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 flonat/flonat-research --skill synthetic-datagit clone --depth 1 https://github.com/flonat/flonat-researchWrote 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/flonat/flonat-research/synthetic-data)<a href="https://agentmods.dev/skills/flonat/flonat-research/synthetic-data"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/synthetic-data/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/flonat/flonat-research/synthetic-data"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/synthetic-data.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 | $0.00048 | $0.02294 |
| Opus 5 | $0.00024 | $0.01147 |
| Sonnet 5 | $0.00010 | $0.00459 |
| Haiku 4.5 | $0.00005 | $0.00229 |
Grade A, and why
synthetic-data 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 5d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthetic Data Generation
Generate structurally realistic synthetic datasets for pilot testing, power analysis, and method development.
Modes
| Mode | What it produces | Entry point |
|---|---|---|
| From design | Synthetic data matching an existing experiment design document | "Generate test data for my experiment" |
| From schema | Synthetic data from a user-described structure | "Create a dataset with these variables" |
| Calibrated | Synthetic data calibrated to published summary statistics | "Make fake data matching these descriptives" |
Default: From schema. If an experiment design document exists in docs/, auto-select From design. If user provides published statistics, auto-select Calibrated.
When to Use
- Testing analysis code before real data collection
- Power analysis via simulation (complements
experiment-designPower mode) - Method development and debugging estimation pipelines
- Generating pilot data for grant proposals or ethics applications
- Teaching demonstrations with realistic-looking data
When NOT to Use
- Designing the experiment itself -->
experiment-design - Running analysis on real data -->
data-analysis - Auditing identification strategy -->
causal-design
Workflow
Step 1: Detect Mode
Detect from context or ask:
| Signal | Mode |
|---|---|
docs/experiment-design.md exists |
From design |
| User describes variables, types, relationships | From schema |
| User provides means, SDs, correlations from a paper | Calibrated |
| Ambiguous | Ask |
Step 2: Interview for Data Structure
Gather the following (adapt questions to mode):
| Parameter | Question | Default |
|---|---|---|
| Variables | What variables do you need? | — |
| Types | Continuous, binary, ordinal, categorical? | Infer from name |
| Sample size | How many observations? | 500 |
| Treatment | Is there a treatment variable? How many arms? | — |
| Effect size | Expected treatment effect (Cohen's d, OR, etc.)? | 0.3 (small-medium) |
| Correlations | Which variables should be correlated? How strongly? | — |
| Clustering | Are observations nested (e.g., students in classrooms)? | No |
| Panel structure | Multiple time periods? How many? | Cross-section |
| Missing data | Should the data include realistic missingness? | No |
| Language | R or Python? | Detect from project or ask |
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.
- 5d ago First seen · 248 lines · 48 tokens per session scan A 03e1730714d3
synthetic-data is a skill published in the GitHub repository flonat/flonat-research (132 stars, last pushed 14d ago), licensed MIT. It adds 48 tokens to every session and 2,294 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 2026-09-03.
Other skills, from other repositories
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
optimization-loop
The optimizer brain for the ladder-foundry pretraining loop. Runs the two-level nested batch loop, delegates gating to gateeval, attributes a failing batch to one weight (attribute-first), and recovers from disk after compaction. Control flow is fully scripted; only the backprop attribution is a judgment call.
ablation-design
Design ablation studies to isolate component contributions in ML systems.
alterlab-pyhealth
Develops, tests, and deploys clinical machine learning models with the PyHealth healthcare AI toolkit. Use when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare…
alterlab-deepchem
Runs molecular machine learning with DeepChem — diverse featurizers, pre-built MoleculeNet benchmark datasets, and pre-trained models (ChemBERTa, GROVER) for property prediction (ADMET, toxicity, solubility) via traditional ML or graph neural networks. Use when running end-to-end molecular ML experiments that need…
alterlab-esm
Run ESM protein language models — ESM3 for generative multimodal protein design across sequence, structure, and function, and ESM C for efficient embeddings and representations — locally or via the cloud Forge API. Use when working with protein sequences, structures, or function prediction, designing novel proteins…