona`; for cross-session themes use `affinity-diagram`.
The English summary is being prepared. Showing the original description.
Design unbiased survey instruments — question wording, scales, and sampling — to measure attitudes at scale. Use when you need quantitative breadth. For behavioural experiments, use `a-b-test-design` (prototyping-testing).
The English summary is being prepared. Showing the original description.
Write the implementation handoff — measurements, behaviours, assets, states, and edge cases. Use when engineering picks up the work. For verifying the result afterwards use `design-qa-checklist`; for reusable library components use `component-spec` (design-systems).
The English summary is being prepared. Showing the original description.
Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use `empathy-map`; for motivation framing use `jobs-to-be-done`.
The English summary is being prepared. Showing the original description.
Author SVG figures for Grida docs — diff-able, version-controlled vector diagrams embedded in doc pages instead of screenshots. Provides reusable primitives (selection chrome, size badges, anchor pins, resize cursors, click ripples), color/typography tokens, a starter template, and finished examples to crib from. Canvas user docs (docs/editor/) are the first consumer; the kit is meant to generalize to any product's docs. Use when drawing diagrams that explain UI behaviour — gestures, alignment, before/after states — that a screenshot alone can't capture. Trigger phrases: "svg diagram", "draw a figure", "visual for docs", "explain this gesture visually", "before/after diagram".
The English summary is being prepared. Showing the original description.
Land the winning experiment from an evo run as a clean, mergeable change -- open a PR when the repo has a remote, otherwise merge into the working branch. Distills the best-scoring experiment down to the minimal diff that reproduces its behaviour, shaped for the qualities a maintainer merges on (scope discipline, test integrity, style adherence), then attaches an advisory mergeability report. Use when the user invokes /evo:ship, asks to land/merge/ship the best result, or wants to turn a finished optimization into a pull request.
The English summary is being prepared. Showing the original description.
Write a PRD for an AI-powered feature, covering the things normal PRDs miss. Use when asked to spec an AI/LLM feature, write a PRD for a feature that uses a model, or plan an AI capability (assistant, summarizer, generator, classifier). Produces an AI feature PRD — problem & UX of uncertainty, model approach, eval criteria, guardrails, fallback behaviour, the data flywheel, and cost/latency budget.
The English summary is being prepared. Showing the original description.
Test-driven development for behaviour a unit test cannot reach, by writing the expectation against the running app before writing the code. Declare the consequence first, watch it fail, implement, watch it pass. Use when building a user-facing feature, when the user asks for TDD on UI or full-stack work, when a unit test cannot express the outcome that matters, or when you want a red-green loop that runs against the real app instead of mocks.
The English summary is being prepared. Showing the original description.
Scaffold a first eval suite for an agent: mine real failures into cases, write behavioural checks over traces, and generate the runner. Use when the user wants evals, regression tests for an agent, a golden set, or asks how to know a prompt/model change did not break things. Do NOT use for a single task's done-check (goal-test) or for auditing context (context-audit).
The English summary is being prepared. Showing the original description.
Walk through a live web app AS a real user to find usability + behavioural bugs that static reviews miss. REQUIRES proof of interaction (typing, clicking, sending, observing) before any verdict — a sweep that didn't interact terminates with verdict 'Incomplete'. Walks threads, exercises every element, runs the multi-pane stress matrix, visual polish sweep, component perfection checklist, automated a11y (axe-core), pragmatic performance budget (LCP/CLS/INP), scenario battery (11 scenarios), and stress recipes including the real-flavour data battery. Hard gates: console errors/warnings = 0, network 5xx = 0, layout collapse = 0, axe Critical/Serious = 0, perf budget green. Audit-the-audit meta-check rejects rushed reports. Each finding has reproduction steps, evidence path, and suspected code location. Trigger with 'ux audit', 'walkthrough', 'qa sweep', 'audit the app', 'dogfood this', 'check all pages', 'find what's broken', 'stress the UI'.
The English summary is being prepared. Showing the original description.
Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots. Triggers: 'design review', 'does this look good', 'review the design', 'check the layout', 'is this polished', 'visual review', 'design audit', 'make it look better', 'it looks off'.
The English summary is being prepared. Showing the original description.
The consumer panel. Spins up a swarm of buyer sub-agents (default 100, --quick for 20) trained on the user's target customer, each with a different income, age, buying behaviour and objection, shows every one the same pitch, and runs the business through 100 buyer scenarios to see who buys, who doesn't, and why. Tallies the answers into buy rates by segment, the reasons people pass in their own words, what would flip a no, and price answers for founder-pricing. Use when the user says "would people buy this", "test it on customers", "run the consumer panel", "simulate buyers", "who is my customer", or "validate demand".
The English summary is being prepared. Showing the original description.
Design a restorative practice protocol for addressing harm, rebuilding trust, and restoring relationships. Use when managing conflict, behavioural incidents, or relationship breakdown between students.
The English summary is being prepared. Showing the original description.
Design a multi-round questioning sequence for interrogating AI chatbot answers, tracking how responses shift and distinguishing genuine updates from sycophantic capitulation. Use when teaching students to probe AI critically.
The English summary is being prepared. Showing the original description.
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified", "is this actually done", "maker checker", "second pair of eyes on this change". Not for prose, docs or typo edits.
The English summary is being prepared. Showing the original description.
Drive the real Course Video Manager web app in a browser and capture proof of what it did. Use to verify a change before opening a PR, to reproduce a reported UI bug, to see what a page actually renders, or to capture a screenshot of app behaviour. Runs on a per-run, writable clone of a local copy of Matt's data by default — click anything that mutates; production is never written to.
The English summary is being prepared. Showing the original description.
Spring Boot best practices and patterns. Use when creating controllers, services or repositories, or when the user asks about Spring Boot layering, wiring, configuration or exception handling. For JPA and Hibernate behaviour, use jpa-patterns instead.
The English summary is being prepared. Showing the original description.
Use when a bug, failing test, or unexpected behaviour needs investigation, especially across sessions or context resets. Isolates it in a debugger subagent with persistent .planning/debug state, unlike skills/systematic-debugging.
The English summary is being prepared. Showing the original description.
Pointer to the upstream skill for behavioural guidelines that reduce common LLM coding mistakes, installed from upstream.
The English summary is being prepared. Showing the original description.
Converges an underspecified request into an IntentSpec: looks up what sources answer, asks only what they cannot, halts instead of guessing, checks delivery against the spec. Use when a request to implement, add, change, fix or configure leaves a decision open — scope, approach, failure behaviour, what done means — contradicts itself, reads two ways, or rests on a premise sources rule out. Silent on a fully stated request its sources do not contradict; not for explaining existing state.
The English summary is being prepared. Showing the original description.