swcstudiospace/agent-swarm/a06-frontend

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

A06 FE Frontend Engineer — Implements UI against A04 tokens/UX specs and A03 API contracts, with component tests and a11y checks. Use for client-side code. Use when the swarm assigns capability code.frontend, code.ui, code.patch.

Install

npx vskill@latest install swcstudiospace/agent-swarm/a06-frontend

SKILL.md

Frontend Engineer (A06 FE) — omp

When to Use

  • The assignment capability is one of: code.frontend, code.ui, code.patch.
  • The user names this agent, slug a06-frontend, or code FE.

Don't use for: Do not edit backend or schema.

Procedure

  1. Dispatch via the omp task tool with agent: a06-frontend (definition: omp/agents/a06-frontend.md), passing the signed task.assign payload.
  2. The agent finishes by calling yield with a task.result object; read it from the task result.
  3. Don't use it for: Do not edit backend or schema.

Registered tools

Discover with swarm_catalog, call with swarm_tool_call (the caller is your own identity).

  • fe_a11y_scan (READ): Scan an HTML snippet with the fe_a11y_check rules and return the issue count.
  • fe_heading_sequence_check (READ): Check that heading levels start at h1 and never skip a level when descending, as the a11y self-gate requires.
  • fe_alt_text_check (READ): Flag non-decorative images with missing, empty, or generic alt text and decorative images that carry alt text.
  • fe_form_label_check (READ): Find visible form controls that lack an accessible name from a label, a non-blank aria-label, or aria-labelle…
  • fe_tab_order_check (READ): Count positive tabindex values and the focus-order inversions they create among supplied DOM-ordered elements.
  • fe_bundle_budget_check (READ): Compare total bundle bytes against a byte budget and, when a baseline is given, against the regression limit…
  • fe_prop_type_coverage (READ): Measure the share of component props with a concrete declared type and list components below the minimum rati…
  • fe_target_size_check (READ): List interactive targets smaller than the minimum CSS-pixel size on either side, default 24 px per WCAG 2.2 S…
  • fe_token_literal_scan (READ): Flag raw colour and spacing literals (hex, rgb/hsl functions, non-zero px/rem/em) in supplied style declarati…
  • fe_state_parity_check (READ): Compare the states implemented per screen or component with ux.spec states for exact parity, listing missing…
  • fe_cwv_budget_check (READ): Gate Core Web Vitals (LCP, INP, CLS) and Lighthouse scores against thresholds, defaulting to LCP 2.5 s, INP 2…
  • fe_client_security_scan (READ): Scan supplied source text for XSS sinks, inline scripts and handlers, external scripts or stylesheets without…

Skills

Read the one that fits with its link; they are hidden from the skill listing.

  • skill://a06-frontend--a11y-selfgate: Use when UI code is ready for IN_REVIEW; run the per-rule a11y tools and fe_a11y_check so serious and critical findings are zero.
  • skill://a06-frontend--api-contract-bind: Use when UI code adds or changes an API call; match every call to a path and method of the pinned contract, type the client from…
  • skill://a06-frontend--bind-inputs: Use when an A06 task starts and before any code is written; read the handover, detect the toolchain, bind spec, token and contrac…
  • skill://a06-frontend--client-security: Use when code adds HTML injection, inline script, external assets or web storage; scan changed sources for XSS, CSP, SRI and PII-…
  • skill://a06-frontend--component-catalog: Use when a component is finished; type its props, write one Storybook story per state and Playwright component tests, and hand th…
  • skill://a06-frontend--design-deviation: Use when the ux.spec is ambiguous or undefined for a state or token, or the UI needs a new pattern or dependency; ask A04 one que…
  • skill://a06-frontend--perf-budget: Use when a build output and a Lighthouse run exist; gate bundle bytes and Core Web Vitals against budget, code-split once on a br…
  • skill://a06-frontend--rework-intake: Use when review comments, a11y violations, security findings or a gate verdict return A06 work; route findings to A06 skills and…
  • skill://a06-frontend--state-parity: Use when a screen or component is complete; prove its implemented states equal ux.spec states exactly and close every missing or…
  • skill://a06-frontend--token-binding: Use when styling code was written or changed; scan declarations for raw colour and spacing literals and replace each with a desig…
  • skill://a06-frontend--visual-flake-triage: Use when a visual or component test fails intermittently; rerun it twice, quarantine (never delete) a flake, and send a baseline…

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/swcstudiospace/agent-swarm/a06-frontend/badge)](https://verified-skill.com/skills/swcstudiospace/agent-swarm/a06-frontend)

Something wrong with this skill or its page? Tell us.