What is protein-language-model-function-analysis-starter?

A protein-language-model workflow that reads protein sequences from FASTA files, creates sequence embeddings, and compares them with supplied function labels. Embeddings are numerical representations of sequences that help compare their meaning.

Use it to validate protein sequences, export embeddings, group sequences by function, and inspect nearest neighbors for annotation or benchmarking.

It provides a deterministic local test path before using larger models or GPU-based inference.

protein-language-model-function-analysis-starter

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add ma-compbio-lab/SkillFoundry --skill protein-language-model-function-analysis-starter

Clone the repo

git clone --depth 1 https://github.com/ma-compbio-lab/SkillFoundry

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ma-compbio-lab/skillfoundry/protein-language-model-function-analysis-starter.svg)](https://agentmods.dev/skills/ma-compbio-lab/skillfoundry/protein-language-model-function-analysis-starter)

Your own site

<a href="https://agentmods.dev/skills/ma-compbio-lab/skillfoundry/protein-language-model-function-analysis-starter"><img src="https://agentmods.dev/badge/skills/ma-compbio-lab/skillfoundry/protein-language-model-function-analysis-starter.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 420 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00420
Opus 5	$0.00000	$0.00210
Sonnet 5	$0.00000	$0.00084
Haiku 4.5	$0.00000	$0.00042

Measured 4d ago against content hash 6a51e28c2896, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

protein-language-model-function-analysis-starter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/run_frontier_starter.py, scripts/run_protein_language_model_function_analysis.py, tests/test_protein_language_model_function_analysis_starter.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/proteomics/protein-language-model-function-analysis-starter/SKILL.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Protein Language Model Function Analysis Starter

Use this skill to validate protein FASTA inputs, extract deterministic smoke-safe embeddings, and run a reusable sequence-to-function triage flow that can later be swapped onto real ESM-2 or ProtT5 backends.

What This Skill Does

reads protein sequences from FASTA and rejects unsupported residue symbols
emits per-sequence embeddings to a TSV contract
runs centroid-based function analysis when labels are supplied
reports nearest-neighbor structure in embedding space
preserves a stable CLI for real transformers backends such as ESM-2 and ProtT5

When To Use It

when you need a concrete local skill for protein-embeddings and sequence-to-function-modeling
when you want a deterministic smoke path before moving to GPU-backed protein language model inference
when you need a compact handoff artifact for downstream DeepFRI, annotation, or benchmarking work

Run

python3 skills/proteomics/protein-language-model-function-analysis-starter/scripts/run_protein_language_model_function_analysis.py \
  --input skills/proteomics/protein-language-model-function-analysis-starter/examples/toy_sequences.fasta \
  --labels skills/proteomics/protein-language-model-function-analysis-starter/examples/toy_labels.tsv \
  --config skills/proteomics/protein-language-model-function-analysis-starter/examples/analysis_config.json \
  --embeddings-out scratch/protein-lm/toy_embeddings.tsv \
  --summary-out scratch/protein-lm/toy_summary.json

Notes

The default mock backend is intentionally deterministic and test-friendly. It preserves the same file contract as a real protein language model run.
For live model inference, switch the backend to transformers and point model_id at an ESM-2 or ProtT5 checkpoint. See refs.md for canonical sources and formatting notes.
The bundled toy labels are illustrative and suitable only for smoke testing or pipeline scaffolding, not biological claims.

Read the full file on GitHub · 35 lines

Files

What ships with it

13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

4d ago First seen · 35 lines · 0 tokens per session scan A 6a51e28c2896

Subscribe to this mod's changes

protein-language-model-function-analysis-starter is a skill published in the GitHub repository ma-compbio-lab/SkillFoundry (38 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 420 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Data and AI Scientific agent-skills ai-for-science automation computational-biology genomics llm-agents

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…

aipoch/open-science · 223 tokens

scgpt

Embed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology. Use this skill when: (1) Producing cell embeddings from an AnnData for clustering/integration, (2) Zero-shot or fine-tuned cell-type annotation, (3) Gene-level representation for perturbation/GRN tasks. For…

aipoch/open-science · 89 tokens

evo2

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…

aipoch/open-science · 83 tokens