Claude-skill-registry bio-blat

Runs local BLAT searches for DNA sequence alignment against hg38 or CHM13 using local .2bit references. Use when a user wants to align a DNA sequence without relying on UCSC API access.

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 "$T/skills/data/bio-blat" ~/.claude/skills/majiayu000-claude-skill-registry-bio-blat && rm -rf "$T"

manifest: skills/data/bio-blat/SKILL.md

BLAT API Searching

Quick start

Run BLAT locally via the Python CLI script. The script manages reference downloads.

Utility script

Install dependencies:

uv pip install typer

Run BLAT with a FASTA file:

python scripts/run_blat_local.py run --reference hg38 --fasta path/to/query.fasta

Run BLAT with a raw sequence:

python scripts/run_blat_local.py run --reference CHM13 --sequence ACTG...

Save JSON output to a file:

python scripts/run_blat_local.py run --reference hg38 --sequence ACTG... --output blat.json

When to read references

Local BLAT setup and references: See
```
references/local_blat.md
```

Workflow (local-only)

Confirm the reference assembly (
```
hg38
```
or
```
CHM13
```
).
Ensure the 2bit reference exists in
```
~/.local/share/blat
```
.
Use the CLI script to run BLAT and get a PSL output.
If FASTA has multiple sequences, split into one sequence per file.