agentleFS
ZAidBinAsifZAidBinAsif/flutter-ai-starter/.cursor/skills/plan-feature/SKILL.md

plan-feature

Skill0 starsChanged 5 months agoMITView on GitHub

Plan non-trivial features — brainstorm, implementation plan, execute with verification. Use for new features beyond one-line fixes.

30 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use explore, review and 4 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.
  • genomewalkerSkill

    explore

    RLM-style recursive memory exploration - dynamically navigate the memory graph

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 5 projects that use this

  • DockerSkill

    review-pr

    Review one or more incoming Docker documentation pull requests as a maintainer. Independently validate technical claims, assess editorial fit and information architecture, choose a verdict, and draft exact inline or PR-wide feedback behind a confirmation gate. Use for requests such as "review PR 123", "is this PR correct?", "does this information belong here?", "validate this PR", or "help review backlog PRs". Do not use to maintain or fix a PR you own; use maintain-pr for that.

    Also in 3 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 3 projects that use this

  • OpenAISkill

    systematic-debugging

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user one question at a time until the problem, constraints, and success criteria are clear.

    line 23
  2. Distinctive:

    Gate: every step has explicit verification.

    line 54
  3. Distinctive:

    Gate: every step verification passes.

    line 69
  4. Distinctive:

    Check every acceptance criterion — verify or explicitly waive with reason.

    line 85
  5. Distinctive:

    Gate: all criteria met or waived.

    line 87

“Common” is measured: kept by at least 6 in 10 of the 29 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

Plan a Feature

Self-contained 4-stage workflow. Chain to flutter-implement → grind-until-green when executing.

When to use

  • Feature beyond a one-line tweak
  • Implementation spans more than a few hours
  • You want per-step verification before calling it done

Do not use when

  • Trivial fix (typo, copy, single-line guard)
  • Emergency hotfix (verify via post-mortem instead)

Optional — grill first

Ask the user one question at a time until the problem, constraints, and success criteria are clear. Explore the codebase instead of asking what code can answer. Provide a recommended answer with each question.


Stage 1: Brainstorm

Input: feature request
Output: short brainstorm doc

Include:

  • Problem statement (stranger-test: understandable without prior context)
  • 3–5 approaches with pros/cons
  • Recommended approach + one plausible alternative rejected
  • Top assumptions and risks

Gate: problem is sharp; alternative is plausible.


Stage 2: Implementation plan

Input: chosen approach from Stage 1
Output: step-by-step plan

Include:

  • File-level changes (create/modify/delete)
  • Order of steps (dependencies first)
  • Per-step verification (command or observable outcome)
  • Acceptance criteria
  • Risks and rollback notes

Gate: every step has explicit verification; another engineer could execute without clarifying questions.


Stage 3: Execute

Input: plan from Stage 2
Use: flutter-implement or implement-tdd per step

Rules:

  • One plan step at a time — run its verification before the next
  • Record deviations from the plan
  • Capture deferred items (do not fix unrelated issues inline)
  • High-stakes steps (auth, migrations): run doubt-review first

Gate: every step verification passes.


Stage 4: Verify before shipping

Input: implemented feature + acceptance criteria from Stage 2
Use: grind-until-green for analyze/test loop

Run:

dart format --set-exit-if-changed .
flutter analyze --fatal-infos
flutter test

Check every acceptance criterion — verify or explicitly waive with reason. Document the verification pass.

Gate: all criteria met or waived.


Variations

  • Tiny feature: skip Stage 1; collapse Stage 2–3 into a short plan + execute; keep Stage 4
  • Multi-PR feature: Stages 1–2 once; Stages 3–4 per PR

Loop-back

  • Approach infeasible during Stage 2 → return to Stage 1
  • Missing verifications in plan → fix plan before Stage 3
  • Repeated verification failures → pause; re-plan or escalate

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.