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.
npx skills add ma-compbio-lab/SkillFoundry --skill ebi-proteins-entry-summarygit clone --depth 1 https://github.com/ma-compbio-lab/SkillFoundryWrote 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.
[](https://agentmods.dev/skills/ma-compbio-lab/skillfoundry/ebi-proteins-entry-summary)<a href="https://agentmods.dev/skills/ma-compbio-lab/skillfoundry/ebi-proteins-entry-summary"><img src="https://agentmods.dev/badge/skills/ma-compbio-lab/skillfoundry/ebi-proteins-entry-summary/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ma-compbio-lab/skillfoundry/ebi-proteins-entry-summary"><img src="https://agentmods.dev/badge/skills/ma-compbio-lab/skillfoundry/ebi-proteins-entry-summary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00041 | $0.00511 |
| Opus 5 | $0.00020 | $0.00255 |
| Sonnet 5 | $0.00008 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
ebi-proteins-entry-summary 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 6d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Resolve a protein accession through the EBI Proteins API and return a compact protein summary with names, organism, sequence size, keywords, and a small subset of comments and features.
When to use
- You already know a protein accession such as
P38398. - You want a quick official protein summary before deeper proteomics or protein-biology work.
When not to use
- You need bulk UniProt-scale exports.
- You need peptide evidence tables or full annotation payloads.
- You need offline execution.
Inputs
- Protein accession
- Optional output path
Outputs
- JSON payload containing a compact protein-entry summary
Requirements
- Python 3.10+
- Network access to
www.ebi.ac.uk
Procedure
- Run
python3 skills/proteomics/ebi-proteins-entry-summary/scripts/fetch_protein_summary.py --accession P38398 --out skills/proteomics/ebi-proteins-entry-summary/assets/brca1_protein_summary.json. - Inspect
recommended_name,gene_names,organism_scientific_name,sequence_length,keywords,comments, andfeatures. - Use the compact summary as a lookup layer before downstream structural or proteomics workflows.
Validation
- Command exits successfully.
- Output contains the requested accession and a non-empty recommended protein name.
- Known human accessions report the correct organism and a positive sequence length.
Failure modes and fixes
- HTTP 404: confirm the accession exists and is public.
- Empty optional fields: some accessions have sparse comments or features; use the stable core fields first.
- Need bulk access: build a separate batch-oriented skill instead of overloading this single-entry helper.
Safety and limits
- Metadata lookup only.
- This skill does not perform protein design, therapeutic recommendation, or wet-lab planning.
Example
python3 skills/proteomics/ebi-proteins-entry-summary/scripts/fetch_protein_summary.py --accession P38398
Provenance
- EBI Proteins API docs: https://www.ebi.ac.uk/proteins/api/doc/
What ships with it
10 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.
- assets/brca1_protein_summary.json 3.3 KB
- assets/p38398_summary.json 3.4 KB
- assets/README.md 96 B
- examples/README.md 310 B
- metadata.yaml 956 B
- refs.md 302 B
- scripts/fetch_protein_entry_summary.py 6.6 KB runs code
- scripts/fetch_protein_summary.py 307 B runs code
- tests/README.md 115 B
- tests/test_ebi_proteins_entry_summary.py 3.0 KB runs code
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.
- 6d ago First seen · 57 lines · 41 tokens per session scan A a13b23fa3bfe
ebi-proteins-entry-summary is a skill published in the GitHub repository ma-compbio-lab/SkillFoundry (38 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 511 once invoked, about $0.0002 per session on Opus 5. 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.
Other skills, from other repositories
arxiv-search
Skill "arxiv-search" from TaewoooPark/MagLab, covering category scoping, query families (3–6 per topic), version and doi resolution, tier classification and output contract.
revision-letter
Point-by-point peer-review response letter workflow for journal resubmission. Invokes RevisionLetterAgent to quote each reviewer comment verbatim, draft a response, and add a change-location marker. Outputs carry HUMAN REVIEW REQUIRED; no auto-send. A DOI or manuscript location is required for every factual response…
literature-search
Broad literature search for magnetism & spintronics — OpenAlex REST query strategy, query family generation, tier classification, and evidencematrix construction (§14.3·§14.7). Activated by the maglab lit search command and the research orchestration search-scout agent.
physics-oracle
Use when validating the dimensional, range, and conservation-law plausibility of magnetic physics quantities, or when performing deterministic physics formula calculations and unit conversions. Gilbert damping 0≤α≤1 check, M≤Ms, exchange length and domain wall width calculations, Oe↔A/m↔T·emu/cm³↔A/m·Jij meV↔K…
statistical-experimental-evaluation
Design and run statistical experiments that test the formal problem, proposed methods, theoretical predictions, baselines, and ablations.
batch-effect-correction
Use when correcting batch effects in merged bulk expression matrices with sample-level batch metadata while preserving biological group structure and generating before-and-after QC plots. NOT for: single-cell integration, raw FASTQ processing, differential expression without batch labels, or datasets without…