esm

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/biology/esm/SKILL.md

Quality

Content

65%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.

A well-structured, actionable skill body with excellent progressive disclosure and concrete code, but it is somewhat verbose and its generation/batch workflows lack explicit validation checkpoints.

Suggestions

Trim padded sections (Best Practices prose, Resources/blog links, repeated install variants) to improve token efficiency.

Add explicit validation/verification checkpoints to generation and Forge batch workflows (e.g., validate generated sequences, verify batch results for errors) to lift workflow clarity.

Make each code example self-contained by defining or noting the 'model' variable and replacing the '<token>' placeholder with a comment on how to supply it.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and code-driven without explaining concepts Claude already knows, but the ~300-line body includes padded sections (Best Practices prose, Resources/blog links, repeated installation variants) that could be trimmed; not 4 because the padding is noticeable, not 2 because it is not heavily padded with concept explanations.	3 / 5
Actionability	Provides multiple concrete, executable code examples with specific imports and model names across the main capabilities; not 5 because several examples assume a 'model' variable defined in earlier sections and use a '<token>' placeholder, so they are not fully self-contained copy-paste ready.	4 / 5
Workflow Clarity	Capability sections are sequenced with 'When to use' and code, and chain-of-thought shows a 3-step refinement, but batch/generation workflows lack explicit validation or verification checkpoints; per the rubric, missing validation in batch operations caps this at 3.	3 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references to real files (esm3-api.md, esm-c-api.md, forge-api.md, workflows.md), each annotated with its contents, making navigation easy and content appropriately split.	5 / 5
	Total	15 / 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 strong description that clearly states capabilities and provides explicit, concrete trigger guidance for when to use the skill. Minor room to sharpen specificity and add common synonyms/file extensions.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('designing novel proteins; generating protein embeddings; performing inverse folding'), matching the 'lists several specific actions; minor gaps' anchor; not 5 because 'protein engineering tasks' is somewhat generic, not 3 because there are clearly more than 1-2 concrete actions.	4 / 5
Completeness	Explicitly answers both what ('Comprehensive toolkit for protein language models including ESM3... and ESM C...') and when ('Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases ('protein sequences, structures, function prediction', 'designing novel proteins', 'inverse folding') with good coverage; not 5 because file extensions/synonyms like .fasta or PDB are absent, not 3 because coverage is clearly good rather than partial.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (ESM protein language models) with distinct, domain-specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 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/biology/esm/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.