code-kit
claudePlan → Confirm → Implement → Verify discipline for software work: hooks, skills, review agents and a CLAUDE.md ruleset.
40 skills · 6 agents · hooks
Brief → Direction → Build → Audit for interface work: a DESIGN_MAP.md direction file, slop and motion hooks, design skills and review agents.
Plugin design-kit from marketplace tansuasici in tansuasici/claude-plugins. Commands read from the repo's manifest — 2 days 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.
brand-methodMake or critique a brand identity (logo, type, palette) as 1–4 sets built together from one brief. Uses a one-message intake, one mechanism per set, decision axes, differentiation from real competitors, a reflex test against AI defaults, then a checkpoint where the user picks. Never picks for the us
design-briefFill DESIGN_MAP.md from the user and the project before any design work. Covers what the product is, who it serves, the one job of the screen, the brand that already exists, real competitors, the assets that actually exist, and a subject inventory of 8–12 things only this product has. Asks only what
directionWrite the five-line design direction (Product, Character, World, Moments, Signature) from the subject itself, plus the idea sentence, the competitor test, the page argument and the token set that follows. Then stop for the user's agreement before any CSS is written.
interface-checkCheck UI code against the interface guidelines (keyboard, targets, forms, state and URL, feedback, touch, layout, content and accessibility, performance, dark mode, hydration, design details) and report file:line findings with severities. Use before shipping a form, dialog, navigation, list or any i
logoMake, refine or critique a logo mark, wordmark or app icon as real SVG files. Three directions that differ in idea or silhouette, the user picks, then build in black first, prove it on a sheet at every size and on every ground, revise one change at a time, and export for web, iOS and Android. Never
motion-craftAdd or change UI animation the disciplined way. Decide first whether it should animate at all (frequency gate), name its purpose, pick the cheapest tool, then the right properties, easing, duration and origin, and ship reduced-motion and hover gating with it. Use when asked to animate, add transitio
motion-reviewReview existing or changed animation code against ten motion standards (justified, frequency-appropriate, responsive easing, sub-300ms UI, correct origin, interruptible, GPU-only, accessible, asymmetric, cohesive). Output a Before/After/Why table, a tiered verdict, and an explicit Block or Approve.
slop-auditAudit a screen for AI-slop signs (reflex gradients, glows, emoji icons, hype copy, heavy headings, pulsing elements, off-scale spacing, template look), decide how much slop there is (heavy, light, none), set or confirm the direction, and fix in nine ordered passes. Use when a UI "looks AI-made", gen
stress-uiBreak a component with worst-case but realistic data (long names, unbreakable emails, CJK/RTL, 0/1/1,000 items, huge numbers, missing fields), wire a dev-only data toggle, check at 320px, 200% zoom, dark mode and RTL, and report Broken/Ugly/Fragile findings with fixes. Report only; fix on request.
design-criticIndependent visual critic. Judges a rendered screen against DESIGN_MAP.md (character, world, signature, tokens) and the slop signs, runs the competitor test, and returns a ranked list of what makes it generic, with exact fixes. Use for a read that isn't anchored on the code that was just written.
interface-reviewerIndependent interface-behaviour reviewer. Audits UI code (and the running screen, if a browser is available) against agent_docs/interface-guidelines.md: keyboard, focus, targets, forms, URL state, feedback, touch, layout, content handling, accessibility, performance, dark mode and hydration. Returns
motion-reviewerIndependent motion reviewer. Measures every animation in scope against the ten motion standards in /motion-review (justified, frequency, easing, duration, origin, interruptibility, GPU-only, accessibility, asymmetry, cohesion) and returns a Before/After/Why table, a tiered verdict, and Block or Appr
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/session-start.sh
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/prompt-router.sh
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/branch-protect.sh
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/block-dangerous-commands.sh
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/slop-scan.sh
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/motion-gate.sh
Plan → Confirm → Implement → Verify discipline for software work: hooks, skills, review agents and a CLAUDE.md ruleset.
40 skills · 6 agents · hooks
Question → Evidence → Draft → Verify → Cite discipline for scholarly writing in LaTeX and BibTeX, with citation enforcement.
23 skills · 5 agents · hooks
Research → Position → Create → Gate → Measure for marketing your own product: a MARKETING_MAP.md evidence file, hooks that block unsourced social proof and gate publishing, skills and review agents.
15 skills · 3 agents · hooks
Ingest → Select → Cut → Compose → Render → QC for editing your own video: an EDIT_MAP.md, read-only source footage, a licence register and checked renders.
hooks
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows
18 skills
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.
2 skills · hooks
GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.
72 skills · 72 commands · 64 agents · 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.