Spatial Raw Processing

What it does

When your agent uses it

• Tasks that involve Bioinformatics

Example prompts

• “/spatial-raw-processing”

Requirements

• Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Parse args (or load bundle JSON / YAML from positional --input).
2. 2_apply_effective_defaults fills missing parameter values (threads, trimming, UMI ranges, etc.).
3. 3_validate_real_run_bundle: check read1 / read2 / ids / ref-map exist and are well-typed; reject duplicate read1=read2; verify FASTQ…
4. 4Call run_stpipeline(...) which shells out to ST-Pipeline (requires the stpipeline binary on PATH or --stpipeline-repo + --bin-path).
5. 5Wrap the resulting count matrix into AnnData with X = raw_counts, layers["counts"], raw = raw_counts_snapshot.
6. 6Save raw_counts.h5ad and result.json. Print "next: spatial-preprocess on raw_counts.h5ad".

What it can do on your machine

Read from SKILL.md and the folder at commit 90a3bec. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Python and R), which the agent can run.

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Spatial Raw Processing loads about 1.7k tokens when it runs, and up to ~4.8k if it reads all its reference files. Until then it costs about 72 tokens; SKILL.md has 530 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~72

When it runs · the whole SKILL.md, loaded when a task matches

~1.7k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from TianGzlab/OmicsClaw at commit 90a3bec, republished under its Apache-2.0 licence (© TianGzlab). 530 words, ~1,748 tokens.

name

spatial-raw-processing

description

Load when converting spatial transcriptomics raw FASTQ pairs through ST-Pipeline into a `raw_counts.h5ad` ready for spatial-preprocess. Skip when input is already a count-matrix AnnData (use spatial-preprocess); non-spatial bulk / scRNA FASTQ (use bulkrna-read-qc).

trigger

spatial raw processing, raw spatial fastq, spatial fastq, st_pipeline, st pipeline, barcode coordinates, ids file, visium raw fastq, slide-seq fastq, slideseq…

tags

spatial, raw-processing, fastq, st-pipeline, visium, slideseq

from skills._sdk.notebook import run_cli

output = run_cli("spatial-raw-processing", "--input", "data/run_bundle.json",
                 inputs=["data/run_bundle.json", "data/R1.fastq.gz",
                         "data/R2.fastq.gz", "data/barcodes.tsv"])

# Demo (synthetic raw_counts.h5ad — does NOT run ST-Pipeline)
python skills/spatial/spatial-raw-processing/spatial_raw_processing.py --demo --output /tmp/spatial_raw_demo

# Real run with explicit args
python skills/spatial/spatial-raw-processing/spatial_raw_processing.py \
  --read1 sample_R1.fastq.gz --read2 sample_R2.fastq.gz \
  --ids barcodes.tsv \
  --ref-map /refs/star_index_human \
  --ref-annotation /refs/genes.gtf \
  --exp-name visium_001 --platform visium \
  --threads 16 \
  --output results/

# Real run from bundle JSON
python skills/spatial/spatial-raw-processing/spatial_raw_processing.py \
  --input run_bundle.json --output results/

# Slide-seq with custom UMI range
python skills/spatial/spatial-raw-processing/spatial_raw_processing.py \
  --read1 R1.fq.gz --read2 R2.fq.gz --ids barcodes.tsv \
  --ref-map /refs/star_index --platform slideseq \
  --umi-start-position 1 --umi-end-position 8 \
  --output results/

© TianGzlab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (references) in skills/spatial/spatial-raw-processing of TianGzlab/OmicsClaw.

• SKILL.md
• examples/example_step.py
• r_visualization/README.md
• r_visualization/raw_processing_publication_template.R
• references/methodology.md
• references/output_contract.md
• references/parameters.md
• spatial_raw_processing.py
• tests/test_spatial_raw_processing.py

Open the folder on GitHubat commit 90a3bec