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

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/ml-training/adaptyv/SKILL.md

Quality

Content

55%

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

The body provides a usable quick-start snippet but is weakened by deferred references to files that are absent from the bundle, missing status/retrieval examples, and no validation checkpoints for the long-running experiment workflow. Conciseness is decent but includes some redundant prose.

Suggestions

Add the referenced bundle files (experiments.md, protein_optimization.md, api_reference.md, examples.md) under a references/ directory, or remove the dangling pointers and inline the essential content.

Include executable examples for experiment status tracking and result retrieval rather than only the submission call, since those are core workflow steps.

Add validation/error-handling checkpoints (e.g., verify the submission response, poll status, handle failed experiments) to clarify the long-running experiment workflow.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code and short sections, but it restates platform basics ('cloud laboratory platform that provides automated protein testing...') already in the description and includes advisory prose ('Common issues to address') that pads the body. It could be tightened toward the lean anchor.	2 / 3
Actionability	The submission example is concrete and executable, but it omits status-tracking/result-retrieval code (deferred to reference files that do not exist in the bundle) and the optimization section only lists tool names without any runnable commands or invocation examples, leaving guidance incomplete.	2 / 3
Workflow Clarity	Authentication and submission steps are sequenced, but for a workflow involving long-running (~21 day) batch experiments there are no validation/status-checking checkpoints, error-handling feedback loops, or explicit sequencing for tracking and retrieving results, capping workflow clarity at 2.	2 / 3
Progressive Disclosure	The body references `reference/experiments.md`, `reference/protein_optimization.md`, `reference/api_reference.md`, and `reference/examples.md`, but no `references/` directory or any bundle files exist in the skill, so the signaled navigation points are missing and the progressive disclosure structure is broken.	1 / 3
	Total	7 / 12 Passed

Description

100%

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 specific, complete, and clearly distinguishes a niche wet-lab protein validation platform with concrete actions and natural trigger terms. It models third person voice and answers both what and when explicitly.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions: binding assays, expression testing, thermostability measurements, enzyme activity assays, and sequence optimization via specific named tools (NetSolP, SoluProt, SolubleMPNN, ESM), matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly states both what the platform does ('automated protein testing and validation') and when to use it ('Use when designing proteins and needing experimental validation including...'), satisfying both the 'what' and 'when' with explicit triggers.	3 / 3
Trigger Term Quality	Uses natural terms a user would say ('designing proteins', 'binding assays', 'expression testing', 'thermostability measurements', 'enzyme activity assays', 'protein sequence optimization'), giving good coverage of the domain vocabulary.	3 / 3
Distinctiveness Conflict Risk	The wet-lab protein validation niche with specific assay types and named computational tools is highly distinctive and unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/ml-training/adaptyv/SKILL.md
Commit: 52845c3

Reviewed: about 11 hours 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.