Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →romainsimon/planning-horizons
Decides how far ahead to plan, what to discount future payoffs by, and which backlog items can be dropped without analysis - using receding-horizon planning, an explicit discount factor, and branch-and-bound pruning against the incumbent.
Passed 20 of 22 test cases with the skill, and 7 of 22 without it.
and 24 more in the full report
15 fixed7 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our backlog candidates and baseline benchmark performance are saved in backlog.json. What shell command executes the branch-and-bound backlog triage script on this data?
| Checked | Without skill | With skill |
|---|---|---|
| Command invokes node scripts/calc.js prune backlog.json. | Missed | Passed |
The instructions your model reads when the skill loads.
Two chronic errors in roadmapping, and both are cheap to fix:
The organising principle is receding horizon planning: plan to depth d, execute the first step, then replan. You are not committing to the plan. You are using the plan to choose the next action.
- [ ] 1. Set the discount factor from a half-life you can defend
- [ ] 2. Find the depth where extra planning stops changing the first move
- [ ] 3. Prune the backlog against the incumbent
- [ ] 4. Evaluate the current plan before replacing it
- [ ] 5. Plan to that depth, commit only the first step, set a replan trigger
Do not argue about gamma. Argue about the half-life: how many periods until a payoff is worth half as much to us? Then convert.
node scripts/calc.js discount --half-life 6
That reports the effective horizon (1/(1-gamma)) - the point past which contributions
are noise - and the weight on payoffs at 1, 3, 6, 12 and 24 periods.
Defensible half-lives depend on your position, not your temperament:
| Position | Monthly half-life | Effective horizon |
|---|
test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.