agentleFS
Sign inStart free
marcusbelzmarcusbelz/di2-starter-kit/.claude/skills/frontend/SKILL.md

frontend

Skill0 starsChanged 4 months agoMITView on GitHub

Build UI components against the real APIs. Use after the backend is built (for features that need one). Default stack is React/Next/Tailwind/shadcn; adapt to the project's actual UI stack.

We split this skill into the rules it gives an agent

7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 43 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read .claude/rules/stack.md (the ui stack) and .claude/rules/ui/ (the project's UI rules: component library, brand tokens, states, a11y).

    line 17
  2. Very specific:

    Read features/INDEX.md and the feature spec (incl.

    line 19
  3. Very specific:

    Use the brand tokens from brand.md in the active flavor under .claude/rules/ui/ — no hardcoded colors.

    line 30
  4. Very specific:

    If context was compacted: re-read the feature spec + features/INDEX.md.

    line 36
  5. Very specific:

    Commit per .claude/rules/general.md bug-fix format.

    line 45
  6. Distinctive:

    No leftover mock data / "TODO: connect API" / placeholder calls where a real endpoint belongs.

    line 50
  7. Distinctive:

    Every API call surfaces loading + error states (skeletons, toasts, inline errors).

    line 51

“Common” is measured: kept by at least 6 in 10 of the 43 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Frontend Developer

Role

You read feature specs + tech design + UX mockups and implement the UI. The default this kit assumes is React + Next.js + Tailwind + shadcn/ui — but the authoritative UI stack is ui in .claude/rules/stack.md. If the project uses a different UI stack, follow that and adapt the component conventions below.

Before Starting

  1. Read .claude/rules/stack.md (the ui stack) and .claude/rules/ui/ (the project's UI rules: component library, brand tokens, states, a11y).
  2. Read features/INDEX.md and the feature spec (incl. Tech Design + UX Design / mockups).
  3. Scan installed UI components, existing custom components, hooks, and pages in the project's layout.

Workflow

  1. Read spec + design + mockups. Identify which library components to use vs. what to build custom.
  2. Clarify (only if no mockups exist): visual style, reference designs, brand colors (or tokens), layout (sidebar/top-nav/centered); mobile-first vs. desktop-first; specific interactions; a11y beyond defaults (target WCAG 2.1 AA).
  3. Implement components. For a shadcn-style stack: ALWAYS check the installed component library first; install missing primitives via the library's CLI; build custom components only as compositions of primitives; style with the project's utility-class system (no inline styles). Use the brand tokens from brand.md in the active flavor under .claude/rules/ui/ — no hardcoded colors.
  4. Integrate into pages/routes. Connect to the real backend APIs (or local state) per the Tech Design.
  5. Cover the four states (loading / empty / error / populated) for every data-driven view.
  6. User review. Tell the user how to run the UI (the run command from stack.md); iterate.

Context Recovery

If context was compacted: re-read the feature spec + features/INDEX.md; git diff for your changes; re-scan existing components; continue — don't restart or duplicate.

Bug-Fix Mode (/frontend BUG-NNNN)

  • Read docs/bugs/bug-NNNN-<slug>.md (Glob docs/bugs/bug-NNNN-*.md).
  • Only UI / interaction / layout / client-state bugs. API/DB/auth → /backend BUG-NNNN; login/session/OIDC → /auth BUG-NNNN.
  • No scope-creep: touch only the files/symptoms in the bug entry. Unplanned refactors/features → a separate bug or ask the user.
  • Commit per .claude/rules/general.md bug-fix format. Don't change bug status — /bug close does that after a green /qa re-test.
  • Handoff: "Fix for BUG-NNNN committed. Next: /qa re-tests, then /bug close BUG-NNNN."

Sanity check before handing off to QA

  • No leftover mock data / "TODO: connect API" / placeholder calls where a real endpoint belongs.
  • Every API call surfaces loading + error states (skeletons, toasts, inline errors).
  • Auth-gated views actually read the session — not a hardcoded isAdmin = true.

Checklist

  • Checked the component library for every UI element; no custom duplicates of existing components
  • Reused existing project components where possible; followed the UX mockups
  • All planned components implemented; utility-class styling only; brand tokens (no hardcoded colors)
  • Loading / empty / error / populated states implemented
  • Responsive (mobile/tablet/desktop); semantic HTML, ARIA labels, keyboard nav
  • Build + lint (from stack.md) pass; all AC addressed; features/INDEX.md "In Progress"; committed

Handoff

"Frontend done and wired to the real APIs. Next step: /qa to test this feature against its acceptance criteria."

Git Commit

feat(<prefix>-XXXX): Implement frontend for [feature name]

Download now (ZIP)

  • Other versions49 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 49

    1. langwatch/langwatch★ 5ksame name
    2. atopile/atopile★ 4ksame name
    3. leookun/cursor-byok★ 3.2ksame name
    4. theopenco/llmgateway★ 1.7ksame name
    5. notque/vexjoy-agent★ 443same name
    6. notque/claude-code-toolkit★ 442same name
    7. AlexPEClub/ai-coding-starter-kit★ 382same name
    8. OyadotAI/oya-browser★ 351same name
    9. speakeasy-api/gram★ 275same name
    10. ThePrimeagen/skills★ 234same name

    39 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use programming, data and 3 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • DevNewbie1826Skill

      programming

      MUST USE for work on Python, Rust, TypeScript, or Go source files and project manifests. Triggers: write or edit code; new project; Go HTTP service (gin lane); Bubble Tea TUI; CJK IME; Connect-Go RPC; sqlc or pgx; branded IDs; exhaustive matching; unsafe Rust; Miri; oversized file; refactoring; logging, log levels, structured logging, or observability; arena, allocator, bumpalo, const fn, const generics, compile-time programming, zero-allocation APIs, bitfields, repr, scope guards, errdefer-style cleanup, Zig-like patterns, zero-copy parsing, packed data, or FFI; Rust public API design or macros.

      Also in 3 projects that use this

    • launch52-aiSkill

      data

      Generate data layer code (Freezed DTOs, repository implementations, data sources) from feature specifications or API references. Creates the bridge between domain entities and external data sources. Use after /domain to implement the data layer.

      Also in 4 projects that use this

    • BlockSkill

      debugging

      Debugging guidelines and best practices

      Also in 5 projects that use this

    • AnthropicSkill

      debug

      Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

      Also in 5 projects that use this

    • NVIDIASkill

      testing

      Run Python and Rust tests for physicsnemo-curator using uv + pytest with coverage reporting via pytest-cov, and cargo-nextest for Rust tests. Includes benchmark workflows with pytest-benchmark and criterion.

      Also in 5 projects that use this

  • In this repository14 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free