An experiment-review command that judges completed experiment results against a linked idea’s hypothesis and records the outcome in a research wiki.

Use it to mark an idea as supported, partly supported, unsupported, or inconclusive, update its failure details and relationships, and rebuild the wiki’s research summaries.

It turns experimental evidence into a clear decision instead of leaving results disconnected from the idea they were meant to test.

How skyllwt/AutoSci configures Claude Code

About the project

AutoSci is an AI research platform organized around a wiki, with an agent that supports stages of scientific work such as reading, experimentation, writing, and retaining knowledge across projects. It is for people building or using AI-assisted research workflows, with Claude Code, Codex, and OpenCode adaptations available. The catalogue add-ons extend those agent-specific workflows.

skyllwt/AutoSci · 1,706 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to skyllwt/AutoSci. 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/skyllwt/AutoSci/main/.claude/skills/exp-eval/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/skyllwt/AutoSci

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/skyllwt/autosci/exp-eval/github.svg)](https://agentmods.dev/skills/skyllwt/autosci/exp-eval)

Your own site

<a href="https://agentmods.dev/skills/skyllwt/autosci/exp-eval"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/exp-eval/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/skyllwt/autosci/exp-eval"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/exp-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,539 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00029	$0.03539
Opus 5.5	$0.00012	$0.01416
Sonnet 5.5	$0.00006	$0.00708
Haiku 4.5	$0.00003	$0.00354

Measured 2mo ago against content hash 145fb5be1d67, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

exp-eval 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/exp-eval/SKILL.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/exp-eval

Convert completed experiment results into wiki knowledge updates. Review LLM acts as an impartial judge (following cross-model-review), independently evaluating how experimental results affect the linked idea's hypothesis. Four verdict paths: supported → idea validated / partially_supported → supplementary experiments / not_supported → idea failed / inconclusive → debug. Auto-updates the linked idea's status, failure_reason, and graph edges.

Inputs

experiment: slug from wiki/experiments/ (status must be completed)
--auto (optional): automatic mode — do not pause for user confirmation before wiki updates (used when called by /research)

Outputs

wiki/ideas/{linked-idea}.md — updated status, failure_reason, date_resolved
wiki/experiments/{slug}.md — ## Idea updates section filled in (records the linked idea's status transition; replaces the legacy ## Claim updates heading)
wiki/graph/edges.jsonl — new supports / invalidates edges added (experiment → idea)
wiki/graph/context_brief.md — rebuilt
wiki/graph/open_questions.md — rebuilt
wiki/log.md — appended log entry
VERDICT_REPORT (printed to terminal) — verdict result, wiki change summary, next step suggestions

Wiki Interaction

Reads

wiki/experiments/{slug}.md — experiment results: outcome, key_result, metrics, full Results section, linked_idea
wiki/ideas/{linked-idea}.md — linked idea current state: status, ## Hypothesis, ## Risks
wiki/experiments/*.md — sibling experiments with the same linked_idea (aggregate assessment)
wiki/graph/context_brief.md — global context
.claude/skills/shared-references/cross-model-review.md — reviewer independence principle

Writes

wiki/ideas/{linked-idea}.md — update status, failure_reason, date_resolved
wiki/experiments/{slug}.md — fill in ## Idea updates section
wiki/graph/edges.jsonl — add supports / invalidates edges (experiment → idea)
wiki/graph/context_brief.md — rebuild
wiki/graph/open_questions.md — rebuild
wiki/log.md — append operation log

Read the full file on GitHub · 321 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 · 321 lines · 29 tokens per session scan A 145fb5be1d67

Subscribe to this mod's changes

exp-eval is a skill published in the GitHub repository skyllwt/AutoSci (1,706 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 3,539 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.

Research Scientific

exp-eval next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
exp-evalskyllwt/AutoSci	Skill	1.7k	1mo ago	MIT	A	29	Claude Code
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	2d 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	today	MIT	A	43	Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmed	Skill	5.8k	yesterday	Apache-2.0	A	205	Claude Code

AutoSci: Skill for Claude Code