project-sizing-guide

Software project effort estimation assistant. Outputs three-point estimates (optimistic/most-likely/pessimistic values with confidence intervals), T-shirt sizes, or Function Point Analysis (FPA) counts. Triggered when users ask 'how long will this feature take,' need to assess project workload, perform PERT estimation, T-shirt sizing, FPA, sprint planning, or quote-based effort breakdowns.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable tooling and clear sequenced workflows, but it is dense and inline-heavy: large FPA reference tables and some basic PERT definitions pad the token budget and would benefit from progressive disclosure into a separate reference file.

Suggestions

Move the FPA complexity weight matrices (DET/RET and DET/FTR tables) and the five-component reference into a `references/fpa-guide.md` file, keeping SKILL.md as an overview with a one-level-deep link.

Trim basic PERT definitions (e.g., the O/M/P "shortest/normal/longest duration" glosses) that Claude already knows, retaining only the non-obvious rules of thumb like the 30%/5× spread thresholds.

Consider extracting the full Estimation Output Template and Adjustment Factor Checklist into a bundled template file to reduce the SKILL.md body length.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference material, but restates concepts Claude already knows (e.g., "O (Optimistic): Shortest duration assuming everything goes smoothly" and basic PERT confidence-interval explanations), and the dense FPA complexity matrices could be tightened or moved off-page.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands for the bundled `scripts/estimate_calculator.py` (verified to exist) across all three methods, plus a concrete output report template.	3 / 3
Workflow Clarity	Each method has a clearly numbered step sequence and an Adjustment Factor Checklist that serves as an explicit checkpoint; estimation is analytical rather than destructive, so no validation-feedback cap applies.	3 / 3
Progressive Disclosure	One script bundle is present and clearly signaled, but the SKILL.md is a monolithic wall of inline FPA complexity weight tables and DET/RET matrices that would be better split into a separate reference file rather than kept inline.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and clearly distinguishes what the skill does from when to invoke it, all in third person. It is among the strongest patterns in the reference set.

Dimension	Reasoning	Score
Specificity	Names multiple concrete outputs — "three-point estimates (optimistic/most-likely/pessimistic values with confidence intervals), T-shirt sizes, or Function Point Analysis (FPA) counts" — matching the anchor for several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (estimation outputs) and when via an explicit "Triggered when users ask..." clause, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Uses natural phrasing a user would actually say — "how long will this feature take," "sprint planning," "T-shirt sizing," "quote-based effort breakdowns" — giving good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (software effort estimation) with distinct triggers and third-person voice, making conflict with other skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zebbern/claude-code-guide
Path: skills/project-sizing-guide/SKILL.md
Commit: af7d491

Reviewed: about 9 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.