Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add TianGzlab/OmicsClaw --skill omics-skill-buildergit clone --depth 1 https://github.com/TianGzlab/OmicsClawWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tiangzlab/omicsclaw/omics-skill-builder)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/omics-skill-builder"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/omics-skill-builder.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 3 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.01293 |
| Opus 5 | $0.00032 | $0.00647 |
| Sonnet 5 | $0.00013 | $0.00259 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
omics-skill-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
omics-skill-builder
When to use
The user wants to add a NEW skill to the OmicsClaw catalog from a
natural-language request. This skill produces a directory scaffold
under the chosen --domain (spatial / singlecell / genomics
/ proteomics / metabolomics / bulkrna / orchestrator) with
the v2 layout: skill.yaml, SKILL.md, references/,
tests/, plus a reproducibility manifest.
For modifying an existing skill, edit its files directly — this
skill is for net-new additions only. For dispatching queries to
existing skills, use orchestrator.
Inputs & Outputs
Outputs
SCAFFOLD_SUMMARY.mdreport.mdresult.jsonskills/<domain>/<skill-name>/- Produces artifact
orchestrator.skill_scaffoldasresult.json(json)
Flow
- Parse
--request(or--demo); raiseSystemExit("--request is required unless --demo is used.")atomics_skill_builder.py:75when missing. - Optionally promote one explicitly identified autonomous-analysis output via
--source-analysis-dir <path>. - Call
create_skill_scaffold(omicsclaw.core.skill_scaffolder); earned promotions enterskills/<domain>/<skill-name>/, while environment-limited promoted code enters the undiscoverableskills/.quarantine/tree. - Write
SCAFFOLD_SUMMARY.md+report.md+reproducibility/commands.sh+result.jsoninto--output.
Gotchas
--requestREQUIRED unless--demo— raisesSystemExit(exit 1).omics_skill_builder.py:75raisesSystemExit("--request is required unless --demo is used."). Different from most OmicsClaw skills which useValueError/parser.error; the exit code is 1, not 2.--domaindefaults toorchestrator— usually NOT what you want.omics_skill_builder.py:30defaults toorchestrator; pass--domain spatial(or whichever) explicitly. Choices are 7 fixed values; an unknown domain is rejected by argparse.- The new skill is written to
skills/<domain>/<skill-name>/, not--output.--outputonly receives the scaffold summary + report + commands.sh; the actual skill code goes underskills/. Don't confuse the two. --trigger-keyword,--method,--input-format,--output-itemare REPEATABLE flags. Pass--trigger-keyword kw1 --trigger-keyword kw2to add multiple. Single quoting won't help — argparse honoursaction="append".- Global
--promote-from-latestselection is disabled. Supply the exact--source-analysis-dir; this keeps concurrent sessions and runs isolated. - A skipped promoted-code gate is not admission. The bundle is quarantined with
references/quarantine.mdevidence and is not registered until a later explicit validation/admission flow exists. --demolands in the orchestrator domain, NOT the implied target domain.omics_skill_builder.py:65resolvesdomain = args.domain or "spatial", butargs.domaindefaults to"orchestrator"(truthy), so the demo scaffold is written toskills/orchestrator/spatial-cellcharter-domains/rather thanskills/spatial/.... For real scaffolds always pass--domain <target>explicitly.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 94 lines · 65 tokens per session scan A 597260e09419
omics-skill-builder is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,293 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
scanpy
Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use…
cellxgene-census-query
Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…
single-cell-scrna-seq-analysis-scanpy
Complete single-cell RNA-seq analysis workflow built on Scanpy and AnnData. Use this skill when: (1) Loading diverse single-cell data formats (10X, h5ad, CSV), (2) Performing quality control and filtering, (3) Normalization, dimensionality reduction, and clustering, (4) Marker gene identification and cell type…
single-cell-multi-omics-analysis-scvi
Probabilistic deep learning framework for single-cell multi-omics data analysis. Use this skill when: (1) Analyzing single-cell RNA-seq data with batch correction, (2) Integrating multi-modal data (CITE-seq, ATAC-seq, multi-omics), (3) Performing cell type annotation with scANVI, (4) Spatial transcriptomics…
braindb
Memory recall and save. Use at every conversation start and whenever the user shares personal information, expertise, project context, preferences, or decisions worth remembering long-term.
braindb-agent
Persistent memory across sessions via the BrainDB agent. Use at conversation start and whenever you need to recall what you know about the user or save new information to long-term memory.