Your app
Agents break nearby features on small edits
Start with the first prompt. Each one says what proof the agent should bring back and when to skip it.
- Status hidden in a pile of flagsPromptFinds features whose real status is spread across a pile of yes/no flags, so combinations that should be impossible can happen.
- Meaning drift across the stackPromptShows where one word (a task, a fund, a run) means slightly different things in different parts of the app.
- Rules the data never enforcesPromptFinds the rules everyone assumes (one owner per task, no negative balance) that nothing actually checks.
- Out-of-date agent instructionsPromptFinds instructions that send agents to files and patterns that no longer exist.
Skills that help
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.engineering-kit·Matt Pocockgrill-meA relentless interview to sharpen a plan or design.engineering-kit·Matt Pocockgrill-with-docsA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.engineering-kit·Matt PococktddTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.engineering-kit·Matt PocockretroConduct a retrospective on a coding session.engineering-kit·Matt Pocock
Not quite your problem? See every symptom.