Ready to supercharge your AI agents?

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

ViennaRNA Structure Prediction · jaechang-hits | DecimalAI

scienceby jaechang-hits

ViennaRNA Structure Prediction

jaechang-hits/viennarna-structure-prediction

Source jaechang-hits/sciagent-skills ↗License NOASSERTION

Predict RNA secondary structure, MFE folding, base-pair probabilities, RNA-RNA interactions via ViennaRNA Python bindings. Pipeline: sequence → MFE → partition function and pair-probability matrix → dot-bracket → duplex.

SkillScore91Maintained

Automatic

Research pack

Last verified 8/23/2026

What it changes

Passed 21 of 23 test cases with the skill, and 18 of 23 without it.

Without skill78%

With skill91%

Checks it passed that the model alone missed

The script calls fc.mfe() prior to calling fc.pf().
The pf method returns the centroid structure string.
The script uses RNA.cofold to compute the duplex interaction.

and 2 more in the full report

4 fixed17 passed either way1 still failing1 broke

Pass-rate lift: +13 pp
Tokens: +354%
Agent turns: 0%
Response time: -13%

Model gemini-3.6-flashMeasured 8/23/2026v121 of 23 cases passed with skill

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-viennarna-structure-prediction/SKILL.md https://app.decimal.ai/s/jaechang-hits-viennarna-structure-prediction/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add jaechang-hits-viennarna-structure-prediction, 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-viennarna-structure-prediction/ and pins it in .decimal/skills.lock

decimalai skills add jaechang-hits-viennarna-structure-prediction

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

curl -fsSL --create-dirs -o .claude/skills/jaechang-hits-viennarna-structure-prediction/SKILL.md https://app.decimal.ai/s/jaechang-hits-viennarna-structure-prediction/SKILL.md

Raw file: /s/jaechang-hits-viennarna-structure-prediction/SKILL.md ↗ · machine-readable summary at /s/jaechang-hits-viennarna-structure-prediction.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

After executing partition function calculation on a fold compound object in Python using pf(), what structural string representation and thermodynamic value are returned by the call?

What was checked, without and with the skill
Checked	Without skill	With skill
The pf method returns the centroid structure string.	Missed	Passed
The pf method returns the ensemble Gibbs free energy value.	Passed	Passed

case-23 · 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.md542 linessingle file

ViennaRNA Structure Prediction

Overview

ViennaRNA is the gold-standard toolkit for RNA secondary structure prediction based on thermodynamic nearest-neighbor parameters. It predicts the minimum free energy (MFE) structure and dot-bracket notation for a given RNA sequence, computes the full partition function to obtain base pair probabilities, and models RNA-RNA interactions via co-folding and duplex prediction. The Python bindings (import RNA) expose the full ViennaRNA C library with sequence-level and fold-compound APIs. Command-line programs (RNAfold, RNAalifold, RNAduplex) are also available and demonstrated here.

When to Use

Predicting the minimum free energy secondary structure of an RNA sequence (mRNA, lncRNA, miRNA precursor, aptamer)
Computing base pair probability matrices to assess structural uncertainty and identify well-defined stem-loops
Designing or evaluating siRNA accessibility by folding the target mRNA region and checking for double-stranded structure
Assessing sgRNA targeting efficiency by predicting guide RNA secondary structure that may reduce on-target activity
Modeling RNA-RNA interactions (co-folding or duplex prediction) for miRNA-target binding or antisense oligonucleotide design
Calculating folding free energies for a set of sequences to compare thermodynamic stability
Use mfold (web server) or RNAstructure instead when you need Mfold algorithm predictions specifically or need the Efold partition function; ViennaRNA uses the Turner 2004 nearest-neighbor parameters and is the standard for research-grade thermodynamic prediction

Prerequisites

Python packages: ViennaRNA (Python bindings), matplotlib, numpy
Data requirements: RNA sequences as strings (ACGU alphabet; T is auto-converted to U by ViennaRNA)
Environment: Python 3.8+; conda installation strongly recommended (handles C library dependencies)

# Install via conda (recommended)
conda install -c conda-forge -c bioconda viennarna

# Verify installation
python -c "import RNA; print(RNA.__version__)"
# 2.6.4

# Install additional Python dependencies
pip install matplotlib numpy pandas

# Optional: verify CLI tools are available
RNAfold --version
# RNAfold 2.6.4

Quick Start

Track record

Benchmark

21 / 23

test cases passed, vs 18 / 23 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/viennarna-structure-prediction/SKILL.md

View on GitHub ↗

License MITImported 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

ViennaRNA Structure Prediction

Overview

When to Use

Prerequisites

Quick Start

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills