Use when the requested outcome is unclear, silently changing, being reinterpreted by discoveries, or disconnected from the active implementation.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add ihabkhaled/AI-Psychiatry --skill goal-lock --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Goal Lock?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ihabkhaled-goal-lock)More formats (shields.io, HTML) on the badges page.
---
name: goal-lock
description: Use when the requested outcome is unclear, silently changing, being reinterpreted by discoveries, or disconnected from the active implementation.
---
# 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.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.