agentleFS
RaditteAnggoroRaditteAnggoro/skill-for-lazy-developer/.agents/skills/lean-senior-engineering/SKILL.md

lean-senior-engineering

Skill1 starsChanged 7 days agoMITView on GitHub

Implement or review a clear code change using existing patterns and focused tests. Use when desired behaviour is known; route unexplained failures to systematic-debugging first.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Distinctive:

    Prefer the first adequate option:

    line 14
  2. Very specific:

    Use full by default. Honour a level requested in plain language for the current conversation.

    line 27
  3. Distinctive:

    Use short feedback cycles.

    line 38
  4. Distinctive:

    Run relevant existing checks after the final change.

    line 40
  5. Distinctive:

    Read review-and-debt.md for reviews, audits, and debt inventories.

    line 44

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Lean Senior Engineering

Deliver the requested behaviour with as little additional complexity as the codebase allows. Explicit user requirements and repository conventions take precedence over this skill. Minimum code means a complete, readable solution, including affected callers and tests.

Choose the change

Inspect the affected code, callers, and nearest tests. Expand the search only as dependencies require. Account for configuration, fixtures, exports, and contracts that must change with it.

Prefer the first adequate option:

  1. Existing behaviour or configuration that already solves the request.
  2. An existing project helper, component, service, or pattern.
  3. A standard library or native platform feature, when it fits project conventions.
  4. An already installed dependency.
  5. A small, direct implementation.
  6. A new dependency or abstraction, only when it solves a demonstrated need.

Readable code and correct behaviour outrank line count. Preserve validation, useful error handling, accessibility, compatibility, and data integrity. Avoid new options or extension points for hypothetical future features.

Work at the requested level

Use full by default. Honour a level requested in plain language for the current conversation; do not claim a persistent setting was saved.

  • lite: implement the user's chosen approach; mention a materially simpler option briefly when useful.
  • full: choose the smallest complete approach within the request.
  • ultra: challenge costly assumptions with concrete alternatives before substantial work; the user's explicit choice still wins.
  • off: stop applying this skill's preferences, retaining normal project instructions.

Implement and check

For a fix, establish the failing behaviour and inspect other callers of the changed code. For a feature, identify acceptance criteria before implementation. Do not turn clear, small requests into a design interview.

Use short feedback cycles. Add focused behaviour tests for meaningful logic or regression risk. Read test-design.md when choosing test boundaries, using mocks, or writing a regression test. Low-impact text or styling edits need proportionate inspection, not artificial tests.

Run relevant existing checks after the final change. Report their actual scope and outcome. Keep unrelated improvements out of the diff; mention a serious adjacent issue separately.

Review, audit, and debt requests

Read review-and-debt.md for reviews, audits, and debt inventories. These requests produce findings; implement only when the user also asks for changes.

Finish

Lead with the result. Include a short verification statement and material gaps. Never invent test execution, performance gains, token savings, or an independent review. A requested implementation is complete only when the requested behaviour and necessary checks are addressed or a concrete blocker is reported.

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.