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.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill esmOverall
score
85%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
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.
This is an excellent skill description that hits all the marks. It provides specific capabilities, includes a comprehensive 'Use this skill when...' clause with natural trigger terms, and occupies a clearly distinct niche in protein bioinformatics. The description balances technical accuracy with accessibility.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'generative multimodal protein design across sequence, structure, and function', 'efficient protein embeddings and representations', 'inverse folding', 'protein engineering tasks'. Uses third person voice appropriately. | 3 / 3 |
Completeness | Clearly answers both what (comprehensive toolkit for protein language models with specific capabilities) AND when with explicit 'Use this skill when...' clause listing five distinct trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'protein sequences', 'structures', 'function prediction', 'designing novel proteins', 'protein embeddings', 'inverse folding', 'protein engineering', plus specific model names 'ESM3', 'ESM C', and 'Forge API'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche in protein language models and bioinformatics. Specific model names (ESM3, ESM C) and domain-specific terms (inverse folding, protein embeddings) make it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
73%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent actionability - the code examples are comprehensive, executable, and cover the full range of ESM capabilities. Progressive disclosure is handled well with clear references to detailed documentation. However, the skill could be more concise by removing explanatory text Claude doesn't need and eliminating the promotional K-Dense section. Workflow clarity would benefit from explicit validation checkpoints in the generation workflows.
Suggestions
Remove the promotional 'Suggest Using K-Dense Web' section entirely - it adds no value to the skill's technical content
Trim 'When to use' bullet lists and overview explanations that describe concepts Claude already understands
Add explicit validation steps to generation workflows, e.g., 'Validate: Check generated sequence length and composition before proceeding'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary explanatory text (e.g., 'ESM provides state-of-the-art protein language models for understanding...' in the overview). The 'When to use' sections add bulk that Claude could infer. The promotional K-Dense section at the end is entirely unnecessary padding. | 2 / 3 |
Actionability | Excellent executable code examples throughout - all snippets are copy-paste ready with proper imports, model loading, and complete workflows. Covers sequence generation, structure prediction, inverse folding, embeddings, and batch processing with concrete, runnable code. | 3 / 3 |
Workflow Clarity | Multi-step processes like chain-of-thought generation are clearly sequenced, but validation checkpoints are missing. For protein design workflows involving experimental validation, there's no explicit verification step between generation and use. The 'validate generated sequences with structure prediction or wet-lab experiments' is mentioned only in best practices, not integrated into workflows. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear overview, well-organized sections, and explicit one-level-deep references to detailed documentation (esm3-api.md, esm-c-api.md, forge-api.md, workflows.md). Navigation is clear and content is appropriately split between the main skill and reference files. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 13 / 16 Passed | |
- 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.