| name | code-change-core |
| description | Use first for bounded code edits, refactors, implementation, simplification, control-flow cleanup, or maintainer clarity before choosing a more specific theory skill. |
Code Change Core
Use first for bounded code edits, refactors, implementation, simplification, control-flow cleanup, or maintainer clarity before choosing a more specific theory skill. This is a router skill: use it to select the
smallest relevant leaf skill, then read that leaf skill before doing the work.
Route First
Classify the code-change force first. Read exactly one primary leaf skill unless the task clearly spans two forces.
- Restate the user's task as one concrete force or uncertainty.
- Choose the first route that directly names that force.
- Read the selected linked leaf
SKILL.md before implementing, reviewing, or advising.
- Load a second leaf only when the task has two independent forces that both affect the outcome.
- If no route fits, continue without a leaf skill and say the category did not match.
Routes
| Leaf Skill | Use When |
|---|
programming-as-theory-building | Default for non-trivial code changes where domain rules must map to code behavior. |
essential-complexity | Use when simplification is requested and the risk is erasing real domain complexity. |
structured-programming | Use when the main problem is tangled branching, loops, exits, callbacks, or mutable control state. |
stepwise-refinement | Use when implementing a feature or algorithm from a high-level specification in small refinements. |
literate-programming | Use when the main problem is maintainer understanding, examples, comments, or explanatory order. |
Avoid
- If the dominant issue is API or module boundary ownership, route to boundary-and-modeling.
- If the dominant issue is tests, reliability, or proof, route to verification-and-reliability.
Prompting Pattern
Before loading a leaf, answer briefly:
- Category force: What makes this task belong here?
- Chosen route: Which leaf skill most directly matches the force?
- Why not others: Which nearby route was rejected and why?
Then load the chosen leaf skill and follow its workflow. Do not blend every
nearby theory into the task; route narrowly and let evidence pull in more context only when needed.
