web-dev-tools

Entry point for all web development — routes to the frontend, backend, or security half. Use when the user asks to build, design, restyle, or audit a website, landing page, dashboard, or component; design an API or schema; implement auth; set up infra or deploy; write or fix tests; run a security review or pentest of a web app; or pick a web-development tool and it is not obvious which discipline it belongs to. Splits into web-dev-frontend (design, UI, animation, a11y, SEO, content), web-dev-backend (APIs, data, auth, infra, backend testing), and web-dev-security (web & app security, SAST, supply chain, secrets, AI/LLM security) — and routes to exactly the right skill and MCP.

Qu'est-ce que web-dev-tools ?

web-dev-tools is a Claude Code agent skill that entry point for all web development — routes to the frontend, backend, or security half. Use when the user asks to build, design, restyle, or audit a website, landing page, dashboard, or component; design an API or schema; implement auth; set up infra or deploy; write or fix tests; run a security review or pentest of a web app; or pick a web-development tool and it is not obvious which discipline it belongs to. Splits into web-dev-frontend (design, UI, animation, a11y, SEO, content), web-dev-backend (APIs, data, auth, infra, backend testing), and web-dev-security (web & app security, SAST, supply chain, secrets, AI/LLM security) — and routes to exactly the right skill and MCP.

Compatible avec✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/yashoramabhat-hash/web-dev-skills/tree/HEAD/skills/web-dev-tools

Installed? Explore more Développement et programmation skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

Demander à votre IA préférée

Ouvre une nouvelle conversation avec cette compétence d'agent déjà préchargée.

Documentation

web-dev-tools — router

The web-development toolkit is split three ways. Pick the discipline, then pick the skill inside it.

SkillCoversCatalog
web-dev-frontendDesign systems & tokens, components, animation & motion, accessibility & UX review, SEO & Core Web Vitals, content & copy, frontend testing105 skills
web-dev-backendAPI design & frameworks, databases & migrations, auth & access control, cloud & DevOps infrastructure, backend testing103 skills
web-dev-securityWeb app & API pentesting, auth & session attacks, injection & request attacks, SAST & supply chain, API hardening, secrets, AI/LLM security180 skills

Each file is self-contained — its own catalog, its own MCP table, its own rules. Loading only one keeps context small.

Step 1 — Which discipline?

The request is mainly about…Load
Visual design, layout, components, styling, brand, colour, typographyweb-dev-frontend
Animation, scroll effects, transitions, motion, videoweb-dev-frontend
Contrast, screen readers, keyboard nav, WCAG, UX reviewweb-dev-frontend
SEO, Core Web Vitals, Lighthouse, page weight, deployweb-dev-frontend
Copy, docs, blog posts, decks, spreadsheetsweb-dev-frontend
REST/GraphQL endpoints, framework choice, error handlingweb-dev-backend
Schema, queries, migrations, indexes, cacheweb-dev-backend
Login, sessions, tokens, OAuth, SSO, RBAC, IAMweb-dev-backend
Docker, Kubernetes, CI/CD, TLS, firewall, WAF, zero-trustweb-dev-backend
Backend tests, API integration tests, load & latencyweb-dev-backend
Pentest or audit a web app / APIweb-dev-security
Auth attacks — JWT, OAuth, BOLA/IDOR, mass assignmentweb-dev-security
Injection classes — SQLi, XSS, SSRF, XXE, CSRF, prototype pollutionweb-dev-security
SAST, dependency audit, SBOM, CI/CD supply chainweb-dev-security
Rate limiting, schema validation, gateway, API hardeningweb-dev-security
Vault, secrets, key rotationweb-dev-security
Prompt injection, LLM guardrails, agent tool poisoningweb-dev-security

Mixed task ("build a dashboard with auth"): load frontend + backend, but still pick only 1–3 skills total — one hub skill per discipline.

Ambiguous ("audit this app"): it is probably both an implementation review and a security review. Load web-dev-backend for the code read and web-dev-security for the finding. Say which skills you picked.

Step 2 — Which skill?

Read the discipline's SKILL.md catalog. Each entry is - \skill-name` — one-line description`. Match the task, then ask the user to confirm with the question tool — never pick silently. Offer the top 2–4 matches plus a "show the full catalog" escape.

Rule: load 1–3 skills, never the whole catalog. Hub skill first, then its sub-skills.

Step 3 — Which MCP?

TaskMCPDiscipline
DOM, computed CSS, console, network, screenshotschrome-devtools (call list_pages first for a pageId)front + security
Accessibility score, Core Web Vitals, SEO auditlighthousefront
Flows, auth, multi-breakpoint captureplaywrightall
Current library/framework docscontext7front + back
Iconslucidefront
shadcn/ui componentsshadcn-registryfront
Generate images / video / audiofalfront
Find design referencesexafront
Figma file → codefigma-officialfront
Next.jsnext-devtoolsfront
Diagrams / wireframesexcalidrawfront
Stock photosimages (needs API key)front
Scrape pages & docsfirecrawlall
Research current APIs / writeupsperplexityall
CVE / EPSS / KEVcve-intelback + security
ATT&CK mappingmitre-attacksecurity
Static analysissemgrepback + security
Template vuln scannuclei (needs NUCLEI_PATH)security
Content / param fuzzingffuf (needs FFUF_PATH)security
SQL injectionsqlmap (needs SQLMAP_PATH)security
Host probinghttpx-scan (needs HTTPX_PATH)security
Passive site intelurlscansecurity

If an MCP call fails, fall back to the CLI equivalent and say so.

Step 4 — The loop

  1. Scope — target, stack, what "done" means.
  2. Inspect before you change — capture the current state (DOM, styles, screenshot, API shape) before editing. Never redesign or refactor blind.
  3. Design — tokens (front) or schema (back) before code.
  4. Build — real states, not placeholders. Match existing project conventions.
  5. Verify — lighthouse + chrome-devtools + playwright for the front; tests + semgrep/codeql for the back; nuclei/ffuf/sqlmap + verification skills for security.
  6. Report — what changed, what was tested, what was not, residual risk.

Non-negotiables

  • No visual claim without a before/after screenshot.
  • WCAG AA contrast, verified with lighthouse.
  • Real assets, no emoji as UI icons. Zero console errors when done.
  • Respect prefers-reduced-motion.
  • Security work: confirm authorisation scope first (bug bounty, CTF, own infra, localhost).
  • Verify every finding before reporting it.

Commands

  • /web — pick any web-dev skill (asks which)
  • /ui — pick a frontend skill (asks which)
  • /backend — pick a backend skill (asks which)
  • /sec — pick a security skill (asks which)
  • /rea — pick from the full ~950-skill cybersecurity library (asks which)
  • /cracked — pick an interview / career skill (asks which)
  • /skills — search every installed skill

Individual skills in this repo

This repo contains 2 individual skills — each has its own dedicated page.

Skills associés