Claude Skills by elitongadotti

Audit a ticket's acceptance criteria against what the branch actually implements. Every item must be satisfied, and each must semantically match the implementation. Never edit or drop a criterion without the user's agreement.

Before picking new work, smoke-test the last "completed" feature. If it's broken, revert and re-open it before touching anything else. Kills the "looks shipped, isn't shipped" bug across sessions.

Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.

Catch secrets, PII, and non-public context in a diff before it is committed or published. Use before any commit, and before pasting output anywhere public.

Write a PR description a reviewer can approve fast. Use when opening any pull request.

Write and review PySpark against Iceberg tables — schema discipline, native functions over UDFs, correct write mode, and table maintenance.

Extract the actual cause from a stack trace instead of pattern-matching the error type. Use on any crash or exception.

Write and read the between-session handoff file so a fresh agent with no memory can pick up where the last one stopped without re-deriving context. Structured prose, not JSON — the model writes prose better.

Write the goal spec on disk before the agent acts, so it can't drift. Use before any multi-step task.

Review SQL and ORM queries for correctness, safety, and performance before they ship.

Routing rules for the cockpit skills. Auto-injected at session start so the other skills trigger reliably. Read first.

Write a commit message that describes the focus of the change, not its supporting work. Use when committing.