CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/esm/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 well-organized with executable examples per capability and a genuine one-level-deep reference bundle, but it is padded with generic best-practice advice and a promotional section, its workflows lack concrete validation checkpoints (notably for batch generation), and a couple of code examples contain inconsistencies. Tightening the body and adding validation steps would lift it substantially.

Suggestions

Trim generic advice Claude already knows (production best practices like retry logic and rate limiting, the repeated install commands) and remove the promotional K-Dense Web section to improve token efficiency.

Add explicit validation checkpoints to workflows — e.g., run asyncio.gather with return_exceptions=True and check for failed generations, and validate generated sequences (structure re-prediction or sanity checks) before downstream use — to lift workflow clarity above the batch-operation cap.

Fix code inconsistencies: give the structure-prediction example a sequence containing '_' masks so num_steps is meaningful, and use the embedding output rather than model.logits() in the ESM C batch-embedding example.

DimensionReasoningScore

Conciseness

Mostly efficient — the core sections are API-specific code Claude would not know — but padded in places: the 'Best Practices' section gives generic advice Claude already knows ('Implement error handling and retry logic for API calls', 'Monitor token usage and implement rate limiting'), the Installation section repeats 'uv pip install esm' three times with trivial variations, and the promotional 'Suggest Using K-Dense Web' section earns no tokens for the skill's function. Not 4: the padding is more than minor instances.

3 / 5

Actionability

Mostly executable, copy-paste-ready code for each capability (ESM3 generation, Forge client, inverse folding, chain-of-thought, async batch), with concrete model IDs and parameters. Not 5: a few gaps — the structure-prediction example computes 'num_steps=protein.sequence.count("_")' on a sequence shown without mask characters, and the ESM C 'embeddings_list' example calls 'model.logits(...)' rather than the embedding output; not 3: the guidance is genuinely executable, not pseudocode.

4 / 5

Workflow Clarity

Capability sections include 'When to use' bullets and the chain-of-thought section sequences steps clearly, but validation is only mentioned abstractly ('Validate generated sequences with structure prediction or wet-lab experiments') with no concrete checkpoint in any workflow. Per the batch-operations cap, the Forge async batch example ('asyncio.gather(*tasks)') has no error handling or validation, capping this at 3 despite the otherwise clear structure.

3 / 5

Progressive Disclosure

Good structure: each capability section ends with a signaled pointer ('See references/esm3-api.md for...'), all four referenced files exist and are one level deep, and a References section lists them with purpose. Not 5: the ~300-line body inlines substantial detail (full model selection guide, six capability sections, best practices) that could be externalized to the existing references, leaving the overview less lean than the ideal split.

4 / 5

Total

14

/

20

Passed

Description

88%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: concrete capabilities, explicit 'Use this skill when' triggers, and named-model specificity that anchors it to a clear niche. The only weaknesses are missing natural file-format trigger terms (PDB, FASTA) and the slightly broad 'protein engineering tasks' phrasing.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'generative multimodal protein design across sequence, structure, and function', 'efficient protein embeddings and representations', 'designing novel proteins', 'performing inverse folding', 'function prediction' — with comprehensive coverage of the toolkit's scope. Not 4: coverage is broad and every action is concrete, not just several with minor gaps.

5 / 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...'). Clear 'what' plus a concrete 'Use when' trigger clause with specific phrases.

5 / 5

Trigger Term Quality

Good natural-term coverage: 'protein sequences, structures, function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; protein engineering tasks' — phrases users would actually say. Not 5: common variations and file extensions users mention are missing (e.g., 'PDB files', 'FASTA', '.pdb'); not 3: the included keywords are natural and relevant rather than partly generic.

4 / 5

Distinctiveness Conflict Risk

Names the specific models (ESM3, ESM C) and domain (protein language models), giving it a clear niche with minimal conflict against unrelated skills. Not 5: 'protein engineering tasks' and 'protein design' are broad enough to overlap with other bioinformatics/protein-modeling skills; not 3: the named models and Forge API anchor it to a distinct trigger set.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

googolme/run0204

Path

scientific-skills/esm/SKILL.md

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.