CtrlK
BlogDocsLog inGet started
Tessl Logo

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`.

72

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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, with the bulk API reference correctly split into a one-level-deep bundle file. Its main weakness is workflow clarity: the submission workflow is a costly batch operation without explicit validation checkpoints or error-recovery feedback loops.

Suggestions

Weave an explicit validation checkpoint into the binding-screen workflow, e.g. 'Review the cost_estimate output; only call create/submit when the estimate is acceptable', and add an error-recovery loop (on error, inspect request_id and retry).

Tighten the auth section and trim the citing section (e.g., move the full citation instructions behind a short pointer) to remove minor verbosity and time-sensitive padding.

Add a brief note on how to validate retrieved results (e.g., checking results_status for none/partial/all) as a final verification step before reporting back to the user.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete code and domain-specific context (lifecycle states, s-expression filters) that Claude would not already know; minor over-explanation in the auth/.env prose and a verbose citing section with time-sensitive version/year details slightly pad it.

4 / 5

Actionability

Fully executable, copy-paste-ready curl and Python snippets covering the common cases — decorator and client patterns, cost_estimate, create, submit, get_results, and a numbered end-to-end binding-screen workflow with real field names.

5 / 5

Workflow Clarity

A clear numbered sequence (find target, preview cost, create, submit, poll, retrieve) is present with a lifecycle map, but the create/submit workflow is a costly batch operation lacking explicit validate-then-proceed feedback loops, so the batch-validation cap holds.

3 / 5

Progressive Disclosure

The body is a well-sectioned overview that offloads the full 32-endpoint reference to a clearly signaled, one-level-deep references/api-endpoints.md (verified present), keeping only key examples inline and making navigation easy.

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.

A strong, third-person description that crisply states both the skill's purpose and a thorough set of natural and code-level triggers. It is specific and highly distinctive with negligible conflict risk.

DimensionReasoningScore

Specificity

Names concrete actions — 'protein experiment design, submission, and results retrieval' — via both API and Python SDK, covering the core workflow, but omits adjacent actions (cost estimation, quote acceptance, token attenuation) leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what ('How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval') and when ('Use this skill whenever the user mentions... Also trigger when code imports...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural terms including synonyms and product-specific identifiers: 'Adaptyv', 'Foundry API', 'protein binding assays', 'BLI/SPR assays', 'thermostability assays', plus code imports 'adaptyv', 'adaptyv_sdk', 'FoundryClient' and the API domain.

5 / 5

Distinctiveness Conflict Risk

Clear niche around a named commercial product with distinctive triggers (specific API host, SDK imports, assay types); minimal risk of triggering for unrelated skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-skills
Reviewed

Table of Contents

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.