Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

sgRNA Design Guide: Three-Tiered Approach · jaechang-hits | DecimalAI

scienceby jaechang-hits

sgRNA Design Guide: Three-Tiered Approach

jaechang-hits/sgrna-design-guide

Source jaechang-hits/sciagent-skills ↗License NOASSERTION

Three-tiered sgRNA design guide using validated Addgene sequences, CRISPick pre-computed datasets, or de novo design rules for CRISPR experiments

SkillScore95Maintained

Automatic

Research pack

Last verified 8/23/2026

What it changes

Passed 20 of 21 test cases with the skill, and 12 of 21 without it.

Without skill59%

With skill95%

Checks it passed that the model alone missed

The response specifies filtering pre-computed datasets by Combined Rank.
The response recommends ordering and testing 3 to 4 sgRNAs per target gene.
The response recommends sorting by Combined Rank as the default selection criterion.

and 11 more in the full report

9 fixed12 passed either way0 still failing1 broke

Pass-rate lift: +36 pp
Tokens: +317%
Agent turns: 0%
Response time: -13%

Model gemini-3.6-flashMeasured 8/23/2026v121 of 22 cases passed with skill · 21 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/jaechang-hits-sgrna-design-guide/SKILL.md https://app.decimal.ai/s/jaechang-hits-sgrna-design-guide/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add jaechang-hits-sgrna-design-guide, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/jaechang-hits-sgrna-design-guide/ and pins it in .decimal/skills.lock

decimalai skills add jaechang-hits-sgrna-design-guide

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/jaechang-hits-sgrna-design-guide/SKILL.md https://app.decimal.ai/s/jaechang-hits-sgrna-design-guide/SKILL.md

Raw file: /s/jaechang-hits-sgrna-design-guide/SKILL.md ↗ · machine-readable summary at /s/jaechang-hits-sgrna-design-guide.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

We obtained a validated sgRNA sequence from the Addgene curated database index. How should we acknowledge and cite this sequence in our manuscript?

What was checked, without and with the skill
Checked	Without skill	With skill
The response specifies citing the original publication's PubMed ID associated with the validated sequence.	Missed	Passed

case-17 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md509 linessingle file

sgRNA Design Guide: Three-Tiered Approach

Metadata

Short Description: Comprehensive guide for finding or designing sgRNAs using validated sequences, CRISPick datasets, or de novo design tools.

Authors: Ohagent Team

Version: 1.0

Last Updated: November 2025

License: CC BY 4.0

Commercial Use: Allowed

Citations and Acknowledgments

If you use validated sgRNAs from our database (Option 1):

Database Source: Addgene (https://www.addgene.org)
Citation: Always cite the original publication associated with each sgRNA using the PubMed ID provided in the database
Acknowledgment: "Validated sgRNA sequences obtained from Addgene (https://www.addgene.org/crispr/reference/grna-sequence/)"

If you use CRISPick designs (Option 2):

Acknowledgment Statement: "Guide designs provided by the CRISPick web tool of the GPP at the Broad Institute"
Citation for Cas9 designs (SpCas9, SaCas9): Sanson KR, et al. Optimized libraries for CRISPR-Cas9 genetic screens with multiple modalities. Nat Commun. 2018;9(1):5416. PMID: 30575746
Citation for Cas12a designs (AsCas12a, enAsCas12a): DeWeirdt PC, et al. Optimization of AsCas12a for combinatorial genetic screens in human cells. Nat Biotechnol. 2021;39(1):94-104. PMID: 32661438
- Note: This paper describes enAsCas12a optimization; specify which variant you used in your methods

Overview

This guide provides a three-tiered approach to sgRNA design, prioritizing validated sequences before moving to computational predictions. Always start with Option 1 and proceed to subsequent options only if needed.

Key Concepts

Validated sgRNA Databases (Tier 1)

Track record

Benchmark

20 / 21

test cases passed, vs 12 / 21 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

jaechang-hits / sciagent-skills

skills/molecular-biology/sgrna-design-guide/SKILL.md

View on GitHub ↗

License openImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

sgRNA Design Guide: Three-Tiered Approach

Metadata

Citations and Acknowledgments

If you use validated sgRNAs from our database (Option 1):

If you use CRISPick designs (Option 2):

Overview

Key Concepts

Validated sgRNA Databases (Tier 1)

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills