Use when status is unclear, activity is high, completion estimates feel unreliable, or the agent may be mistaking reading, reasoning, tools, or churn for progress.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add ihabkhaled/AI-Psychiatry --skill progress-audit --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Progress Audit?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ihabkhaled-progress-audit)More formats (shields.io, HTML) on the badges page.
---
name: progress-audit
description: Use when status is unclear, activity is high, completion estimates feel unreliable, or the agent may be mistaking reading, reasoning, tools, or churn for progress.
---
# Progress Audit
## Core principle
Progress is completed requirements, removed blockers, passing relevant tests, delivered artifacts, and verified acceptance conditions.
## Procedure
1. Restate objective and finite DoD.
2. List completed and remaining requirements.
3. Name the last meaningful progress event.
4. Count repeated failures, reverted work, redundant tools, rereads, and scope growth.
5. Identify the actual blocker and highest-value next action.
6. Trigger recovery if outcomes stayed flat.
## Required output
Completed, remaining, blocker, repetitive activity, progress state, and one next action.
## Limits
Keep the audit concise; do not create a giant ledger.
## Common mistakes
Do not award progress for activity alone or fake precise percentages.
## Stop condition
Stop when the task is clearly advancing, stalled with recovery selected, blocked, or complete.
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.