Singlecell Qc

What it does

When your agent uses it

• Implementing single-cell RNA-seq QC in Python
• R with a human-in-the-loop
• Data-driven approach
• ScRNA QC metrics

Example prompts

• “/singlecell-qc”

Requirements

• Python 3

Workflow steps

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

1. 1Inspect before acting — matrix type, species, sample metadata, existing checkpoints.
2. 2Pilot samples first — default 1–3 samples; expand only after user OK.
3. 3Metrics before filters — run 01-calculate_metrics; stop and report.
4. 4Propose thresholds, never silently apply — show expected cell loss per sample.
5. 5Ask at gates — which metrics next? which thresholds? proceed to filter? merge?
6. 6No silent heavy steps — no full-cohort filter, Scrublet, decontX, or merge without explicit approval.
7. 7Reversible checkpoints — pre-filter metadata/counts stay intact; filtering writes new files.
8. 8Scripts = one stage — owner-editable; thresholds visible at top of filter scripts.

What it can do on your machine

Read from SKILL.md and the folder at commit 2ba143b. 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 3 files in scripts/ (Python and R), which the agent can run.

  Shell commands in SKILL.md call:

  • rg
  • 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

Singlecell Qc loads about 1.6k tokens when it runs, and up to ~7.2k if it reads all its reference files. Until then it costs about 129 tokens; SKILL.md has 535 words of instructions outside code blocks.

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

~129

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

~1.6k

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

~7.2k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from xuzhougeng/wisp-science at commit 2ba143b, republished under its AGPL-3.0 licence (© xuzhougeng). 535 words, ~1,579 tokens.

name

singlecell-qc

description

Use when designing, reviewing, or implementing single-cell RNA-seq QC in Python or R with a human-in-the-loop, data-driven approach. Trigger for scRNA QC metrics, per-sample diagnosis, threshold discussion, mitochondrial/ambient/doublet assessment, MAD vs fixed cutoffs, or refactoring automated merge-first QC. The analyst confirms key decisions at each step—agents must inspect data, propose options, and wait for approval before filtering, doublet removal, or merging. Not a turnkey pipeline skill.

inspect data → compute metrics → human reviews → confirm thresholds → small action → re-inspect

find <project_root> -maxdepth 4 -type f \( -name '*.py' -o -name '*.R' -o -name '*.h5ad' -o -name '*.md' \) | head -60
rg -n "filter_cells|calculate_qc|metadata|mito|n_genes" <project_root>/scripts 2>/dev/null | head -30

scripts/01-qc/
  01-calculate_metrics.py|R   # metrics only
  02-qc_diagnosis.py|R        # figures from metadata
  03-filter_cells.py|R        # runs only after threshold sign-off
result/01-qc/ ...
figure/01-qc/ ...

# Typical pilot — metrics only
python .../calculate_metrics.py \
  --matrix-dir <dir> --sample-id PILOT --species human \
  --output-dir result/01-qc/01-calculate_metrics/PILOT

© xuzhougeng, AGPL-3.0. 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 13 other files (scripts, references, assets) in skills/singlecell-qc of xuzhougeng/wisp-science.

• SKILL.md
• assets/gene_sets/chrY_genes_human.txt
• assets/gene_sets/hbb_genes_human.txt
• assets/gene_sets/hbb_genes_mouse.txt
• assets/qc_thresholds.example.yaml
• references/filtering-strategies.md
• references/human-in-the-loop.md
• references/metrics-catalog.md
• references/project-layout.md
• references/python-scanpy.md
• references/r-seurat.md
• scripts/calculate_metrics.R
• scripts/calculate_metrics.py
• scripts/inspect_qc_metadata.py

Open the folder on GitHubat commit 2ba143b