Goal Lock

Use when the requested outcome is unclear, silently changing, being reinterpreted by discoveries, or disconnected from the active implementation.

ihabkhaled ee82294 1.1 KB Updated

File contents

Goal Lock

Core principle

Discoveries do not mutate the user’s objective; only explicit user direction or a proven blocker or required condition may change execution.

Procedure

  1. Quote or precisely restate the requested outcome.
  2. Define observable success and the minimum DoD.
  3. List included and excluded scope.
  4. Connect the active work item to one DoD condition.
  5. Compare every proposed branch with the locked goal.
  6. Request direction only when a real conflict cannot be resolved from evidence.

Required output

Objective, success, DoD, scope, out-of-scope, and the active requirement.

Limits

One primary objective; local plan updates may not redefine it.

Common mistakes

Do not promote an interesting defect, architecture concern, or optional improvement into the goal.

Stop condition

Stop when the objective is stable and every active action maps to a required outcome.

ihabkhaled/AI-Psychiatry/tree/main/.ai/skills/goal-lock commit ee822945f6

Frequently asked questions

npx skillmds@latest add ihabkhaled/goal-lock