Skip to content
Automation
Skill

/reproducibility-third-party-verification

(Proposal, unverified) Attempt to verify a paper's reported results by actually executing its released code/scripts against its own reported configuration — the only SOP in this package whose action type is code execution rather than text reading/judgment. Use this after

From plugin
de-anthropocentric-research-engine
393200 skills
Install
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill reproducibility-third-party-verification --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/reproducibility-third-party-verification

Context preview

The summary Claude sees to decide when to auto-load this skill.

(Proposal, unverified) Attempt to verify a paper's reported results by actually executing its released code/scripts against its own reported configuration — the only SOP in this package whose action type is code execution rather than text reading/judgment. Use this after

SKILL.md

reproducibility-third-party-verification.SKILL.md
name: reproducibility-third-party-verification
description: (Proposal, unverified) Attempt to verify a paper's reported results by actually executing its released code/scripts against its own reported configuration — the only SOP in this package whose action type is code execution rather than text reading/judgment. Use this after unit-classification has extracted the paper's reported configuration/hyperparameters as classified units; "not_attempted" is a correct, common output when the paper's own reporting is too incomplete to run, not a failure of this SOP.
version: 1.0.0
category: paper-reading
type: sop
execution: subagent
prompt: ./prompt.md
input: 'classified_units (list of {unit_text, offset, label})'
output: 'verification_result (list of {claim, reproducible, notes})'
dependencies:
  sops:
  - spawn-agent

Reproducibility Third-Party Verification (Proposal)

Actually runs code to check reported results against the paper's own extracted configuration — unique action type (execution) in this package. Fills the evidence-verification × engineering-metadata gap in the evaluative-stance × content-layer matrix.

Execution

Subagent — spawned via spawn-agent skill.

Dependency: unit-classification, not raw full_text (graph correction L20)

This SOP needs the paper's reported configuration already pulled out in structured form before attempting to verify it — hence its input is `classified_units`, not `full_text` directly. An earlier graph draft had this SOP depending on nothing upstream, which meant it had no defined way to get the structured claims it needs to check.

Proposal Status — Read Before Modifying

No primary-source precedent, no inter-rater-reliability baseline. Keep "(Proposal, unverified)" in the description until real usage validates the method. Given the code-execution action type, treat any scope expansion here with more caution than the other 3 proposal SOPs.

<!-- BEGIN available-tables (generated) -->

Available SOPs

| SOP | When to use | | --- | --- | | spawn-agent | Spawn a customized CC subagent with full MCP tool access. |

<!-- END available-tables (generated) -->

Read more
Ships withde-anthropocentric-research-engine

The complete research orchestration system for AI-native science. What It Does Design Philosophy Architecture (v3.2.2) Quick Start Configuration Roadmap License DARE is not a tool that helps you do research. It is the researcher.

Get the whole plugin
Stats
393
Stars
34
Forks
Active
Maintenance
HTML
Language
Apache-2.0
License
19h ago
Last commit
6mo ago
Created

Repo: yogsoth-ai/de-anthropocentric-research-engine