agentleFS
Sign inStart free
sxntixgosxntixgo/frugal-skills/skills/software-development/SKILL.md

software-development

Skill0 starsChanged 4 months agoMITView on GitHub

Builds a backend or frontend feature end-to-end with a test-driven loop and DRY/YAGNI/KISS discipline. Use when implementing a feature, endpoint, component, or bugfix, or when asked to write/change production code.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. channingwalton/skills★ 2same name
    2. axross/skills★ 1same 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 repository11 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the TDD red→green→refactor loop (this skill owns the loop).

    line 16
  2. Distinctive:

    Add features nobody asked for (YAGNI) or design for hypothetical futures.

    line 20
  3. Very specific:

    Create a TodoWrite item per stage.

    line 25
  4. Very specific:

    Prefer extending existing patterns in the codebase over introducing new ones.

    line 37
  5. Distinctive:

    Run it; confirm it fails for the right reason.

    line 45
  6. Very specific:

    Run the tests AND exercise the actual behavior (invoke the endpoint, render the component, run the CLI) — not just a typecheck.

    line 61

≈ “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

Software Development

Build the smallest correct slice, test-first, then keep it simple. Follow the five stages in order; each is a checkpoint you can resume from.

Scope

This skill DOES:

  • Take a feature/bugfix from understanding → plan → TDD implementation → refactor → verify it runs.
  • Apply DRY, YAGNI, KISS at the refactor step.
  • Use the TDD red→green→refactor loop (this skill owns the loop).

This skill does NOT:

  • Enumerate or author the actual test cases → delegate that to writing-tests.
  • Add features nobody asked for (YAGNI) or design for hypothetical futures.
  • Skip running the code — "compiles" is not "works" (that's verify/run).

Workflow

Create a TodoWrite item per stage. Checkpoint each stage to ./.claude-skills-work/software-development/<task>/ (plan, decisions, progress) so work resumes if interrupted.

Stage 1 — Understand ⛔ STOP if unclear

Restate the task in one or two sentences: inputs, outputs, and the observable behavior that means "done". List unknowns. If a requirement is ambiguous or you'd be guessing at intent, STOP and ask — do not invent requirements (YAGNI).

Stage 2 — Plan the smallest slice

Pick the smallest end-to-end slice that delivers real behavior. Identify the one or few files to touch and the seams. Write the plan to the checkpoint file. Prefer extending existing patterns in the codebase over introducing new ones. For stack-specific guidance read references/backend.md or references/frontend.md now.

Stage 3 — TDD loop (red → green → refactor)

Repeat per behavior in the slice:

  1. Red — write a failing test for the next behavior. For WHICH cases to write (happy path, edges, boundaries, error paths), use writing-tests. Run it; confirm it fails for the right reason.
  2. Green — write the simplest code that makes it pass. No extra abstraction, no speculative options (KISS, YAGNI).
  3. Refactor — with tests green, clean up (see Stage 4 principles). Rerun tests. Commit-sized, behavior-preserving.

Stage 4 — Refactor for DRY / YAGNI / KISS

Apply after green, never at the cost of a failing test:

  • DRY — remove real duplication of knowledge. Don't over-DRY: two things that look alike but change for different reasons should stay separate.
  • YAGNI — delete anything not needed by a current requirement (unused params, config, hooks, "just in case" branches).
  • KISS — prefer the simplest thing that works; fewer moving parts, clear names, shallow nesting. If a reviewer would ask "why so complex?", simplify.

Stage 5 — Verify it runs

Run the tests AND exercise the actual behavior (invoke the endpoint, render the component, run the CLI) — not just a typecheck. If a project verify/run skill exists, use it. Report what you ran and what you observed.

Red flags (stop and correct)

If you notice…Do this
Writing code before a failing testStop; write the test first (Stage 3)
Building for a future requirementDelete it — YAGNI; add it when needed
A clever/complex solutionPrefer the simplest that passes (KISS)
Copy-pasting logic a third timeExtract the shared knowledge (DRY)
DRY-ing two things that just look alikeLeave them separate — coincidental duplication
Guessing an ambiguous requirementSTOP and ask
"It compiles / types pass, so it works"Actually run it (Stage 5)

Done when

  • The slice's behavior is covered by tests written test-first, and they pass.
  • Code satisfies DRY/YAGNI/KISS (no speculative or duplicated logic).
  • You ran the real behavior and observed it working.

References (load only when needed)

  • references/backend.md — backend concerns (APIs, data, errors, security seams).
  • references/frontend.md — frontend concerns (state, components, a11y, UX).

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.

Check your setup, free