CtrlK
BlogDocsLog inGet started
Tessl Logo

crispr-grna-designer

Design CRISPR gRNA sequences for specific gene exons with off-target prediction and efficiency scoring. Trigger when user needs gRNA design, CRISPR guide RNA selection, or genome editing target analysis.

Install with Tessl CLI

npx tessl i github:aipoch/medical-research-skills --skill crispr-grna-designer
What are skills?

88

Does it follow best practices?

Validation for skill structure

SKILL.md
Review
Evals

Evaluation results

100%

61%

CRISPR Guide RNA Design for Cancer Research

gRNA design and output format

Criteria
Without context
With context

Uses main.py script

0%

100%

Output file created

100%

100%

Top-level JSON schema

40%

100%

Guide object fields

41%

100%

Guide ID format

20%

100%

Correct gene and genome

50%

100%

Guides sorted by efficiency

0%

100%

GC content values present

0%

100%

Efficiency scores in 0-1 range

25%

100%

Summary identifies top 3

100%

100%

Warnings field used

100%

100%

Without context: $0.2981 · 1m 45s · 16 turns · 19 in / 6,395 out tokens

With context: $0.6817 · 2m 16s · 27 turns · 6,943 in / 5,752 out tokens

98%

46%

Guide RNA Quality Assessment for Gene Knockout

efficiency scoring and quality criteria

Criteria
Without context
With context

Uses scripts/main.py

0%

100%

GC content optimal range

0%

100%

Poly-T penalty documented

100%

100%

Position 20 G preference

100%

100%

Position 19 C preference

0%

100%

High-activity threshold stated

0%

80%

Guides sorted by efficiency

50%

100%

Efficiency scores 0-1

0%

100%

Warnings for quality issues

100%

100%

Top guide analysis

100%

100%

Score formula components

100%

100%

Without context: $0.9826 · 5m 8s · 31 turns · 38 in / 17,189 out tokens

With context: $0.7772 · 3m 20s · 30 turns · 6,768 in / 8,189 out tokens

90%

35%

Therapeutic CRISPR Guide Selection with Off-Target Risk Assessment

off-target prediction and high-specificity design

Criteria
Without context
With context

Stricter mismatch threshold

50%

100%

Narrower GC range

40%

100%

Off-target count in output

75%

100%

Genomic context risk classification

33%

58%

Seed region explanation

80%

100%

CFD score referenced

100%

100%

Experimental validation recommended

80%

50%

Guides sorted by efficiency

14%

100%

Uses main.py script

0%

100%

Off-target risk integrated in ranking

87%

100%

In silico limitation acknowledged

57%

100%

Without context: $0.6277 · 4m · 17 turns · 23 in / 15,099 out tokens

With context: $0.8497 · 3m 40s · 30 turns · 6,658 in / 10,010 out tokens

Evaluated
Agent
Claude Code

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.