Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →cbrock84/schedule-development-and-analysis
Builds and interrogates a project schedule — logic-driven sequencing, dependency types and lags, float and the critical path, resource loading and leveling, schedule risk analysis, and measuring progress against a baseline rather than against optimism. Use this to construct a schedule, audit one you have inherited, find out why a plan keeps slipping, work out what a date change actually costs, or judge whether a reported percentage complete means anything.
Passed 18 of 24 test cases with the skill, and 16 of 24 without it.
and 1 more in the full report
4 fixed14 passed either way4 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
A project scheduler added a 14-day lag between the Final Code Freeze and System Integration Testing tasks because the team wanted to pad the schedule in case code freeze gets delayed. What is the appropriate usage of lag in network logic?
| Checked | Without skill | With skill |
|---|---|---|
| The response states that lag must represent concrete physical or procedural delay periods. | Passed | Passed |
| The response identifies using lag for date alignment as an unrecorded hidden assumption. | Missed | Passed |
The instructions your model reads when the skill loads.
A schedule is a model of how work connects. Most schedules in circulation are a list of dates someone typed, which looks the same in a status deck and behaves completely differently when anything moves.
Every task except the first and last should be connected to something. A task with a date and no predecessor is an assertion; a task with a predecessor is a plan, because when the predecessor moves the task moves with it and the schedule tells you so.
Hard-coded date constraints are where schedules go to die. Each one severs the logic at that point, so slippage upstream stops propagating and the schedule keeps reporting a date it can no longer support.
Float is how long a task can slip before it moves the end date. The critical path is the chain with none. Attention belongs there and almost nowhere else — expediting work with three weeks of float buys nothing and consumes the same management capacity.
Two readings worth taking regularly: near-critical chains, which become critical after one bad week and are where surprises come from, and negative float, which means the schedule is already telling you the date is impossible and someone has not looked.
A schedule that assumes the same three people work on five parallel tasks is fiction that will resolve itself as a delay. Load the named constraint — the one team, the one approver, the one environment — and level it. Leveling extends the schedule; that extension was always there, it was just unrecorded.
test cases passed, vs 16 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.