agentleFS
RaditteAnggoroRaditteAnggoro/skill-for-lazy-developer/.agents/skills/feature-discovery/SKILL.md

feature-discovery

Skill1 starsChanged 8 days agoMITView on GitHub

Clarify an ambiguous feature or consequential design choice into acceptance criteria and an implementation outline. Skip interviews for clear small changes.

5 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use code-review.

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.
  • 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 5 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:

    Read the request, applicable repository guidance, and the relevant existing flow.

    line 12
  2. Distinctive:

    Keep the specification proportional.

    line 23
  3. Distinctive:

    If the user requested planning only, deliver the specification and unresolved decisions without implementing.

    line 31
  4. Distinctive:

    Use a failing behaviour check and short implementation slices when adding logic.

    line 33
  5. Distinctive:

    Do not create issue-tracker tickets, update external documentation, or start another chat solely because this skill was invoked.

    line 35

“Common” is measured: kept by at least 6 in 10 of the 5 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

Feature Discovery

Turn uncertainty that would change the implementation into concrete decisions. Respect existing decisions and the user's requested depth. A clear feature request does not need a compulsory interview.

Investigate before asking

Read the request, applicable repository guidance, and the relevant existing flow. Identify which requirements are stated, which can be inferred from existing behaviour, and which choices materially affect the result. Reuse established terms; create a glossary only when repeated ambiguity makes one useful.

For consequential uncertainty, give the user a recommended default with its trade-off and ask a concise question. Continue independent inspection while awaiting a reply. Do not ask again for a decision already made. If the answer would only affect a reversible implementation detail, use a stated assumption and proceed.

A broad improvement request may be handled with either one decision-changing question or two or three outcome-based choices. Use the shorter form that makes the decision easiest. Do not run a questionnaire, expose internal skill names, or ask the user to explain implementation concepts that can be learned from the repository.

Describe the feature

Keep the specification proportional. For a small feature, a few lines in the conversation are sufficient. For larger work, use the repository's existing documentation location when a saved plan is requested or needed for execution.

Cover the user outcome, scope and exclusions, current behaviour, main flow, important error or empty states, and acceptance criteria that can be observed. Include API, data, migration, compatibility, or permission changes only where relevant.

Describe the smallest useful increment. Identify affected modules from code evidence, integration uncertainties, and verification. Present alternatives only if they change a meaningful property such as compatibility, deployment cost, or data ownership.

Move into the requested work

If the user requested planning only, deliver the specification and unresolved decisions without implementing. If they requested a build or fix, proceed once decisions that block correctness are resolved. A mandatory design-signoff ritual is not implied.

Use a failing behaviour check and short implementation slices when adding logic. Measure success against the agreed acceptance criteria rather than the number of files or tasks produced.

Do not create issue-tracker tickets, update external documentation, or start another chat solely because this skill was invoked. Those actions require relevant user authorization.

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.