lifesciences-research: Skill for Claude Code

.claude/skills/lifesciences-crispr/SKILL.md

lifesciences-crispr is a skill for Claude Code from donbr/lifesciences-research. It costs 102 tokens per session (2,993 once invoked), scanned A, original, MIT.

A workflow for checking synthetic-lethality claims using CRISPR knockout-screen data from BioGRID ORCS. Synthetic lethality means that disabling either of two genes alone may be tolerated, while disabling both is harmful.

In plain words
What is it for?
Use it to query essential genes, compare cell-line screens, inspect screen annotations, and validate gene-dependency or synthetic-lethality hypotheses. It requires a BioGRID API key.
Why use it?
It provides a defined sequence for checking whether a proposed gene dependency appears in experimental screens, while filtering for screens where the gene was considered essential.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is donbr/lifesciences-research's own configuration. It tells Claude Code how to work on lifesciences-research itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lifesciences-research configures →

Reuse

Borrowing it

Nothing to install: this file belongs to donbr/lifesciences-research. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/donbr/lifesciences-research/main/.claude/skills/lifesciences-crispr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/donbr/lifesciences-research

Made for: Claude Code.

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.

agentmods badge for lifesciences-crispr

README.md
[![agentmods](https://agentmods.dev/badge/skills/donbr/lifesciences-research/lifesciences-crispr/github.svg)](https://agentmods.dev/skills/donbr/lifesciences-research/lifesciences-crispr)
Your own site
<a href="https://agentmods.dev/skills/donbr/lifesciences-research/lifesciences-crispr"><img src="https://agentmods.dev/badge/skills/donbr/lifesciences-research/lifesciences-crispr/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.

agentmods 80×15 button for lifesciences-crispr

Your own site · 80×15
<a href="https://agentmods.dev/skills/donbr/lifesciences-research/lifesciences-crispr"><img src="https://agentmods.dev/badge/skills/donbr/lifesciences-research/lifesciences-crispr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,993 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00102 $0.02993
Opus 5 $0.00051 $0.01496
Sonnet 5 $0.00020 $0.00599
Haiku 4.5 $0.00010 $0.00299

Measured 12d ago against content hash 0323890127db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

lifesciences-crispr scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Validate synthetic lethality hypotheses using BioGRID ORCS CRISPR screen data via curl.
.claude/skills/lifesciences-crispr/SKILL.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRISPR Essentiality & Synthetic Lethality Validation

Validate synthetic lethality hypotheses using BioGRID ORCS CRISPR screen data via curl.

Quick Reference

Task Endpoint Key Parameters
Get essential screens only /gene/{entrez_id}?hit=yes hit=yes filters to essential
Get all gene screens /gene/{entrez_id} Returns all screens
Get screen annotations /screens/?screenID=1|2|3 Pipe-separated IDs
Find cell line screens /screens/?cellLine={name} Cell line name

BioGRID ORCS API

IMPORTANT: Use orcsws.thebiogrid.org (NOT orcs.thebiogrid.org)

  • Base URL: https://orcsws.thebiogrid.org
  • Auth: Requires BIOGRID_API_KEY which is captured in .env file
  • Rate Limit: ~10 req/s
  • Formats: format=tab (default) or format=json

Critical Parameter: hit=yes

Always use hit=yes when querying gene essentiality. This filters results to only screens where the gene scored as a hit (essential), dramatically reducing data volume:

  • Without filter: ~1,400 records (all screens)
  • With hit=yes: ~300-400 records (essential screens only)

Data Format (JSON)

{
  "SCREEN_ID": "16",
  "IDENTIFIER_ID": "7298",
  "OFFICIAL_SYMBOL": "TYMS",
  "SCORE.1": "100.84",
  "SCORE.2": "-",
  "HIT": "YES",
  "SOURCE": "BioGRID ORCS"
}

Screen Annotation Fields

Query /screens/?screenID={ids} to get cell line and publication data:

  • SCREEN_ID: Unique screen identifier
  • SOURCE_ID: PubMed ID
  • AUTHOR: First author and year
  • CELL_LINE: Cell line name
  • PHENOTYPE: Screen phenotype (e.g., "cell proliferation")

5-Phase Synthetic Lethality Validation Workflow

Phase 1: Resolve Gene Identifiers

Use Life Sciences MCPs to get Entrez IDs:

# Using HGNC MCP: search_genes → get_gene
# Extract "entrez" from cross_references object
# Example: DHODH → {"cross_references": {"entrez": "1723"}}

# Using Entrez MCP: search_genes
# Top result format: "NCBIGene:1723"
# Extract numeric ID: 1723

Read the full file on GitHub · 297 lines

Files

What ships with it

1 file 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.

  1. 12d ago First seen · 297 lines · 102 tokens per session scan A 0323890127db

Subscribe to this mod's changes

lifesciences-crispr is a skill published in the GitHub repository donbr/lifesciences-research (7 stars, last pushed 9d ago), licensed MIT. It adds 102 tokens to every session and 2,993 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

molecular-rag

Retrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. Based on MolRAG (Xian 2025, ACL).

synthetic-sciences/openscience · 40 tokens

chembl-query

Query ChEMBL database for bioactivity data on drug-like compounds. Use this skill when: (1) Finding compounds active against a protein target (target-based search), (2) Getting bioactivity profile for a molecule (molecule-based search), (3) Finding drugs for a disease indication (indication-based search).

PharMolix/OpenBioMed · 69 tokens

by-scoring

Interpret and apply BY custom scoring metrics for protein and antibody design. This skill covers ipSAE (interface Predicted Structural Accuracy Error) — the primary custom metric that differentiates BY from generic structure prediction tools — along with ipTM, pLDDT, RMSD, liability scoring, and the BY composite…

001TMF/blatant-why · 3 tokens

by-screening

Comprehensive screening battery for evaluating protein binder and antibody designs produced by PXDesign and BoltzGen. This skill encodes all quality filters, scoring thresholds, liability checks, and developability assessments used to triage designs before experimental validation.

001TMF/blatant-why · 3 tokens

by-campaign-manager

Plan, execute, monitor, and assess protein/antibody design campaigns. This skill governs how to size a campaign, track run state, coordinate multi-run efforts, estimate cost and time on each compute target (local GPU, HPC, Tamarind), monitor progress, and evaluate campaign health.

001TMF/blatant-why · 4 tokens

by-design-workflow

Skill "by-design-workflow" from 001TMF/blatant-why, covering by design workflow — master orchestration skill, when to use this skill, inputs, outputs and clarification questions.

001TMF/blatant-why · 4 tokens