This skill loads a compact rule set inspired by Robert C. Martin’s Clean Code. It tells a coding agent to write for local reasoning: precise names, small functions at one level of abstraction, explicit mutation and a readable happy path.
It is meant as a default for everyday implementation and code review, where working code is only the starting point.
What You Get
- A mini rule set with decision rules, trigger rules and a closing checklist for everyday coding
- A nano version for tight context budgets and a full version for reference
- A skill description that makes the agent load the rules for implementation and review tasks
Common Use Cases
- Splitting a function that mixes setup, validation, computation and side effects
- Renaming code whose vocabulary hides intent or forces comments to compensate
- Separating functions that both mutate state and return answers
- Reviewing a change for tests that protect the intended contract
What Makes It Unique
It is the smallest and most general of the repository’s rule sets, aimed at daily coding and review without architecture vocabulary. Its checklist ends with questions the agent must answer about its own work, including whether it removed at least one smell and whether it ran the relevant tests. It also limits cleanup to the smallest refactor that makes the requested change safe.
Under The Hood
The skill is a SKILL.md with a name and description, plus Markdown files holding the mini, nano and full versions of the rules. The SKILL.md tells the agent to read the mini file before design or code decisions and the full file only for harder tradeoffs. It contains no scripts. It does not fetch web pages, call APIs, run commands or write files; the agent only reads the rule text.