Skip to content
Agentmart
Submit a tool

estimate

Estimate effort for a feature, plan, or backlog with explicit assumptions and confidence ranges — never a single confident number.

Skill by prestarius

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/prestarius-estimate

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Estimate effort for a feature, plan, or backlog with explicit assumptions and confidence ranges — never a single confident number. Use whenever the user asks "how long will this take", "estimate this", "size the backlog", "t-shirt sizes for these", or a plan/issue set needs effort attached before commitment.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/estimate

What's inside

Skill name
estimate
Description
Estimate effort for a feature, plan, or backlog with explicit assumptions and confidence ranges — never a single confident number. Use whenever the user asks "how long will this take", "estimate this", "size the backlog", "t-shirt sizes for these", or a plan/issue set needs effort attached before commitment.
License
MIT
Instructions
21 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Produce estimates a stakeholder can trust *because* the uncertainty is visible, not hidden.

1. **Decompose first.** Break the work into independently estimable items (reuse the
   Epic / US / Task numbering from the working agreement if the input is a backlog; if items are too vague to size,
   say which and why). Read `./CONTEXT.md` for the team's units and velocity conventions.
2. **Estimate per item, as a range.** Three-point (optimistic / likely / pessimistic) for
   anything consequential; T-shirt sizes only when the audience asked for rough order.
   State the unit explicitly (person-days, sprints) — never bare numbers.
3. **Surface what drives the spread.** List the assumptions each estimate rests on and the
   unknowns that dominate the pessimistic tail. Where one unknown dwarfs the rest, recommend
   a spike via the `prototype` skill to shrink it before anyone commits to the number.
4. **Aggregate honestly.** Sum the ranges, don't sum the likely values and call it the total.
   Give the total as a range with a stated confidence, and flag dependency chains where one
   slip cascades.
5. **State the invalidation conditions.** What change (scope, staffing, a discovered constraint)
   would void the estimate — so the reader knows when to ask again.

An estimate with no assumptions listed is a guess in a suit. If the input is genuinely
un-estimable, say so and name the one question that would change that.

From prestarius/jet-skills-stack, MIT.

More from prestarius/jet-skills-stack

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Sep 10, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/prestarius/jet-skills-stack
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from prestarius

Cite this page

estimate skill. Agent Mart. https://agentmart.dev/skills/prestarius-estimate (last updated 2026-10-24)