AutoResearchClaw is a system that turns a research idea into a scientific paper through autonomous and collaborative AI research workflows. It is for researchers who want agents to investigate questions, run experiments, and produce papers, with optional human guidance. Catalogue skills and agents provide parts of its research workflow.
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 aiming-lab/AutoResearchClaw --skill metabolic-study-plannergit clone --depth 1 https://github.com/aiming-lab/AutoResearchClawWrote 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/aiming-lab/autoresearchclaw/metabolic-study-planner)<a href="https://agentmods.dev/skills/aiming-lab/autoresearchclaw/metabolic-study-planner"><img src="https://agentmods.dev/badge/skills/aiming-lab/autoresearchclaw/metabolic-study-planner/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/aiming-lab/autoresearchclaw/metabolic-study-planner"><img src="https://agentmods.dev/badge/skills/aiming-lab/autoresearchclaw/metabolic-study-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00069 | $0.01706 |
| Opus 5 | $0.00034 | $0.00853 |
| Sonnet 5 | $0.00014 | $0.00341 |
| Haiku 4.5 | $0.00007 | $0.00171 |
Grade A, and why
metabolic-study-planner 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 10d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metabolic Study Planner
Overview
Use this skill before gsmm-builder, fba-simulator, and flux-analyzer when
the project starts from a broad prompt such as "do a metabolic flux analysis
paper" or "find a publishable idea in microbial metabolism".
The goal is to turn a vague topic into a concrete, executable, paper-shaped study plan:
organism + model + condition + perturbation + metric + figure set + claim
This is the MFA analogue of choosing a collider process and parameter scan before generating events.
Planning Inputs
Extract or infer the following:
| Field | Examples |
|---|---|
| Biological scope | microbial metabolism, cancer metabolism, yeast fermentation, tuberculosis |
| Organism | E. coli, S. cerevisiae, human Recon3D, M. tuberculosis |
| Model source | BiGG ID, local SBML/JSON, manually constructed toy model |
| Objective | biomass, product secretion, ATP maintenance, dual objective |
| Condition | aerobic, anaerobic, carbon source, nutrient limitation |
| Perturbation | gene knockout, reaction knockout, medium swap, oxygen sweep |
| Target output | growth, product yield, essential genes, secretion profile |
| Paper type | mechanism hypothesis, metabolic engineering strategy, benchmark, reproduction |
If the user provides no organism, start with one of these low-risk defaults:
| Default | Model | Why |
|---|---|---|
| E. coli K-12 | iJO1366 or core model |
Fast, well curated, standard for FBA papers |
| S. cerevisiae | iMM904 |
Fermentation and product-yield studies |
| Human metabolism | Recon3D |
Disease metabolism, but larger and harder |
| M. tuberculosis | iNJ661 |
Essentiality and drug-target hypotheses |
Prefer E. coli for fully autonomous first runs because it is fast and interpretable.
Study Archetypes
Archetype A: Knockout Strategy for Product Overproduction
Use when the topic mentions metabolic engineering, bio-production, yield, or fermentation.
Plan:
- Select a product exchange reaction, e.g. succinate, lactate, ethanol, acetate.
- Run WT FBA and pFBA under a defined medium.
- Screen single reaction/gene knockouts.
- Rank perturbations by product secretion subject to retaining growth.
- Validate top candidates with FVA and carbon-source sensitivity.
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.
- 10d ago First seen · 242 lines · 69 tokens per session scan A c61bc06caa2f
metabolic-study-planner is a skill published in the GitHub repository aiming-lab/AutoResearchClaw (14,375 stars, last pushed 21d ago), licensed MIT. It adds 69 tokens to every session and 1,706 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 2026-08-30.
Other skills, from other repositories
adme-property-predictor
Predict ADME (Absorption, Distribution, Metabolism, Excretion) properties for drug candidates using cheminformatics models and molecular descriptors. Evaluates drug-likeness, bioavailability, and pharmacokinetic profile to guide lead optimization and candidate selection in drug discovery.
aclawdemy
The academic research platform for AI agents. Submit papers, review research, build consensus, and push toward AGI — together.
arxiv-summarizer-orchestrator
End-to-end orchestration skill for periodic arXiv collection and reporting using three sub-skills: arxiv-search-collector, arxiv-paper-processor, and arxiv-batch-reporter. Supports manual language control across all markdown outputs and Stage-B processing strategy (subagentparallel default max 5, or serial).
baseline-comparison-audit
Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent…
eval-design-forensics
Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan…
proof-derivation-forensics
Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its theorem, or does it skip an obligation, assume its own conclusion, take an invalid step, drift a symbol's meaning, or smuggle an unstated assumption? Decides from the WRITTEN proof/derivation …