What is write-experiment?

A skill for writing the experiments section of a research paper in LaTeX. This section reports benchmark results, comparisons, ablation studies, and statistical analysis.

Use it after experiments, figures, and at least one recorded contribution are available to describe results, baselines, ablations, and comparisons.

It turns collected experiment results and publication figures into a consistent paper section instead of requiring the author to assemble them manually.

write-experiment — Skill for Claude Code and Codex by DataLab-atom

Install

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.

Any agent

npx skills add DataLab-atom/EvoAny --skill write-experiment

Clone the repo

git clone --depth 1 https://github.com/DataLab-atom/EvoAny

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/datalab-atom/evoany/write-experiment/github.svg)](https://agentmods.dev/skills/datalab-atom/evoany/write-experiment)

Your own site

<a href="https://agentmods.dev/skills/datalab-atom/evoany/write-experiment"><img src="https://agentmods.dev/badge/skills/datalab-atom/evoany/write-experiment/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/datalab-atom/evoany/write-experiment"><img src="https://agentmods.dev/badge/skills/datalab-atom/evoany/write-experiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 955 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00026	$0.00955
Opus 5.5	$0.00010	$0.00382
Sonnet 5.5	$0.00005	$0.00191
Haiku 4.5	$0.00003	$0.00096

Measured 2mo ago against content hash b8a30e584422, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

write-experiment 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 2mo 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.

plugin/skills/write-experiment/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/write-experiment — Experiment Chapter Writing

D2: Experiment chapter generation — transforms B-layer experiment results and figures into a comprehensive experimental section.

Purpose

Read the B-layer experiment results (metrics, figures) and the C-layer forest contributions, and generate a well-structured Experiment section in LaTeX format.

Usage

/write-experiment <forest_id> [--venue <venue_name>]

Examples:

/write-experiment exp-2024-run-01 --venue NeurIPS
/write-experiment my-forest --venue CVPR

Prerequisites

Before running this skill, ensure:

B-layer experiments have been executed and results collected
Viz figures have been generated — call viz_generate during Phase 2 Step 4 of /research-loop to generate ablation curves, score distributions, and contribution heatmaps before proceeding. If research/figures/ is empty, generate them now:
- Call viz_generate on each confirmed hypothesis
- Call viz_polish for publication-quality rendering
- Record the output paths for reference in the chapter
The forest has at least one contribution recorded

Behavior

Step 1: Gather Experiment Data

Read the forest: research_get_forest(forest_id) — get contributions and experiment nodes
Collect all experiment results:
- Metrics from bench_run outputs
- Figure paths from viz_generate outputs (stored in research/figures/)
- Polished figures from viz_polish outputs
List all figures: check research/figures/ directory
- If no figures exist: call viz_generate now for ablation curves and main result plots
- Call viz_polish on each figure before including in the chapter

Step 2: Organize Results

Group results into categories:

Main Results — primary performance comparisons
Ablation Studies — contribution of individual components
Sensitivity Analysis — robustness to hyperparameters
Additional Experiments — any supplementary results

Step 3: Synthesize the Experiment Chapter

Read the full file on GitHub · 120 lines

Changes

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.

2mo ago First seen · 120 lines · 26 tokens per session scan A b8a30e584422

Subscribe to this mod's changes

write-experiment is a skill published in the GitHub repository DataLab-atom/EvoAny (37 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 955 once invoked, about $0.0001 per session on Opus 5.5. 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.

Scientific Writing and docs

write-experiment next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
write-experimentDataLab-atom/EvoAny	Skill	37	6mo ago	Apache-2.0	A	26	Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	3d ago	Apache-2.0	A	123	Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	83	Claude Code
matlabK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	44	Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	71	Claude Code, Codex
research-engineerdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	43	Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmed	Skill	5.8k	yesterday	Apache-2.0	A	205	Claude Code