DeepScientist is a local research studio that manages the cycle from baseline experiments through research findings and paper-ready outputs. Researchers use it to organize autonomous scientific investigations, review progress, and take control when needed. The catalogue add-ons provide workflows and agent integrations for running research projects with it.
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 ResearAI/DeepScientist --skill analysis-campaigngit clone --depth 1 https://github.com/ResearAI/DeepScientistWrote 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/researai/deepscientist/analysis-campaign)<a href="https://agentmods.dev/skills/researai/deepscientist/analysis-campaign"><img src="https://agentmods.dev/badge/skills/researai/deepscientist/analysis-campaign.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00034 | $0.04334 |
| Opus 5 | $0.00017 | $0.02167 |
| Sonnet 5 | $0.00007 | $0.00867 |
| Haiku 4.5 | $0.00003 | $0.00433 |
Grade A, and why
analysis-campaign 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 7d 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analysis Campaign
Use this skill when follow-up evidence is needed after a durable result. The goal is to answer a bounded, resource-aware evidence question, not to keep opening more slices just because they are imaginable.
Match signals
Use analysis-campaign when:
- a durable main result already exists and follow-up evidence is needed
- the quest needs ablations, robustness checks, sensitivity checks, failure analysis, error analysis, efficiency or cost checks, or limitation-boundary checks
- writing, review, or rebuttal pressure exposed an evidence gap that should be answered by bounded follow-up slices
Do not use analysis-campaign when:
- the quest still lacks a credible main run or accepted baseline and the proposed work depends on that missing reference
- the next step is obviously another main experiment rather than follow-up evidence work
- the proposed slice does not connect to a parent claim, parent result, paper gap, reviewer item, or route decision
One-sentence summary
Answer the smallest evidence question that changes, confirms, or blocks a parent claim, then stop when the next route is clear.
Control workflow
- Lock the parent object, evidence question, comparison target, and stop condition. Make explicit what claim, failure mode, or route decision is actually being tested.
- Audit the real execution envelope before designing the slice set. Make explicit the current device and runtime limits: available GPU or CPU class, memory, wall-clock budget, storage, concurrency, required dependencies, and any queue or service constraints that materially limit what can run now.
- Choose the lightest analysis route and the smallest slice set that can answer the question within that envelope. Prefer slices with the highest soundness gain per unit of compute, time, or engineering effort. Run claim-critical slices first and mark infeasible slices explicitly instead of quietly keeping them in scope.
- Keep slices isolated and comparable. Record exactly what changed, what stayed fixed, and whether apples-to-apples comparison still holds.
- Record slice-level evidence before making any campaign-level claim. Every meaningful slice should leave a durable outcome and a claim update.
- Aggregate only the decision-relevant findings and route the next step. End in continue, write, experiment, idea, decision, blocker, or stop.
What ships with it
7 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.
- references/artifact-flow-examples.md 2.7 KB
- references/boundary-cases.md 2.8 KB
- references/campaign-checklist-template.md 2.4 KB
- references/campaign-design.md 2.1 KB
- references/campaign-plan-template.md 2.2 KB
- references/operational-guidance.md 6.8 KB
- references/writing-facing-slice-examples.md 1.9 KB
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.
- 7d ago First seen · 301 lines · 34 tokens per session scan A 9dcb5f01f030
analysis-campaign is a skill published in the GitHub repository ResearAI/DeepScientist (3,315 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 4,334 once invoked, about $0.0002 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…