claude

dev-harness

51 skills, the poort quality gate, plus commit-guard and verified-claim-guard hooks for Claude Code.

3 on GitHubby Robin Brilv1.12.0MITupdated 22 days ago
/

Plugin dev-harness from marketplace dev-harness in robinbril/claude-code-harness. Commands read from the repo's manifest — 21 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.

What it installs

Skills (52)

  • animate-expo

    Build animations in React Native and Expo, making the decisions in the order that determines whether they feel right — should it animate, which thread it runs on, which properties, spring or timing, how the gesture hands off, how it degrades. Writes the implementation with Reanimated, Gesture Handle

  • animate

    Build an animation from scratch, making the decisions in the order that determines whether it feels right — should it animate at all, what purpose, which tool, which properties, which curve and duration, how it interrupts, how it exits. Writes the implementation. Use when asked to animate something,

  • animation-vocabulary

    Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without know

  • apple-design

    Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking,

  • ask-sonner

    Guide to Sonner, the React toast library — install and wire up the Toaster, pick the right toast() call, promise and loading toasts, updating, dismissing and persisting toasts, styling, theming and icons, positioning and multiple toasters. Use when working with Sonner or troubleshooting it — toasts

  • batch-grill-me

    A relentless interview that asks every frontier question at once, round by round.

  • bi-dashboards

    Power BI-stijl rapporten en dashboards in eigen web-apps (Vue + ECharts), zonder Power BI te embedden; finance, ATS-analytics (Polpo) en de assistent naast de cijfers. Gebruik bij "Power BI-stijl", "ms-visuals" of "meer visuals", KPI-kaarten, brug of IBCS-afwijking, matrix met databalken, slicers en

  • bouw-loop

    Story-loop die een feature of tasklist story-voor-story bouwt met een verse sonnet-worker per story en verificatie door de orchestrator. Ondersteunt parallelle waves via de Workflow-tool voor onafhankelijke stories. Gebruik bij "bouw dit", "werk de tasklist af", "/bouw-loop", "implementeer deze stor

  • brandkit

    Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized

  • code-audit

    Full code review of a branch, diff or commit with open-code-review: OCR picks the files and rules, the agent reviews. Use for an audit or a complete review. Requires the `ocr` CLI. Requires the `ocr` CLI installed (via `npm install -g @alibaba-group/open-code-review` or GitHub release binary). Does

  • commit-discipline

    Voorkomt commit-spam: nooit autonoom committen tijdens werkbatches, werk verzamelen in de working tree, en op signaal van de gebruiker indelen in 3-7 thematische commits. Bevat het hergroepeer-recept voor als er toch te veel lokale commits staan. Gebruik bij elke commit-beslissing, bij "commit dit",

  • council

    Convene a multi-voice AI council that deliberates on a hard decision through independent positions, a blind peer-review round, and a chairman synthesis. Use for ambiguous calls with several credible paths, such as architecture choices, build-vs-buy, ship-vs-hold, strategy tradeoffs, go/no-go calls,

  • createloopprompt

    Zet een taakomschrijving om in een volledige, begrensde Autonomous Coding Loop Prompt voor Claude Code, Cursor of Codex. Gebruik bij "maak een loop prompt voor X", "laat een agent X autonoom fixen", of als iemand een agent wil laten itereren zonder rommel of scope creep.

  • data-visualization

    ALWAYS use before building or changing ANY chart, graph, KPI-tile, dashboard widget or visualization (Vue/SVG/Recharts/ECharts/Chart.js/D3/Python). The Chart Selection Guide picks the chart type from the data relationship (trend, composition, ranking, flow, delta) BEFORE any code is written; also fi

  • design-taste-frontend

    Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

  • diagram-design

    Create branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, polar chart (polar/radial lollipop), loop/flywheel, nested, tree, org chart, layer stack, Venn, pyramid/funnel, treemap, heatmap, bar, waterfall, line, Gantt

  • dicht-loop

    Security-gaten dichten in bestaande code zonder dat normaal gedrag verandert, door bestaande harness-skills op volgorde te draaien: e2e legt het huidige gedrag vast, speur-loop vindt en bewijst de kwetsbaarheden, fix-loop dicht ze een voor een met een aanvalstest, find-bugs keurt de diff. Fixes die

  • e2e-rules

    House rules for end-to-end UI tests with e2e (TesterArmy). Use alongside the e2e skill on any UI change in a web or mobile app, when setting up e2e in a project, and when an e2e run fails. Covers the subscription-only model setup, the config template, file naming, and when a task counts as done.

  • e2e

    Agentic end-to-end tests with e2e, the e2e runner. Covers scaffolding e2e.config.ts, picking the Playwright browser engine or the agent-device mobile engine, starting the app under test from the config, driving flows with agent.act, judging with agent.assert, agent.waitFor, and agent.extract, pinnin

  • emil-design-eng

    This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

  • find-animation-opportunities

    Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values, it does not implement it. Use when the user asks "what could be animated here?" or wants to "make this feel more alive". For fixing existing animat

  • find-bugs

    Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.

  • fix-loop

    Autonome fix-loop die een falende test, build of bug repareert tot het doelcommand groen is, met verse diagnose-workers per iteratie en een harde stop na 5 pogingen. Gebruik bij "fix deze bug", "maak de build groen", "deze test faalt", "/fix-loop", of elke failure met een herhaalbaar verificatiecomm

  • fixing-accessibility

    Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or reviewing WCAG compliance.

  • frontend-gotchas

    Bewezen frontend-valkuilen op deze machine. Use when: building or debugging a Next.js 16/Turbopack/React 19 app; adding routes to a Vite SPA with a dev-proxy; writing CSS hide/override rules for branding overlays; or a chart/preview/screenshot hangs during frontend work.

  • goal

    Proactive goal mode. Give one outcome; drive to it autonomously with verifiable steps, parallel subagents, and independent verification. Derives a concrete finish line from vague scope, resumes interrupted runs ("ga door"), reports progress pulses. Only stops at real decision points. Zwaarte-keuze:

  • improve-animations

    Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "imp

  • keten-loop

    Orchestratie-chain die een einddoel end-to-end schipt door de loop-collectie aan elkaar te rijgen: sweep (recon) -> plan -> bouw-loop -> polijst-loop -> fix-loop -> onafhankelijke eind-verificatie. Het token-zuinige supergoal-alternatief: een evaluator-pass per gate in plaats van de volledige evalua

  • make-interfaces-feel-better

    Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, micro-interactions, enter/exit animations, or any visual detail work. Triggers on UI polish, design detail

  • mobile-native

    Make a web app feel native on a phone — the small CSS and meta-tag fixes that separate "a website in a browser" from something that feels installed. Covers sticky hover states, tap highlight flashes, the 100vh bug, inputs that zoom the page, laggy taps, pull-to-refresh hijacking scroll, content unde

  • office-docs

    Generate PowerPoint (.pptx), Excel (.xlsx) and Word (.docx) files programmatically with Python. Use when the user wants to build or fill a presentation, spreadsheet or document. Triggers: "maak een powerpoint/pptx", "maak een excel/xlsx", "maak een word/docx", "genereer een presentatie/spreadsheet/d

  • pick-ui-library

    Pick the right library for a given frontend task from a curated, opinionated list — numbers, OTP inputs, charts, command menus, virtualization, drag and drop, toasts, state, styling, and more. Only runs when explicitly invoked; it does not trigger on its own.

  • polijst-loop

    Kwaliteits-loop die een UI, tekst of deliverable iteratief verbetert via score-tegen-rubric, gerichte fixes en een verse judge per ronde, tot de score plateaut. Gebruik bij "maak dit mooier/beter", "polish deze pagina", "/polijst-loop", "haal dit naar niveau", of na een eerste werkende versie die no

  • polpohire-design

    The current PolpoHire (Polpo) frontend-v4 design language, extracted verbatim from the redesign on branch codex/design-performance-polish. Bold, high-density, light indigo/violet theme with Apple-light shadows, a flat button system, one spring motion voice, and a status-quartet colour language. Use

  • pre-pr-gates

    Review kill-gates before opening or updating a PolpoHire PR. Use before every `gh pr create`, `gh pr ready`, "open een pr", "klaar voor review", or when reporting a feature branch as review-ready. Catches the recurring review classes that tests and typecheck do not: ghost versions, cancelled gesture

  • projectstructuur

    Ontwerp, herstructureer veilig en bewaak een repositoryindeling die een junior begrijpt. Gebruik bij een nieuwe repo of een expliciet geautoriseerde opschoning van een bestaande repo.

  • prototype

    Build multiple genuinely different versions of a UI piece you describe, rendered behind a visual picker so you can flip through them live and promote the one that feels right. Only runs when explicitly invoked; it does not trigger on its own.

  • rea

    Reverse engineer websites, shipped apps, JavaScript bundles and binaries with REA, backed by evidence. Use for /rea and exact interface reconstruction; not for ordinary source-code review.

  • reverse-engineer-anything

    Reverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.

  • readme

    Layout, wording and visuals for a README and the one-line GitHub repo description - problem first, sharp expert copy, custom light/dark SVG images, verified in GitHub's own renderer. Use for /readme, a new README, a README overhaul or a repo description.

  • redesign-existing-projects

    Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

  • render-proof

    Render a web page or local HTML file headless to PNG with Playwright, full page or one element, at a chosen width, and read the expected fact off the image. Use to prove a UI change visually before calling it done, at 1440, 768 and 390 wide, or when another skill asks for a render proof.

  • repo-hygiene

    Read-only git/GitHub hygiene check for a repo - dev vs main drift, unmerged and dead branches (incl. squash-merged), merge conflicts per branch via side-effect-free git merge-tree, open PRs and failing GitHub Actions. Use when asked for a codehygiene check, repo health, "is alles gemerged", "loopt d

  • review-animations

    Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

  • skill-finder

    Find, reuse, or write a skill. At the start of any non-trivial request: check which installed skills fit; if none, search for proven implementations before building; and if the task recurs, write a new skill with proper structure. Triggers: "skill finder", "welke skill kan ik hiervoor gebruiken", "i

  • speur-loop

    Loop-until-dry vind-loop voor onbekende hoeveelheden: bugs, dead code, inconsistenties of research-claims (security-vondsten horen bij security-audit; deze loop kan die skill als lens draaien). Rondes van parallelle finders met verschillende lenzen, dedup, adversarial verificatie, en stoppen na 2 dr

  • supergoal

    Plan and autonomously build a task end-to-end in independently verified phases. A separate evaluator re-checks every phase against the repo and the running result, blind to the builder's own report. Use for `/supergoal`, "plan and ship X", "autonomous build", "don't stop until it's done", or any non

  • systematic-debugging

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

  • theme-selector

    Bouw de complete PolpoHire/TSS theme-selector na in elke web-app. 18 colourway-presets met contrast-vloeren, custom kleuren met live re-derive, merk-accenten, font-picker, dichtheid, en Liquid Glass (matglas + glossy iOS-variant) met intensiteit, inclusief persistentie en no-flash. Inclusief de comp

  • transitions-dev

    Production-ready CSS transitions for web apps. Use when implementing notification badges, dropdowns, modals, panel reveals, page transitions, card resizes, number pop-ins, text swaps, icon swaps, success checks, avatar group hovers, or error state shakes. Triggers on "add a transition", "animate the

  • ux-heuristics

    Evaluate and improve interface usability using heuristic analysis. Use when the user mentions "usability audit", "users are confused", "form usability", "navigation problems", "Nielsen heuristics", "cognitive walkthrough", or "is this easy to use". Also trigger when reviewing a design for usability

  • waak-loop

    Babysit-loop voor externe state die de harness niet zelf trackt: een CI-run, deploy, DNS-propagatie, URL-health, mailbox of kanban-kolom. Pollt cache-bewust via ScheduleWakeup, voert bij verandering een vooraf afgesproken actie uit en stopt bij het eindcriterium. Gebruik bij "hou de deploy in de gat

Hooks (3)

  • PreToolUse

    node "${CLAUDE_PLUGIN_ROOT}/hooks/commit-guard.js"

  • Stop

    node "${CLAUDE_PLUGIN_ROOT}/hooks/verified-claim-guard.js"

  • SessionStart

    node "${CLAUDE_PLUGIN_ROOT}/hooks/guidelines.js"

View source on GitHub

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

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

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

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

career-ops-hq/career-ops 82,253

Maintain dev-harness?

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.

claude & codex pluginslisted