install
source · Clone the upstream repo
git clone https://github.com/majiayu000/claude-skill-registry
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/crispr-prediction" ~/.claude/skills/majiayu000-claude-skill-registry-crispr-prediction && rm -rf "$T"
manifest:
skills/data/crispr-prediction/SKILL.mdsource content
---name: crispr-offtarget-predictor description: Predicts potential off-target sites for a given sgRNA sequence using mismatch analysis. license: MIT metadata: author: BioKernel Team version: "1.0.0" compatibility:
- system: Python 3.9+ allowed-tools:
- run_shell_command
keywords:
- crispr-prediction
- automation
- biomedical measurable_outcome: execute task with >95% success rate. ---"
CRISPR Off-Target Predictor
This skill identifies potential off-target binding sites for a specific sgRNA sequence. It helps researchers assess the specificity of their CRISPR design.
When to Use This Skill
- Designing new CRISPR experiments.
- Validating sgRNA specificity before synthesis.
- Analyzing potential safety risks in gene editing protocols.
Core Capabilities
- Mismatch Scoring: Calculates mismatch penalties for potential sites.
- PAM Validation: Filters targets based on PAM (Protospacer Adjacent Motif) compatibility.
- Risk Assessment: Categorizes off-targets as Low, Medium, or High risk.
Workflow
- Input: sgRNA sequence (20nt) and PAM (e.g., NGG).
- Analysis: Scans a reference library (mocked for this version) for similar sequences.
- Output: List of potential off-targets with locations and risk scores.
Example Usage
User: "Check sgRNA 'GAGTCCGAGCAGAAGAAGAA' for off-targets."
Agent Action:
python3 Skills/Genomics/CRISPR_Prediction/impl.py --sequence GAGTCCGAGCAGAAGAAGAA --pam NGG