agentleFS
kazemcodeskazemcodes/skill-tree/skills/superpowers/SKILL.md

superpowers

Skill1 starsChanged 5 months agoMITView on GitHub

Enforce TDD, clean architecture, YAGNI, and evidence-based development from the Superpowers framework

15 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use context7 and 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.
  • JetBrainsSkill

    context7

    Up-to-date library and framework documentation via Context7 MCP. Use when setup, API, or version-specific questions require current documentation.

    Also in 4 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

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 13 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 13

    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:

    Write code before test? Delete it.

    line 16
  2. Distinctive:

    RED: Write one failing test. Watch it fail.

    line 20
  3. Distinctive:

    GREEN: Write minimal code to pass.

    line 21
  4. Distinctive:

    If test passes immediately → you're testing existing behavior → fix the test

    line 27
  5. Distinctive:

    Write minimal code to pass.

    line 28
  6. Distinctive:

    After green: remove duplication, improve names, extract helpers

    line 29
  7. Distinctive:

    Follow existing codebase patterns — never introduce alien abstractions

    line 46
  8. Distinctive:

    Remove unnecessary features ruthlessly

    line 51
  9. Distinctive:

    Don't add error handling for scenarios that can't happen

    line 52
  10. Distinctive:

    Don't add feature flags or backwards-compatibility shims

    line 53
  11. Distinctive:

    Verify before declaring success

    line 58
  12. Distinctive:

    Run tests and confirm — don't assume

    line 59
  13. Distinctive:

    When stuck: write wished-for API, write assertion first

    line 60

“Common” is measured: kept by at least 6 in 10 of the 12 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

Superpowers

Based on obra/superpowers. Non-negotiable engineering discipline.

TDD — Iron Law

NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST

Write code before test? Delete it. Start over. No exceptions.

RED → GREEN → REFACTOR

  1. RED: Write one failing test. Watch it fail. Confirm failure message is expected.
  2. GREEN: Write minimal code to pass. Don't add features, don't refactor.
  3. REFACTOR: Clean up while keeping tests green.

Rules

  • Watch EVERY test fail before implementing
  • If test passes immediately → you're testing existing behavior → fix the test
  • Write minimal code to pass. Nothing extra.
  • After green: remove duplication, improve names, extract helpers
  • "Tests after achieve the same goals" is FALSE

Red Flags — Delete and Restart

  • Code before test
  • Test passes immediately
  • "I'll test after"
  • "Too simple to test"
  • "Keep as reference"
  • "TDD is dogmatic"

Clean Architecture

  • Break systems into smaller units with one clear purpose
  • Communication through well-defined interfaces
  • Each unit: what does it do, how do you use it, what does it depend on?
  • Follow existing codebase patterns — never introduce alien abstractions
  • No stubs or placeholder code in production

YAGNI (You Aren't Gonna Need It)

  • Remove unnecessary features ruthlessly
  • Don't add error handling for scenarios that can't happen
  • Don't add feature flags or backwards-compatibility shims
  • Three similar lines > premature abstraction

Evidence Over Claims

  • Verify before declaring success
  • Run tests and confirm — don't assume
  • When stuck: write wished-for API, write assertion first
  • "Manually tested" ≠ comprehensive

Anti-Patterns

PatternWhy It's Wrong
Writing code before testsViolates iron law
Test passes immediatelyTesting existing behavior
Mocking without understandingHides real dependencies
"I'll test after"Proves nothing
Over-engineeringViolates YAGNI

Verification Checklist

Before marking done:

  • Every new function has a test
  • Watched each test fail before implementing
  • Each test failed for expected reason
  • Wrote minimal code to pass
  • All tests pass
  • Output pristine (no errors/warnings)
  • Tests use real code (mocks only if unavoidable)
  • Edge cases covered

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.