What is paper-to-experiment?

A workflow for turning a physics research paper into a validated experiment plan for a specific simulation framework. The plan can be run to produce a report and at least one figure.

Use it to reproduce part of a physics paper, register any new simulation components, and create a runnable configuration file.

It prevents unsupported experiment settings by requiring the paper PDF, registered framework components, and schema validation before the plan is written.

How thematteroftime/agentic-md-for-dummies configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to thematteroftime/agentic-md-for-dummies. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/thematteroftime/agentic-md-for-dummies/main/.claude/skills/paper-to-experiment/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/thematteroftime/agentic-md-for-dummies

Made for: Claude Code.

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/thematteroftime/agentic-md-for-dummies/paper-to-experiment/github.svg)](https://agentmods.dev/skills/thematteroftime/agentic-md-for-dummies/paper-to-experiment)

Your own site

<a href="https://agentmods.dev/skills/thematteroftime/agentic-md-for-dummies/paper-to-experiment"><img src="https://agentmods.dev/badge/skills/thematteroftime/agentic-md-for-dummies/paper-to-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/thematteroftime/agentic-md-for-dummies/paper-to-experiment"><img src="https://agentmods.dev/badge/skills/thematteroftime/agentic-md-for-dummies/paper-to-experiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,280 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	$0.00077	$0.04280
Opus 5.5	$0.00031	$0.01712
Sonnet 5.5	$0.00015	$0.00856
Haiku 4.5	$0.00008	$0.00428

Measured 2mo ago against content hash d44c58a64dc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

paper-to-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.

.claude/skills/paper-to-experiment/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paper → Experiment Skill

Turn a physics paper into a validated configs/plan_<topic>.json that python scripts/run_experiment.py can launch directly. The output of one run of this skill is a campaign that — when run end-to-end — produces a report.md and at least one figure per run dir. Anything less is incomplete.

This skill is a gate, not a free-form writer. You follow the template, the schema, and the registry. You don't invent fields. You surface ambiguity to the user before writing JSON.

Hard rules (no exceptions)

Registry first. Open references/force_types.md AND tools/registry.py (the framework's forwarding station for forces / lattices / analyzers / plotters / aggregators / visualizers) BEFORE proposing any field. The skill works only with registered strings — for any extension, you must walk through §"Adding a new force type" 8-step process and register the new class in tools/registry.py:_REGISTRY AND in the matching package's local __init__.py.
Paper PDF on disk. Step 2 requires a real PDF under papers/<slug>.pdf. If the user only has an abstract / link / mental model, stop and ask them to put the PDF in papers/. Abstract-only reproduction is unsupported — it has produced bad reproductions in the past.
Citations are mandatory. Every observable in §1 of the design doc must cite a paper Eq. or Fig. number. If a number isn't in the paper, mark it with * and explain in §11. No bare claims like "expected to converge."
Smoke before production. Every config you emit must have pipeline.smoke=true and smoke_steps ≥ 100 unless the user explicitly asks otherwise (and you note the override in _comment).
Validation gate. Before announcing the config is ready, run python scripts/validate_config.py <path> --strict. If it returns non-zero, fix the issues and re-run; do not hand off a failing config.
Cost budget. If the validator reports single-run wall > 24 hr or VRAM > 8 GB, propose smaller N or steps rather than asking the user to approve a 1-day GPU burn.

Read the full file on GitHub · 244 lines

Files

What ships with it

15 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.

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 · 244 lines · 77 tokens per session scan A d44c58a64dc7

Subscribe to this mod's changes

paper-to-experiment is a skill published in the GitHub repository thematteroftime/agentic-md-for-dummies (6 stars, last pushed 6mo ago), licensed MIT. It adds 77 tokens to every session and 4,280 once invoked, about $0.0003 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 2026-08-31.

Educational Research Scientific complex-plasma molecular-dynamics physics-simulation reproducible-research taichi

paper-to-experiment next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
paper-to-experimentthematteroftime/agentic-md-for-dummies	Skill	6	6mo ago	MIT	A	77	Claude Code
figure-styleaipoch/open-science	Skill	5.5k	yesterday	Apache-2.0	A	91	Claude Code, Codex
remote-compute-sshaipoch/open-science	Skill	5.5k	yesterday	Apache-2.0	A	53	Claude Code, Codex
paper-narrativeaipoch/open-science	Skill	5.5k	yesterday	Apache-2.0	A	58	Claude Code, Codex
figure-composeraipoch/open-science	Skill	5.5k	yesterday	Apache-2.0	A	93	Claude Code, Codex
literature-reviewaipoch/open-science	Skill	5.5k	yesterday	Apache-2.0	A	54	Claude Code, Codex
scvi-toolsaipoch/open-science	Skill	5.5k	yesterday	Apache-2.0	A	100	Claude Code, Codex

agentic-md-for-dummies: Skill for Claude Code