write-code
/write-code
Adds or changes Python code in this repo, with a test, then formats, lints and tests it. Use when asked to add a feature, fix a bug or refactor.
- Author
- frankcaron ↗
- Repository
- claude-triage-agent ↗
- Licence
- MIT
- Last repository change
- 10.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 10.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Adds or changes Python code in this repo, with a test, then formats, lints and tests it. Use when asked to add a feature, fix a bug or refactor.
Arguments
/write-code [change to make]
Original author description
Adds or changes Python code in this repo, with a test, then formats, lints and tests it. Use when asked to add a feature, fix a bug or refactor.
How it works
SKILL.md has no level-two headings · 15 lines, 213 words
SKILL.md preview
---
name: write-code
description: Adds or changes Python code in this repo, with a test, then formats, lints and tests it. Use when asked to add a feature, fix a bug or refactor.
argument-hint: "[change to make]"
---
# Write code
Change: $ARGUMENTS
1. Understand the change requested and the context in the code.
Ask discovery questions against requirements before outright attempting a fix. Work to ascertain how the code is meant to function relative to the bigger business context around the application.
2. Read the code you'll touch. Say in two lines what you'll change and which files.
If the change touches prompts/, runbooks/, incidents/ or .claude/, or needs a new dependency, STOP and ask first.
3. Make the smallest change that does it, following the Python rules.
4. Add a test in tests/ for the new behaviour, following the testing rules.
5. Run `ruff format <new files>`, `ruff check <new files>` and `python -m pytest tests -q`. Fix the code, not the test, until they pass. Three failed tries: STOP and show the failure.
6. Run the code-reviewer agent on the changed code outside tests/, passing each file and its changed lines. Show its findings and suggested fixes. Don't apply them without the human's OK.
7. Then run the test-reviewer agent on the tests you added, passing along any behaviours code-reviewer said the tests should cover.
8. Reply with one line per file changed, the test result and both reviews. Don't commit or push. The human reviews the diff.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · frankcaron/claude-triage-agent | 86 | MIT |
| rowansci/rowan-python | 100 | MIT |
| JamieMason/syncpack | 100 | MIT |
Database snapshot: 13.11.2026 · package version 01e0ca144014 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100python-code-style
Writes, reviews, formats, and lints Python code against shared style and language standards with Ruff. Use when writing, reviewing, refactoring, or modernizing Python code; adding type annotations, docstrings, or unit tests; fixing lint or formatting issues; configuring Ruff in… - 100tdd
Red-green-refactor procedure: write the failing test first, show it fail, write the minimum code, refactor on green. Use for any bug fix or new behavior in code that has or could have tests, including 'fix this bug', 'add a function', 'use TDD' and 'write the test first'. - 100tdd
Test-driven development: red-green-refactor, one test per cycle. Use when the task asks to build a feature, fix a bug or change behaviour, before you write the code. - 100test-driven-development
Use when implementing any feature, bugfix, refactor, or behavior change, before writing the implementation code — write the failing test first, watch it fail, write minimal code to pass, then refactor. Also use when writing or changing tests, adding mocks, or when code feels… - 100test-driven-development
Use when implementing any feature, bug fix, refactor or behavior change, before writing implementation code. Write the failing test first, watch it fail, then write the minimal code to pass. - 100ruff-check
Lints and formats all Python files in the project using Ruff. Activates when the user asks to "lint my Python", "fix Python code style", "run ruff", "format my Python files", "check Python quality", or "fix linting errors". Installs Ruff if not present, auto-fixes resolvable…