Conciseness

Much of the body is genuinely useful reference data (FPA weight matrices, T-shirt size tables, adjustment-factor percentages), but it also explains concepts Claude already knows: 'Variance V = σ²', a confidence-interval table restating the empirical rule (68.3% = ±1σ, 95% = ±2σ), and definitions like 'O (Optimistic): Shortest duration assuming everything goes smoothly'. Mostly efficient with some unnecessary explanation that could be tightened, matching anchor 3 rather than the noticeably-padded anchor 2 or the minor-trim anchor 4.

Actionability

The three script invocations for PERT, tshirt, and fpa are copy-paste ready with complete JSON payloads, and I verified the bundled scripts/estimate_calculator.py implements exactly these flags and value tables. Together with the method-selection table, concrete thresholds (e.g., 'O should not be less than 30% of M'), and a fill-in output template, the common cases are fully covered — the top anchor.

Workflow Clarity

The Quick Start gives a clear 4-step sequence, each method has numbered steps, and the O/M/P rules of thumb and adjustment-factor checklist function as verification checkpoints. However, there is no explicit feedback loop (e.g., 'if spread ratio > 4, clarify requirements and re-estimate'), so it fits anchor 4 (most checkpoints present, minor gaps) rather than anchor 5's explicit validate-then-retry pattern.

Progressive Disclosure

The single bundle file (scripts/estimate_calculator.py) is clearly signaled with executable usage in two places, and the body is well-sectioned with a navigation-friendly method-selection table up front. Scored against the actual bundle (one script, no references/), the remaining gap is that ~290 lines of FPA DET/RET lookup matrices and T-shirt conversion tables are inlined where a references/ file would keep the overview lean — good structure with minor organization gaps, i.e., anchor 4 not 5.

Specificity

Enumerates multiple concrete capabilities covering its full method space: 'Outputs three-point estimates (optimistic/most-likely/pessimistic values with confidence intervals), T-shirt sizes, or Function Point Analysis (FPA) counts.' All three supported methods are named with their concrete outputs, matching the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.

Completeness

Explicitly answers both questions: what it does ('Outputs three-point estimates... confidence intervals... FPA counts') and when to use it via a concrete 'Triggered when users ask...' clause with quoted trigger phrases. This matches the anchor requiring clear and explicit what AND when with concrete trigger phrases.

Trigger Term Quality

Contains natural phrases a user would actually say — "how long will this feature take", "assess project workload" — plus methodology keywords 'PERT estimation, T-shirt sizing, FPA, sprint planning, or quote-based effort breakdowns'. Coverage includes a verbatim user utterance, synonyms, and all methodology names, so it sits at the top anchor rather than merely 'good coverage with a few missing'.

Distinctiveness Conflict Risk

The effort-estimation niche with method-specific triggers (PERT, FPA, T-shirt sizing) is clearly distinct, but 'sprint planning' and 'assess project workload' are broad phrases that could overlap with general agile-planning or project-management skills — minor overlap risk with closely related skills, fitting the anchor 4 rather than 5.