This skill gives a coding agent a set of working rules inspired by Andrew Hunt and David Thomas’s The Pragmatic Programmer. When a task touches engineering judgment, the agent reads a compact rule set and applies it to design and code decisions.
The rules cover knowledge-level DRY, orthogonality, tracer bullets, prototypes, automation, explicit contracts, error and resource handling, debugging from reproduced facts and the broken windows rule. A longer version of the same rules sits beside it for harder tradeoffs.
What You Get
- A compact rule set of decision rules, trigger rules and a final checklist that the agent loads when the skill applies
- A longer reference version of the same rules for tradeoffs the compact version does not settle
- A short nano version for very tight context budgets
- Review prompts that look for duplicated knowledge, hidden coupling, manual steps and slow feedback
Common Use Cases
- Reviewing a change that copies the same rule into the UI, API and database layers
- Starting a feature with a thin end-to-end slice before building every layer
- Turning a repeated manual release or setup routine into a versioned script
- Deciding whether a prototype can be hardened or must be thrown away
What Makes It Unique
Most book-based skills cover one narrow practice such as refactoring or architecture. This one is a general engineering layer: it spans DRY, orthogonality, feedback loops, contracts, resources, concurrency visibility and team habits in one rule set. Each trigger rule says what to do when a specific situation shows up, such as the same fact in several files or a prototype turning into production code.
Under The Hood
The skill is a short SKILL.md that tells the agent to read the compact rules file before making design or code decisions, and to open the full file only when the compact one does not settle a tradeoff. There are no scripts. It does not fetch web pages, call APIs, run commands or write files. The rules shape how the agent reasons and what it proposes.