CtrlK
BlogDocsLog inGet started
Tessl Logo

adaptyv

Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation.

65

Quality

57%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/adaptyv/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

N/A

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

Something went wrong

Implementation

57%

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

The skill has good structural organization with clear progressive disclosure to reference files, making it easy to navigate. However, it falls short on actionability by deferring too many critical details to reference files while including some unnecessary explanatory content that Claude already knows (protein optimization concepts, assay type descriptions). The workflow would benefit from explicit sequencing with validation steps for the submit-track-retrieve cycle.

Suggestions

Add a complete end-to-end workflow sequence (submit → check status → download results) with explicit validation checkpoints like checking HTTP status codes and handling errors.

Remove the explanatory descriptions of assay types and protein optimization issues that Claude already knows, and instead focus on the specific API parameters and formats needed for each.

Make the basic usage example more complete with response status validation, a status-checking polling loop, and result retrieval code.

DimensionReasoningScore

Conciseness

Mostly efficient but includes some unnecessary explanation (e.g., describing what each assay type does at a high level, explaining common protein issues Claude would already know). The bullet list of optimization issues and tool descriptions add moderate bloat.

2 / 3

Actionability

The basic usage code example is concrete and nearly executable, but the experiment submission payload uses placeholder values ('MKVLWALL...') and the request/response handling lacks error checking or a complete workflow. Key details like actual API endpoints, valid experiment_type values, and sequence format requirements are deferred to reference files.

2 / 3

Workflow Clarity

The authentication setup is sequenced clearly, but the overall workflow (optimize → submit → track → retrieve results) is only implied, not explicitly sequenced. There are no validation checkpoints (e.g., checking API response status codes, verifying sequence format before submission) despite this being a multi-step process involving external API calls.

2 / 3

Progressive Disclosure

Excellent progressive disclosure structure with a concise overview and well-signaled one-level-deep references to reference/experiments.md, reference/protein_optimization.md, reference/api_reference.md, and reference/examples.md. Content is appropriately split between the overview and detailed reference files.

3 / 3

Total

9

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

10

/

11

Passed

Repository
K-Dense-AI/claude-scientific-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.