Skip to content
Agentmart
Submit a tool

frontend-planner

Use when breaking down a frontend feature, project, or migration, when a frontend repo has no documented conventions, or before implementation starts on…

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-planner

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 breaking down a frontend feature, project, or migration, when a frontend repo has no documented conventions, or before implementation starts on non-trivial UI work.

Use cases: design, frontend

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-planner

What's inside

Skill name
frontend-planner
Description
Use when breaking down a frontend feature, project, or migration, when a frontend repo has no documented conventions, or before implementation starts on non-trivial UI work.
License
MIT
Instructions
65 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Frontend Planner

## Iron Law

```
No plan without recon. Read the repo before proposing anything.
If the repo has no conventions file, the first deliverable is the conventions file, not the feature.
A task that does not name its files, its layer, and its test is not a task.

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".
2. **Recon first** — never propose tasks before Phase 1 is complete.
3. **Confirm** before writing any file, including the conventions file.
4. **Report** the plan, the convention gaps, and what you could not resolve.

---

## Phase 1 — Recon

| Read | To learn |
|---|---|
| `package.json`, lockfile, framework config | Installed versions — never assume them from the task |
| The conventions file, if any | Which rules already exist |
| 3 comparable features and their tests | The de-facto pattern and the real testing bar |
| Lint / CI config | What is machine-enforced — never plan human process for it |

## Phase 2 — Conventions gate

| State | Action |
|---|---|
| Exists | Plan inside it; each task cites the rules it follows |
| Absent | Task 1 is to write `FRONTEND-CONVENTIONS.md` from the 3 samples, each rule marked **observed** or **proposed** |
| Code contradicts it | Report the drift, ask which wins, then plan |

**Conventions sections:** stack and versions · directory and layer map · import boundaries · component contract · state ownership · data layer · platform forks · testing bar · accessibility bar · performance budgets · open decisions.

## Phase 3 — Decompose

Vertical slices, each shippable alone. Every task names:

- **Files** created or changed, and their layer
- **Public surface** it exposes, and who consumes it
- **States**: loading, empty, error, success
- **Test** that proves it, at the level this repo already tests
- **Accessibility** requirement, named rather than implied
- **Done when** — one observable condition

Sequence by dependency and flag blockers. Keep risks and unknowns in their own list; never bury an unknown inside a task.

---

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