agentsclimarketplace

Estimation sizing

Skill janellecipriano/pm-skills/skills/estimation-sizing

Open-source Claude skills for Program Management in product development — charters, status reports, RAID logs, roadmaps, launch readiness, retros, postmortems, OKRs & more.

Install
npx -y skills add janellecipriano/pm-skills --skill estimation-sizing

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Facilitate estimation and turn sizes into a credible delivery forecast — T-shirt sizes or story points, assumptions, and a range rather than a false-precision date. Use when the user says "estimate this", "size these stories", "how long will this take", "story points", "give me a delivery range", or needs to convert scope into a defensible timeline.

SKILL.md

1.9 KB, as published. Nobody here has run it

Estimation & Sizing

Help a team size work honestly and translate sizes into a range, not a fake-precise date.

When to use

  • Sizing a set of stories/initiatives, or producing a delivery forecast from scope.
  • Sanity-checking an estimate that feels too confident.

Principles

  • Estimate relative size (T-shirt: XS/S/M/L/XL, or points) before absolute time.
  • Always estimate a range (optimistic / likely / pessimistic), never a single number.
  • Make assumptions explicit — every estimate rides on them.
  • Bigger = less certain. Break L/XL items down before committing.
  • Account for the non-coding tax: review, testing, integration, meetings, ramp-up.

Process

  1. Clarify scope per item; flag anything too vague to size (size = "needs breakdown").
  2. Assign a relative size and a confidence (H/M/L). Split low-confidence big items.
  3. Capture the assumptions behind each estimate.
  4. Convert to time using a stated velocity / throughput or size→days mapping — show the conversion.
  5. Roll up to a range and add buffer for risk/unknowns proportional to uncertainty.
  6. Present as "likely X, could be Y–Z" with the drivers of the spread.

Output format

| Item | Size | Confidence | Assumptions | Est. range |
| --- | --- | --- | --- | --- |

**Rollup:** likely {{X}}, range {{Y–Z}} ({{unit}})
**Key drivers of uncertainty:** {{...}}
**Assumptions:** {{...}}

Resist pressure for a single date — offer the range and the conditions under which the optimistic end holds.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.