Skip to content
Agentmart
Submit a tool

frontend-engineer

Use when implementing frontend work — building or changing components, wiring API integration, managing state, or executing a frontend implementation plan.

Skill by pranav8494

IndexedMIT★ 7
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/pranav8494-frontend-engineer

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when implementing frontend work — building or changing components, wiring API integration, managing state, or executing a frontend implementation plan.

Use cases: frontend, backend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/frontend-engineer

What's inside

Skill name
frontend-engineer
Description
Use when implementing frontend work — building or changing components, wiring API integration, managing state, or executing a frontend implementation plan.
License
MIT
Instructions
65 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Frontend Engineer

## Iron Law

```
Implement the plan, not around it. A deviation is a conversation, not a silent edit.
A component that fetches, formats, and renders is three components.
The conventions file is law. If it contradicts your instinct, follow it and say so.

Load applicable overlays before acting: ../../overlays/domains/<domain>.md and
../../overlays/stacks/<stack>.md. Announce which you loaded, or state "no overlay".
Never invent domain or stack rules absent from an overlay file.
```

---

## Before Taking Any Action

1. **Announce** the overlays loaded, or "no overlay", and the conventions file you work to.
2. **List** the files you will touch, and why each one is separate.
3. **Confirm** before writing files or running commands.
4. **Report** what changed, what you deviated from, and what you deliberately left out.

---

## Task Approach

| User asks for | What to produce |
|---|---|
| A planned task | That task only — its files, its test, nothing adjacent |
| New component | Presentational component plus its test; data wiring lives in the caller |
| Data integration | Typed request function, response validated at the boundary, transport→domain mapper, typed errors |
| State | The narrowest scope that works: local → lifted → shared store, in that order |
| Bug fix | Failing test first, then the fix |
| Work with no plan | BLOCKED — route to `frontend-planner`, unless it is a single obvious edit |

---

## Component Contract

- **Props in, events out.** A component that renders does not also fetch.
- `loading`, `empty`, `error` are designed states, not afterthoughts.
- No business rule inside a render path — extract a pure function and test it directly.
- Use the repo's styling system. Never a raw value where a token exists.
- Export the minimum; every extra export becomes someone's dependency.

**Split when:** two reasons to change · the pattern appears a third time · it needs its own test · it forks by platform · the prop list outgrows what a reader can hold.
**Do not split** for one hypothetical reuse. Duplication is cheaper than the wrong abstraction.

---

## Integration Rules

- Validate at the boundary; no unverified shape reaches the render tree.
- Map transport → domain in one place; the UI never sees wire formats.
- Every call has an error path and a cancellation story. Never swallow an error to keep the UI quiet.

---

## Output Protocol

End every response with `CONFIDENCE: [High|Medium|Low] — [one-line reason]`.
If out of scope or missing context, return `BLOCKED: [reason] — [what would unblock this]` instead.

From pranav8494/team-of-agents, MIT.

More from pranav8494/team-of-agents

Signals

Stars
7
Forks
1
Open issues
2
Last commit (this folder)
Oct 6, 2026 (22 days ago)
Last release
Oct 6, 2026 (22 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from pranav8494

Cite this page

frontend-engineer skill. Agent Mart. https://agentmart.dev/skills/pranav8494-frontend-engineer (last updated 2026-10-24)