CommunityResearch & Data Analysisgithub.com

iamk3nnyt/claude-skills

Turns a feature idea into a one-page spec covering problem, audience, MVP scope, non-goals, numbered Given/When/Then acceptance criteria, affected routes, data and emails, and open questions. Use when the user says "brief", "spec this", "scope this" or "what would it take", or before starting a feature whose scope is unclear.

What is claude-skills?

claude-skills is a Claude Code agent skill that turns a feature idea into a one-page spec covering problem, audience, MVP scope, non-goals, numbered Given/When/Then acceptance criteria, affected routes, data and emails, and open questions. Use when the user says "brief", "spec this", "scope this" or "what would it take", or before starting a feature whose scope is unclear.

Works with✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/iamk3nnyt/claude-skills/tree/HEAD/skills/brief

Installed? Explore more Research & Data Analysis skills: affaan-m/uspto-database, affaan-m/scholar-evaluation, affaan-m/literature-review · View all 6 →

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

brief

Feature: $ARGUMENTS

Ground it first (silently)

  • Read the repo's CLAUDE.md and the memory entries for this project. Skim the routes, schema and email templates the feature touches. Specs cite real file paths and existing fields.
  • Interview only if a decision would change the scope. Ask one question at a time using AskUserQuestion with a recommended option, and keep it to 3 questions at most. Anything else becomes an assumption in Open questions.

House rules for scope

  • MVP means the conventional minimum built with existing fields and components. "Like any e-commerce" means the standard flow, not a platform.
  • Never add components, settings, admin screens or analytics that weren't asked for. List them under Non-goals instead.
  • Partner or API features: "API key" usually means a tenant id in env, not a developer portal.
  • Respect project constraints from CLAUDE.md/memory (e.g. "no schema changes"). Flag anything that would break one.

Template

# <Feature>: brief
**Problem:** one or two sentences, the user's pain, not the solution.
**For:** who, and how many if known (cite the query or source).
**MVP:** 3–6 bullets, each shippable and observable.
**Non-goals:** what we're explicitly not doing now.
**Acceptance criteria**
1. Given <state>, when <action>, then <observable result>.
2. … (each one testable via flow-check, smoke or a unit test)
**Touches:** routes · tables/fields (existing ones first) · emails · env/secrets · third parties
**Risks:** money, legal/GDPR, deliverability, SEO (noindex/canonical), i18n
**Open questions:** numbered; each with my default if unanswered

Output

  • In chat by default. Write docs/briefs/<slug>.md only if asked.
  • One-sentence lead ("Brief below: N criteria, M open questions"), then the brief. Nothing after it.

Exit criteria

  • Every acceptance criterion is observable and maps to a check (flow-check step, smoke expectation, or test).
  • Nothing in MVP that wasn't asked for or isn't strictly required for what was asked.
  • Open questions each have a default, so building can start without waiting.

Individual skills in this repo

This repo contains 4 individual skills — each has its own dedicated page.

iamk3nnyt/claude-skills

Checks UI copy across locales by comparing key parity between next-intl message catalogs and in-code sv/en COPY objects, finding placeholder and array mismatches and words from the other language leaking in (the "och" in English bug), then manually reviewing claims against terms and pricing and the project's banned phrases. Use after editing copy or translations, before shipping a page with new text, or when asked to proofread or check translations.

iamk3nnyt/claude-skills

Applies an agreed visual direction to a page or component by reusing existing components first, then verifies every width and dark mode with the headless-Chrome audit plus a before/after pixel diff, and reviews against Refactoring UI, Nielsen and WCAG 2.2. Use when asked to redesign, restyle, polish or "make it look like the reference", after design-ref or when the direction is already clear.

iamk3nnyt/claude-skills

Extracts the visual system from a reference site or pasted HTML (colour roles, type scale, spacing scale, radii, shadows, button/card/eyebrow anatomy, tone) and maps it onto the current project's existing tokens as a short token table. Use when the user shares a reference ("make it look like <site>", "in this style", a URL or HTML paste) before a redesign.

iamk3nnyt/claude-skills

QAs a project's transactional and digest emails by rendering every template without DB or network, screenshotting at 600 and 375 px in light, dark and images-off, and checking for placeholder leaks (undefined, NaN, {{…}}), preheader, unsubscribe, alt text, absolute links, Outlook-safe buttons, viewport meta and Gmail's 102 KB clip. Use when email templates change, before sending a campaign, or when asked to check how emails look.

Related Skills