project-recoverylisted
Install: claude install-skill teodstr/workbench
# Project recovery
A late project rarely recovers by working harder on the same plan. This skill measures the real gap, finds why it happened, and puts honest options in front of the person who decides.
## When to use
- When a milestone slipped or the budget is going beyond its reserve.
- When the people involved no longer believe the plan.
- Not for a single new request that changes the scope: use `scope-change`.
## Inputs
1. The current plan, the budget and what has been done.
2. The latest status (`status-update`) and the risk register.
3. The fixed constraints: dates that cannot move, money that cannot grow.
## Method
1. **Stop and measure**: remaining work re-estimated from scratch by the people doing it, against the time and money left. No "we will catch up".
2. **Find the causes**: underestimated work, scope that grew, missing people or skills, external delays, decisions that were not made. Ask "why" until the cause is something that can be acted on.
3. **List the options**, usually a mix of: cut or postpone scope (deliver the essential first), move the date, add money, change the approach (simplify, buy instead of build, outsource), stop the project. Adding people late tends to slow work down in the short term, as Brooks observed for software teams: check whether the newcomers can be useful quickly.
4. **Compare them** on time, cost, quality and risk (`decision-making`), and recommend one.
5. **Decide with the decision owner**, then rebuild the schedule and the