fair-esm2

Use ESM2 protein language models for embeddings, mutation scoring, remote homology, or representation analysis. Use when a task needs protein embeddings, zero-shot variant scores, clustering, or sequence-function triage.

Quality

72%

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 ./skills/fair-esm2/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 is concise and well-structured as an overview, but it provides only abstract steps with no executable code or commands and no validation checkpoints, which limits actionability and workflow clarity.

Suggestions

Add at least one concrete, copy-paste-ready example (e.g. a Python snippet showing how to load an ESM2 checkpoint and produce embeddings) to lift actionability.

Insert explicit verification steps into the workflow (e.g. 'Confirm the checkpoint hash matches the expected version before running') to satisfy the validation-checkpoint requirement.

Specify the actual package/route names (model names, CLI commands, or API endpoints) rather than the generic 'local package, checkpoint, endpoint, or notebook route' phrasing.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence without explaining basic concepts, with only minor phrasing that could be tightened, fitting the 'efficient; minor instances' anchor rather than the perfectly lean 5.	4 / 5
Actionability	Guidance is high-level and abstract (e.g. 'Verify the local package, checkpoint, endpoint, or notebook route') with no executable code, commands, or specific API calls, matching the 'minimal concrete guidance; high-level hints' anchor.	2 / 5
Workflow Clarity	Steps are clearly sequenced but lack explicit validation checkpoints, and the judging guidelines cap batch/embedding-generating workflows without verification at 3.	3 / 5
Progressive Disclosure	For a short single-purpose skill with no bundle files, the well-organized sectioned overview meets the simple-skill exception for a top progressive-disclosure score.	5 / 5
	Total	14 / 20 Passed

Description

87%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 well-constructed description that names a specific domain and concrete capabilities and pairs them with an explicit 'Use when' trigger. It is concise, third-person, and low-conflict.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions (embeddings, mutation scoring, remote homology, representation analysis) with minor coverage gaps, matching the 'several specific actions; minor gaps' anchor rather than the comprehensive 5.	4 / 5
Completeness	Clearly states both what it does ('Use ESM2 ... for embeddings, mutation scoring ...') and an explicit 'Use when a task needs ...' trigger clause, matching the explicit what-and-when anchor.	5 / 5
Trigger Term Quality	Good natural keyword coverage including 'protein embeddings', 'zero-shot variant scores', 'clustering', but misses some synonyms and file-extension style terms that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (ESM2 protein language models) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 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: companion-inc/feynman
Path: skills/fair-esm2/SKILL.md
Commit: 95c51d9

Reviewed: about 9 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.