OpenParable
Skip to content
← Back to skills

Protocol Element Extraction

Documents
protocol-element-extraction

Protocol Element Extraction is an Agent Skill for documents published in the yogsoth-ai/de-anthropocentric-research-engine repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Extract evaluation protocol parameters from papers

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/yogsoth-ai/de-anthropocentric-research-engine/blob/HEAD/skills/protocol-element-extraction/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/protocol-element-extraction, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Protocol Element Extraction SOP

Extract all evaluation protocol parameters from a paper's description of how it evaluated on a specific benchmark. Captures the implementation details that affect reproducibility.

Input

  • paper_content: Full text or relevant sections of the paper
  • benchmark_name: The specific benchmark whose evaluation protocol to extract

Procedure

  1. Locate evaluation/experimental setup sections
  2. Extract all protocol parameters across 5 categories
  3. Flag parameters that are ambiguous or unstated
  4. Compare against original benchmark protocol (if known)
  5. Note any deviations or innovations in protocol

Output

Structured protocol specification with completeness assessment.

Available SOPs

Optional, no fixed order; the final leaf is always a sop.

SOPWhen to use
spawn-agentSpawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent.