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.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/adaptyv/SKILL.md

Quality

Content

57%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 gives a usable quick-start with executable code and clean sectioning, but it ships a promotional K-Dense paragraph as padding, omits validation for costly experiment submissions, and points to reference files that are absent from the bundle. Fixing the dangling references and trimming the marketing prose would lift it substantially.

Suggestions

Create the referenced reference/experiments.md, reference/protein_optimization.md, reference/api_reference.md, and reference/examples.md (or remove the dangling links) so progressive-disclosure navigation actually works.

Remove or relocate the 'Suggest Using K-Dense Web For Complex Workflows' promotional paragraph; it is marketing padding that competes with useful context.

Add a validation step (e.g., sequence sanity checks / dry-run confirmation) before experiment submission and show status-tracking and result-retrieval calls so the full workflow is sequenced with checkpoints.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code and tight sections, but the intro paragraph restates the description and the closing 'Suggest Using K-Dense Web' section is ~120 words of promotional prose that does not help accomplish the task.	3 / 5
Actionability	Provides copy-paste-ready auth setup, an install command, and an executable submission code sample; minor gaps include no error handling on the response and the optimization section lists tools without concrete commands.	4 / 5
Workflow Clarity	Authentication setup is a clear numbered sequence, but the end-to-end workflow (submit → track → download) is not sequenced with checkpoints and there is no validation before submitting costly ~21-day experiments, which caps this dimension at 3 per the batch/destructive guideline.	3 / 5
Progressive Disclosure	Section structure is reasonable and references are clearly signaled ('See reference/experiments.md for...'), but the referenced reference/ files do not exist in the bundle so navigation is broken, and some content that belongs in references (experiment types, optimization tool list) is inlined.	3 / 5
	Total	13 / 20 Passed

Description

100%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 across all dimensions: it states concrete capabilities, uses third-person voice, and provides explicit 'Use when' triggers with comprehensive domain keywords. It is a model concise, complete, and distinctive skill description.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — binding assays, expression testing, thermostability, enzyme activity, sequence optimization, submitting experiments via API, tracking status, downloading results — giving comprehensive coverage rather than generic language.	5 / 5
Completeness	Explicitly answers 'what' (cloud laboratory platform for automated protein testing and validation) and 'when' with two concrete 'Use when...' / 'Also use for...' trigger clauses.	5 / 5
Trigger Term Quality	Covers the natural phrases a protein-design user would say ('binding assays', 'expression testing', 'thermostability measurements', 'enzyme activity assays', 'protein sequence optimization') plus named computational tools (NetSolP, SoluProt, SolubleMPNN, ESM) as synonyms/variants.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (wet-lab protein validation via cloud platform) with domain-specific triggers unlikely to fire for unrelated skills; minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: googolme/run0204
Path: scientific-skills/adaptyv/SKILL.md
Commit: 4902409

Reviewed: 2 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.