frontend-planner
Skill7 starsChanged 6 months agoMITView on GitHub
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.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- ankitluthra/frontend-quality-graphtheir own version, first seen Oct 20, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- ankitluthra/frontend-quality-graph★ 0same name
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.
In this repository19 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- backend-engineerSkill
- data-analystSkill
- devexSkill
- document-writerSkill
- fintech-frontend-engineerSkill
- frontend-engineerSkill
- frontend-reviewerSkill
- kotlin-devSkill
- kotlin-reviewerSkill
- orchestratorSkill
- product-managerSkill
- project-managerSkill
- qa-engineerSkill
- senior-engineerSkill
- seo-managerSkill
- sreSkill
- technical-business-analystSkill
- ux-researcherSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
Confirm: before writing any file, including the conventions file.
- Very specific: line 69
If out of scope or missing context, return BLOCKED: [reason] — [what would unblock this] instead.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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
- Announce the overlays loaded, or "no overlay".
- Recon first — never propose tasks before Phase 1 is complete.
- Confirm before writing any file, including the conventions file.
- 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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.