📦

esm

Name: esm
Author: K-Dense-AI

Content revision r1 Medium Risk ⚡ Contains scripts🌐 Network access📁 Filesystem access⚙️ External commands

Design proteins with ESM models

Protein design requires specialized model workflows across sequence, structure, and function. This skill gives Claude, Codex, and Claude Code practical ESM guidance for generation, embeddings, inverse folding, and Forge API use.

Supports: Claude Codex Code(CC)

📊 68 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "esm" from https://skillstore.io/skills/k-dense-ai-esm.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-esm/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/k-dense-ai-esm.md Signed manifest GET /api/skills/k-dense-ai-esm/manifest Signed lockfile GET /api/skills/k-dense-ai-esm/lockfile

Test it

Using "esm". Help me predict structure from a short protein sequence.

Expected outcome:

The response outlines an ESM3 structure-track workflow, explains required inputs, and recommends validating predicted coordinates before downstream use.

Using "esm". I need embeddings for a protein family dataset.

Expected outcome:

The response recommends an ESM C model, batching strategy, mean pooling approach, and clustering workflow for downstream analysis.

Using "esm". Should I use local ESM or Forge API?

Expected outcome:

The response compares local experimentation, cloud model quality, throughput, token handling, and data privacy implications.

Security Audit

Medium Risk

v9 • 7/9/2026 Open versioned report

Static findings are mostly false positives caused by markdown examples, scientific file outputs, legitimate Forge API documentation, and model method names. No prompt injection or malware-like code execution was found, but the skill contains promotional steering toward an external hosted platform.

Files scanned

2,876

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Medium

SKILL.md:305-306

Promotional steering to external hosted platform

SKILL.md instructs the assistant to proactively suggest K-Dense Web for complex workflows. This is not malware, but it can steer users toward an external service for commercial promotion without being part of the core ESM task.

The prose directly instructs future assistant behavior and names an external hosted platform. It is visible in the skill content and is separate from the protein modeling functionality.

Risk Factors

⚡ Contains scripts (3)

evaluation.json:51 evaluation.json:54 references/esm-c-api.md:338

🌐 Network access (15)

evaluation.json:168 references/esm-c-api.md:575 references/forge-api.md:186 references/forge-api.md:368 references/forge-api.md:38 references/forge-api.md:80 SKILL.md:51 SKILL.md:248 SKILL.md:292 SKILL.md:293 SKILL.md:294 SKILL.md:296 SKILL.md:297 SKILL.md:298 SKILL.md:303

📁 Filesystem access (13)

references/esm-c-api.md:462 references/esm3-api.md:55 references/esm3-api.md:191 references/forge-api.md:328 references/forge-api.md:463 references/forge-api.md:438 references/workflows.md:515 references/workflows.md:92 references/workflows.md:95 references/workflows.md:278 references/workflows.md:283 references/workflows.md:436 references/workflows.md:634

⚙️ External commands (41)

Audited by: claude View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/k-dense-ai-esm/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/k-dense-ai-esm/security.svg)](https://skillstore.io/skills/k-dense-ai-esm?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/k-dense-ai-esm?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-esm/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-esm.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

K-Dense-AI. (2026). esm security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-esm/audits/9

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-esm-2026,
  author = {K-Dense-AI},
  title = {esm security audit report (audit version 9)},
  institution = {Skillstore},
  year = {2026},
  number = {9},
  url = {https://skillstore.io/skills/k-dense-ai-esm/audits/9},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "esm security audit report (audit version 9)"
version: "unspecified"
type: report
authors:
  - name: "K-Dense-AI"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/k-dense-ai-esm/audits/9"
identifiers:
  - type: other
    value: "skillstore:k-dense-ai-esm:audit:9"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

K-Dense-AI Recommended Current

k-dense-ai-esm

Skillstore Score 68

Evidence Confidence High

Skillstore usage 12

Updated

2026-09-09

davila7

davila7-esm

Skillstore Score 67

Evidence Confidence High

Skillstore usage 8

Updated

2026-09-09

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Generate candidate proteins

Create sequence prompts, choose ESM3 generation settings, and refine candidates with structure and function tracks.

Analyze protein representations

Generate ESM C embeddings for similarity search, clustering, classification, and dataset exploration.

Prototype scalable inference

Compare local models with Forge API usage for batch generation, caching, and production-style retry patterns.

Try These Prompts

Choose an ESM model

I have a protein sequence analysis task with 500 sequences. Help me choose between ESM3 and ESM C, and explain the tradeoffs.

Generate a protein sequence

Use ESM3 concepts to design a 150 amino acid protein candidate with a fluorescent protein function annotation.

Build an embedding workflow

Plan an ESM C workflow to embed a FASTA dataset, cluster the sequences, and summarize representative proteins.

Design a scalable Forge pipeline

Design a Forge API batch pipeline for 10,000 protein generation requests with checkpointing, caching, retries, and privacy considerations.

Best Practices

Start with smaller local models for prototypes before using larger Forge models.
Cache embeddings and generated outputs when repeated analyses use the same inputs.
Review biosafety, privacy, and validation requirements before using generated proteins.

Avoid

Do not treat generated proteins as experimentally validated results.
Do not send proprietary protein sequences to cloud APIs without approval.
Do not choose the largest model before testing workflow quality and cost.

Frequently Asked Questions

What does this skill help with?

It helps users work with ESM3 and ESM C for protein generation, structure prediction, inverse folding, and embeddings.

Can it run ESM models directly?

The skill provides guidance and examples. Actual execution depends on the user environment, installed packages, model access, and hardware.

What is the difference between ESM3 and ESM C?

ESM3 is used for multimodal generation across sequence, structure, and function. ESM C focuses on efficient protein embeddings.

Does Forge API usage have privacy implications?

Yes. Forge API examples send data to an external service, so users should check policy requirements before submitting sensitive sequences.

Are generated proteins ready for lab use?

No. Generated proteins need computational checks, safety review, and experimental validation before practical use.

Can Claude Code use this skill for scripts?

Yes. Claude Code can use the examples to help draft workflows, but users should inspect commands and outputs before running them.

Developer Details

Author

K-Dense-AI

License

MIT license

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/esm

Ref

1ffa7643651792ccb4bd3b15d924d2c97edff755

Maintenance freshness

7/18/2026

Usage

7 downloads · 393 views

File structure

📁 references/

📄 esm-c-api.md

📄 esm3-api.md

📄 forge-api.md

📄 workflows.md

📄 evaluation.json

Explore Open Targets Drug Discovery Data

by davila7

Drug discovery teams need fast access to target, disease, evidence, and drug data. This skill guides Claude, Codex, and Claude Code through Open Targets GraphQL workflows.

Data & Analytics View

esm

Install with my Agent

Agent-readable resources

Test it

Security Audit

Confirmed security concerns (1)

Risk Factors

Copy report link

Markdown badge

HTML badge

Embed card

APA citation

BibTeX citation

CITATION.cff

Compare variants

Skillstore Score

What You Can Build

Generate candidate proteins

Analyze protein representations

Prototype scalable inference

Try These Prompts

Best Practices

Avoid

Frequently Asked Questions

Developer Details

More from K-Dense-AI

venue-templates

iso-13485-certification

pytdc

diffdock

hypothesis-generation

statistical-analysis

Related Skills

drugbank-database

bioservices

chembl-database

kegg-database

medchem

opentargets-database