ToolUniverse is a collection of tools, interfaces, and supporting components for building AI systems that perform scientific work. It is for developers creating AI scientist agents that use APIs, databases, machine-learning tools, and domain-specific utilities. The catalogue includes skills, commands, an MCP server, an agent, and a hook for working with the ecosystem.
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 mims-harvard/ToolUniverse --skill tooluniverse-fastq-qcgit clone --depth 1 https://github.com/mims-harvard/ToolUniverseWrote 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/mims-harvard/tooluniverse/tooluniverse-fastq-qc)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-fastq-qc"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-fastq-qc/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-fastq-qc"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-fastq-qc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Output Handling · line 150 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00000 | $0.02984 |
| Opus 5.5 | $0.00000 | $0.01194 |
| Sonnet 5.5 | $0.00000 | $0.00597 |
| Haiku 4.5 | $0.00000 | $0.00298 |
Grade A, and why
tooluniverse-fastq-qc 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 1mo 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FASTQ Quality Control & Trimming Decisions
Run quality control on raw sequencing reads, interpret the report, and make an evidence-based decision about whether to trim — using real local command-line tools (FastQC, MultiQC, fastp, Cutadapt, seqkit).
Honesty contract (read first)
This skill drives real binaries. It must never fabricate QC numbers.
- Preflight before anything. Check whether the required tools are on PATH. If a required tool is missing, emit the install plan and STOP. Do not estimate, guess, or describe hypothetical QC results.
- Never auto-trim. Trimming is a decision. QC-only is the default.
Only trim after inspecting adapter content / per-base quality, and only
when the user has confirmed
--mode trim. - Never overwrite raw FASTQs. All outputs go to a separate
--workdir. The input directory is read-only. Trimmed reads are written as NEW files. - If you cannot run, say so. "FastQC is not installed; here is the install plan" is the correct answer — not a made-up PASS/FAIL table.
When to use vs. not
Use this skill when the user wants to:
- Run FastQC / fastp QC on one or more FASTQ (
.fastq,.fq,.gz) files - Interpret a FastQC report (per-base quality, adapter content, etc.)
- Decide whether adapter or quality trimming is needed before downstream work
- Summarize many samples into one MultiQC report
- Count reads, get length/GC stats, or subsample with seqkit
- Trim adapters/low-quality bases with fastp or Cutadapt (explicitly)
Do NOT use this skill for (route elsewhere):
- Differential expression / DEG / fold-change analysis ->
tooluniverse-rnaseq-deseq2 - Read alignment, coverage depth, samtools, BWA ->
tooluniverse-sequence-analysis - Variant calling, VCF, VAF, mutation analysis ->
tooluniverse-variant-analysis - Single-cell / scRNA QC (per-cell metrics, scanpy) ->
tooluniverse-single-cell
Essential inputs to confirm
Before running, confirm with the user (ask if unstated):
What ships with it
4 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.
- 1mo ago First seen · 198 lines · 0 tokens per session scan A 7c423d601518
tooluniverse-fastq-qc is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,984 tokens. 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
ai-agent-tool-routing
Use when designing or reviewing an AI agent tool registry or MCP router: document parameter schemas, caller authorization, execution limits, replay-safe retries and verification evidence.
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.
construct-toy-examples
Generate and analyze simpler examples that satisfy both the assumptions and the conclusion of a theorem statement or subgoal. Use when you are stuck in reasoning and need simpler examples to regain traction, or when you want to see where the assumptions take effect and gain intuition.
obtain-immediate-conclusions
Derive immediate mathematical consequences from a theorem statement or subgoal. Use when starting a new problem, branch, or subgoal, or when cheap progress or a cleaner reformulation is needed before deeper proof search.
clinical-research-analysis-framework
Guided workflow for statistical and ML analysis of clinical data. Use when planning or executing research analyses on MIMIC, eICU, or similar EHR data. Ensures methodological rigor through structured consultation, assumption checking, and stepwise execution with audit trails.
apache-iv-score
Calculate APACHE IV (Acute Physiology and Chronic Health Evaluation IV) score for ICU mortality prediction. Use for severity assessment, hospital mortality prediction, ICU benchmarking, or case-mix adjustment. eICU has pre-computed scores; MIMIC-IV requires custom implementation with diagnosis mapping challenges.