adaptyv

How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

80%Weight 40%Scale 1-5

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 and well-structured, offloading exhaustive endpoint detail to a reference file while keeping executable workflows inline. Its main weakness is workflow_clarity: batch submission of paid, long-running experiments proceeds without explicit validation checkpoints before cost-incurring or results-retrieval steps.

Suggestions

Add an explicit checkpoint before submit: verify the cost_estimate is acceptable and that target_id/sequences are correct before calling experiments.submit().

Insert a status guard before results retrieval: confirm the experiment's status is 'Done' (or results_status is not 'none') before calling experiments.get_results().

Add a validation note to the auto-accept-quote pipeline (workflow 2) warning to dry-run cost_estimate first, since skip_draft + auto_accept_quote commits cost without human review.

Tighten the opening paragraph: drop the 'Adaptyv Bio is a cloud lab...' framing and keep only the API/SDK facts Claude cannot infer.

Dimension	Reasoning	Score
Conciseness	Dense, non-obvious API specifics (s-expression filter grammar, lifecycle table, sequence rules) earn their tokens, but a framing intro paragraph ('Adaptyv Bio is a cloud lab...') and some narrative add minor over-explanation that could be trimmed — matching the score-4 anchor.	4 / 5
Actionability	Copy-paste ready curl, install commands, and full FoundryClient/decorator examples cover the common cases (browse, estimate, create, submit, retrieve, webhooks), matching the score-5 anchor; remaining placeholders are illustrative, not gaps.	5 / 5
Workflow Clarity	The submit workflow is clearly numbered, but for a batch/external operation (paid wet-lab experiments, ~21-day turnaround) it lacks validation checkpoints (e.g., confirm cost estimate before submit, verify status before get_results) — the rubric caps batch/destructive workflows without validation at 3.	3 / 5
Progressive Disclosure	SKILL.md is a clear overview with bulk endpoint detail offloaded to a one-level-deep, verified references/api-endpoints.md that is explicitly signaled, matching the score-5 anchor for well-organized, easily navigable structure.	5 / 5
	Total	17 / 20 Passed

Description

95%Weight 40%Scale 1-5

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 strong: it clearly states what the skill does, when to trigger it, and uses rich natural-language and code-level trigger terms in a distinctive niche. The only minor weakness is that the enumerated capability list is brief relative to the top anchor.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('protein experiment design, submission, and results retrieval') plus API/SDK and code-level triggers, but the action list is shorter than the score-5 anchor's multi-action enumeration, so it sits just below it.	4 / 5
Completeness	Explicitly answers 'what' (use the API and SDK for design/submission/retrieval) and 'when' ('Use this skill whenever the user mentions...') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural triggers with synonyms ('protein binding assays', 'BLI/SPR assays', 'thermostability assays'), code import triggers, and a domain URL — matching the score-5 anchor for synonym and extension coverage.	5 / 5
Distinctiveness Conflict Risk	A tightly scoped niche (Adaptyv/Foundry API, specific assay types, named imports, a specific domain URL) makes collision with other skills unlikely, matching the score-5 anchor.	5 / 5
	Total	19 / 20 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: K-Dense-AI/scientific-agent-skills
Path: skills/adaptyv/SKILL.md
Commit: b2a92ba

Reviewed: 3 days 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.