bio-crispr-screens-base-editing-analysis

bio-crispr-screens-base-editing-analysis is a skill for Claude Code, Codex from GPTomics/bioSkills. It costs 218 tokens per session (6,076 once invoked), scanned A, original, MIT.

A workflow for measuring how base-editing CRISPR screens affect specific DNA variants. Base editors change selected DNA letters without making the full double-strand cuts used by standard CRISPR editing.

In plain words
What is it for?
Use it to quantify editing and byproducts from amplicon sequencing, map guides to intended and bystander variants, calculate variant fitness, and compare variants with ClinVar or COSMIC annotations.
Why use it?
A guide may change the intended base, nearby bases, or create small insertions and deletions. This separates those outcomes so variant effects and screen measurements are assigned to the right change.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to quantify editing and byproducts from amplicon sequencing, map guides to intended and bystander variants, calculate variant fitness, and compare variants with ClinVar or COSMIC annotations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gptomics/bioskills/base-editing-analysis
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 GPTomics/bioSkills --skill base-editing-analysis
Clone the repo
git clone --depth 1 https://github.com/GPTomics/bioSkills

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.

agentmods badge for bio-crispr-screens-base-editing-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/gptomics/bioskills/base-editing-analysis/github.svg)](https://agentmods.dev/skills/gptomics/bioskills/base-editing-analysis)
Your own site
<a href="https://agentmods.dev/skills/gptomics/bioskills/base-editing-analysis"><img src="https://agentmods.dev/badge/skills/gptomics/bioskills/base-editing-analysis/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 bio-crispr-screens-base-editing-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/gptomics/bioskills/base-editing-analysis"><img src="https://agentmods.dev/badge/skills/gptomics/bioskills/base-editing-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 218 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,076 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00218 $0.06076
Opus 5 $0.00109 $0.03038
Sonnet 5 $0.00044 $0.01215
Haiku 4.5 $0.00022 $0.00608

Measured 7d ago against content hash f5281e8ac0d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

bio-crispr-screens-base-editing-analysis 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (examples/base_editing_analysis.sh), 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

crispr-screens/base-editing-analysis/SKILL.md · 357 lines

How it starts

The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Version Compatibility

Reference examples tested with: CRISPResso2 2.2.14+, BE-Hive 1.0+ (BE prediction), pandas 2.2+, biopython 1.83+, numpy 1.26+, scipy 1.12+, scikit-learn 1.4+; Broad be-validation-pipeline notebooks (repo HEAD).

Before using code patterns, verify installed versions match. If versions differ:

  • CLI: CRISPResso --version
  • Python: pip show CRISPResso2; BE-Hive is a GitHub clone (maxwshen/be_predict_bystander), not a PyPI package

If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying.

Base Editing Screen Analysis

"Analyze my base-editor variant-function screen" -> Quantify per-sgRNA target-base conversion, bystander rate, and indel byproducts from amplicon sequencing; filter on editing efficiency; map each sgRNA to its intended SNV (target + bystander pattern); compute per-variant fitness from the screen log-fold change; reconcile target vs bystander variant attribution; annotate against ClinVar / COSMIC.

  • CLI: CRISPResso --base_editor_output for per-amplicon BE quantification
  • CLI: Broad be-validation-pipeline for end-to-end pooled-screen analysis with editing-efficiency filtering
  • Python: BE-Hive (Arbab 2020) for editing-efficiency prediction; clone maxwshen/be_predict_bystander and import via sys.path
  • Web: BE-Designer (Hwang 2018, RGEN Tools) for variant-encoding sgRNA design

Base Editor Chemistry Selection

Editor Reaction Editing window Indel byproduct rate When to use
BE3 (Komor 2016) C->T (also G->A on opposite strand) Pos 4-8 from PAM-distal end 5-10% Original; superseded
BE4 / BE4max (Koblan 2018) C->T Pos 4-8 <5% CBE standard
eA3A-BE3 C->T narrow specificity Pos 5-7 <5% Specifically TC contexts (eA3A prefers TC)
ABE7.10 (Gaudelli 2017) A->G (T->C opposite strand) Pos 4-7 <2% First ABE; slow at non-TA contexts
ABE8.20 (Gaudelli 2020) A->G Pos 4-8 <2% Modern ABE; high activity
ABE8e (Richter 2020) A->G Pos 4-8 <2% Highest editing activity; more processive than ABE7.10
evoCDA-BE C->T (broader) Pos 1-9 5-10% Larger editing window; more bystander
CGBE1 (Kurt 2021) C->G Pos 5-7 5-10% C-to-G transversion; rare use
GBE (Zhao 2021) C->G or C->A Pos 4-7 5-10% Transversions; less mature

Read the full file on GitHub · 357 lines

Files

What ships with it

2 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.

  1. 7d ago First seen · 357 lines · 218 tokens per session scan A f5281e8ac0d1

Subscribe to this mod's changes

bio-crispr-screens-base-editing-analysis is a skill published in the GitHub repository GPTomics/bioSkills (1,199 stars, last pushed 26d ago), licensed MIT. It adds 218 tokens to every session and 6,076 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens