This skill loads a compact rule set inspired by Steve McConnell’s Code Complete. It tells a coding agent to treat construction quality as a deliberate choice: cohesive routines, purpose-revealing data, simple control flow and checks at trust boundaries.
It applies to implementing, reviewing, debugging, refactoring or tuning production code where defect risk matters.
What You Get
- A mini rule set with decision rules, trigger rules and a closing checklist for construction work
- A nano version for tight context budgets and a full version for reference
- A skill description that makes the agent load the rules for routine, class and implementation tasks
Common Use Cases
- Designing a routine that is hard to name or mixes setup, validation and side effects
- Deciding what to validate, assert or reject where input crosses a trust boundary
- Debugging by reproducing, isolating and explaining a failure before changing code
- Replacing repeated branching with a validated table
What Makes It Unique
It covers the whole construction loop in one rule set: preparation, routine and data design, defensive handling, integration, debugging, tuning and layout. It asks for pseudocode or intent comments on complex routines and for evidence before performance work, with a measure before and after. The scope is wider than the repository’s readability-focused rule set.
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.