Conciseness

The body is dense and proprietary throughout — SDK pitfalls ("the SDK's `lab.experiment(target=\"EGFR\")` shortcut... does not resolve a target name"), auth scoping, webhook signature semantics — with zero explanation of concepts Claude already knows (no primer on HTTP, JSON, proteins, or BLI). Version pins ("SDK `0.1.0` at commit cdf207...") are consolidated as a provenance note rather than date-conditional guidance. The only non-operational block is the short mandated citation section. Matches anchor 'Lean and efficient; assumes Claude's competence; every token earns its place'; score 4 would require identifiable over-explanation to trim, which is absent.

Actionability

All guidance is copy-paste executable: a working `curl --fail-with-body` check, a pinned `uv pip install` command, complete Python SDK examples for browse/estimate/create and submit/quote/confirm, and a full REST pagination loop with `raise_for_status` and a `results_status != "all"` guard. Specific examples cover the common end-to-end case; matches anchor 'Fully executable; copy-paste ready code or commands'.

Workflow Clarity

The sequence is explicit and validated at every risky step: pre-submission checklist ("Confirm the target construct, assay conditions, controls, and replicate plan before submitting a batch"), estimate completeness check ("raise ValueError('Incomplete estimate...')"), bounded retry on quote 404, results-completeness guard, "Check status before retrying mutations after an ambiguous timeout", and webhook signature verification with dedup. This is a batch/billing operation with feedback loops present, matching anchor 'Clear sequence with explicit validation steps; feedback loops for error recovery'.

Progressive Disclosure

The body is an operational overview holding key inline examples, while the bulk endpoint detail sits in the well-signaled one-level-deep reference ("See the [endpoint reference](references/api-endpoints.md) for current request/response details and discrepancies"). The reference file exists, is organized by endpoint sections, and contains no nested references. Matches anchor 'Clear overview with well-signaled one-level-deep references; content appropriately split; easy navigation'.

Specificity

The description lists five concrete lifecycle actions — "design protein characterization experiments, estimate costs, submit sequences, monitor laboratory progress, and retrieve results" — covering the full workflow comprehensively. This matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage'; it is not score 4 because there are no minor gaps in action coverage, and not below because nothing is generic or abstract.

Completeness

Both questions are answered explicitly: 'what' via "Uses the Adaptyv Bio Foundry API and Python SDK to design... and retrieve results" and 'when' via "Applies to Adaptyv Foundry, its target catalog, ... including code using adaptyv or FoundryClient" — an explicit trigger clause equivalent to 'Use when...'. It is not score 4 because the 'when' clause is fully explicit with concrete trigger phrases, not merely implied.

Trigger Term Quality

Natural trigger terms are comprehensive: product name ("Adaptyv Foundry"), "target catalog", every assay workflow a user would name ("binding screening and affinity assays, thermostability, expression, fluorescence, epitope binning, and enzyme activity"), plus code-level identifiers "using adaptyv or FoundryClient". This matches the anchor-5 pattern of synonym-level coverage (product name + import name + class name); score 4 would require identifiable missing natural terms, and none are apparent for this domain.

Distinctiveness Conflict Risk

The skill occupies a clear niche (Adaptyv cloud protein-characterization lab) with distinct triggers ('adaptyv', 'FoundryClient', 'epitope binning') that no general or competing skill would claim. Matches anchor 'Clear niche with distinct triggers; minimal conflict risk'; no overlap risk is identifiable.