agentleFS
WhosnooryWhosnoory/greenprint/.claude/skills/repro/SKILL.md

repro

Skill2 starsChanged 5 months agoMITView on GitHub

Use when asked to fix a bug, error, crash, or wrong/incorrect behavior. Reproduces the bug with a failing (RED) stdlib unittest BEFORE any source edit, registers it with Greenprint, and keeps the turn open until that test passes (GREEN). Required because Greenprint blocks source edits until a RED test exists.

6 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions6 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 6

    1. vaadin/web-components★ 585same name
    2. ucsandman/DashClaw★ 318same name
    3. getsentry/repro★ 2same name
    4. TestBeagle/TestBeagle★ 2same name
    5. tokyubevoxelverse/repro★ 1same name
    6. TPN-Labs/ClaudeSkills★ 0same 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 repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use Python's standard-library unittest only, no pytest, no pip, no extra deps.

    line 13
  2. Very specific:

    Only report the bug as fixed when this prints ALL GREEN.

    line 64

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

/repro: reproduce a bug with a failing test first

Greenprint will not let you edit source code to fix a bug until a test has failed for the right reason (proving the bug is real), and will not let you end the turn until that test passes (proving the fix works). This skill is how you satisfy that gate. No production code without a failing test first.

Use Python's standard-library unittest only, no pytest, no pip, no extra deps. Tests go in tests/test_repro_<symbol>.py.

Steps

  1. Identify the target. From the bug description, find the source file and the function/symbol that is wrong (e.g. app/cart.py, cart_total). Read it.
  2. Write a failing test at tests/test_repro_<symbol>.py that asserts the correct behavior, so it fails against the current buggy code. Import the target from the repo root. Template:

    import unittest
    from app.cart import cart_total  # adjust import to the real target
    
    class TestCartTotalRepro(unittest.TestCase):
        def test_includes_every_item(self):
            # Correct behavior: total is the sum of ALL prices.
            self.assertEqual(cart_total([10, 20, 30]), 60)
    
    if __name__ == "__main__":
        unittest.main()

    Writing the test file is allowed. Greenprint never blocks edits under tests/.

  3. Run it through Greenprint so the failure is verified and the guard is registered (pass the target file and symbol):

    python3 .claude/hooks/greenprint.py runtest tests/test_repro_<symbol>.py --target <path/to/source.py> --symbol <symbol>
    • GREENPRINT: RED registered → the bug is reproduced. Continue to step 4.
    • GREENPRINT: ERROR → the test could not run (import/syntax/runtime error). That is not a valid reproduction. Fix the test so it fails on an assertEqual/assert*, then re-run.
    • GREENPRINT: PASS → the test does not actually exercise the bug. Tighten the assertion so it fails against the current behavior, then re-run.
  4. Fix the source. Now edit the target file. Greenprint allows it because a guard covers that file.
  5. Confirm GREEN before you finish:

    python3 .claude/hooks/greenprint.py check

    Only report the bug as fixed when this prints ALL GREEN. If you try to end the turn while it is still RED, the Stop gate will send you back here.

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.