aglabo/deckrd

Method-level agent that defines decision rules for BDD implementation. Handles tests at the assertion level rather than file level, and enforces strict RED→GREEN→REFACTOR phased implementation based on the '1 message = 1 test' principle.

your goals to tasks framework

Deckrd task implementation skill - extracts specified tasks from tasks.md and implements them using strict BDD process. Internally applies bdd-coder decision rules.