CtrlK
BlogDocsLog inGet started
Tessl Logo

esmfold2

Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release: masked-LM logits, hidden states, mutation scoring, contact prediction, and the SAE interpretability head. MIT-licensed weights on HuggingFace org `biohub`. Use this skill when: (1) Predicting complex structures with single-sequence input, (2) Validating designed binders with ESMFold2-Fast, (3) Running ESMFold2 with MSA input, (4) Getting ESMC embeddings or per-residue mutation scores, (5) Choosing kernel backend and sampling-step settings for paper-faithful throughput.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 dense, action-oriented body with executable code throughout, well-organized sections, and clean one-level references for ESMC and design-hook detail. Minor conciseness trims and an explicit validation loop would push it higher.

DimensionReasoningScore

Conciseness

Mostly lean with dense tables, copy-paste install blocks, and minimal over-explanation; a few descriptive passages (e.g. SVD gotcha prose) could be trimmed but earn their place.

4 / 5

Actionability

Fully executable install commands, runnable Python fold() example with exact kwargs, and copy-paste monkeypatch code covering common cases.

5 / 5

Workflow Clarity

Install, usage, throughput, and MSA workflows are clearly sequenced with explicit gotchas and fallbacks; lacks a fully explicit validate-fix-retry loop, though batch sampling/seeds imply verification.

4 / 5

Progressive Disclosure

SKILL.md is a clear overview with well-signaled one-level-deep references (references/design-hook.md, references/esmc.md) for bulk detail; both referenced files exist and are appropriately split.

5 / 5

Total

18

/

20

Passed

Description

92%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 highly specific, well-structured description that explicitly covers both what the skill does and when to use it across ESMFold2 and ESMC models. Trigger phrasing is concrete and numbered, with minor room for broader synonyms.

DimensionReasoningScore

Specificity

Lists many concrete actions (single-sequence and MSA folding, masked-LM logits, hidden states, mutation scoring, contact prediction, SAE head) across protein/DNA/RNA/ligand inputs.

5 / 5

Completeness

Clearly states what it does and an explicit 'Use this skill when:' clause with five numbered trigger scenarios.

5 / 5

Trigger Term Quality

Covers natural terms like 'predicting complex structures', 'validating designed binders', 'embeddings', 'mutation scores', but lacks common synonyms/file extensions a user might say.

4 / 5

Distinctiveness Conflict Risk

A very specific niche (Biohub ESMFold2/ESMC) with concrete model names and benchmark figures, making overlap with other skills minimal.

5 / 5

Total

19

/

20

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.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
UnicomAI/wanwu
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.