python-skills
AGENTS.md0 starsChanged 5 months agoApache-2.0View on GitHub
Battle-tested Python skills, distributed as a Claude Code plugin. Built from custom engineering conventions. Blocks commits whose staged Python violates the skills, via Claude headless review. Note: this is an LLM review: non-deterministic and adds latency/token cost per commit. It catches judgment-level rules (cohesion, SOLID, hardcoded values) a linter cannot.
In this repository5 other files it gives its agents.
- python-anti-patternsSkill
- python-clean-codeSkill
- python-code-reviewSkill
- python-design-principlesSkill
- python-testing-tddSkill
The file
Files
python-skills plugin
Battle-tested Python skills, distributed as a Claude Code plugin. Built from custom engineering conventions.
Skills
| Skill | Trigger | Covers |
| python-clean-code | clean code, refactor, naming, comments, data classes, code smells | Line/function readability: naming, comments, classes-vs-functions, data types, smells, DRY/KISS/YAGNI |
| python-design-principles | SOLID, dependency inversion, coupling, strategy pattern | Class/module structure: SOLID, coupling/cohesion, Strategy |
| python-testing-tdd | write tests, pytest, TDD, fixtures, coverage | Red-Green-Refactor + quality pytest patterns |
| python-code-review | code review, review PR, pre-merge | Review Pyramid, priority-first review |
| python-anti-patterns | import order, file too long, hardcoded values, module constants | Custom module-organization rules |
Install in another repo
/plugin marketplace add <git-url-or-local-path-to-this-repo>
/plugin install python-skills@clean-pythonCommands
/python-skills:review-rules: reviews a Python diff (from stdin) against the skill rules and emitsVIOLATION:/NO_VIOLATIONS. Defined incommands/review-rules.md.
Pre-commit harness (per target project)
Blocks commits whose staged Python violates the skills, via Claude headless review.
- Install the plugin in the target project (above). Requires
claudeandjqon PATH. - Copy
assets/pre-commit.sh→.git/hooks/pre-commitin that project andchmod +xit. - On each commit it pipes the staged diff to
/python-skills:review-rules; violations block the commit. Bypass once withgit commit --no-verify.
Note: this is an LLM review: non-deterministic and adds latency/token cost per commit. It catches judgment-level rules (cohesion, SOLID, hardcoded values) a linter cannot.
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
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.

