skills.rest
tubtrb
tubtrbCOMMUNITY
Explore all skills by this author →
GitHub

ai-corpus-verification

Collect and analyze external-AI draft corpora to validate manual YAML workflows.

Updated Mar 15, 2026
Search Tags:#reproducibility#prompt-testing#corpus-analysis#ai-corpus-verification#yaml-flow#debug-app#prompt-packs
One-click install
npx skills add https://github.com/tubtrb/autoreport --skill ai-corpus-verification
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-corpus-verification
Source: https://github.com/tubtrb/autoreport/tree/main/codex/skills/ai-corpus-verification
Command: npx skills add https://github.com/tubtrb/autoreport --skill ai-corpus-verification

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yaml, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Collect and analyze real external-AI draft corpora for autoreport's manual YAML workflow, enabling robust evaluation across multiple providers and prompt packs.

Core Features & Use Cases

  • Collect real-world AI drafting samples across providers (ChatGPT, Gemini, Claude) for reproducible testing.
  • Compare prompt packs and surface failure taxonomy to feed debug-corpus surfaces and tracking tables.
  • Produce artifact-backed results and data surfaces for the debug app, including metrics and summaries.

Quick Start

Run a corpus-collection cycle to seed the local manual-draft-check with prompts and store the results.

Frequently Asked Questions about ai-corpus-verification

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I validate YAML workflows using AI draft corpora from multiple providers?▼

Reproducible corpus analysis requires a provider-aware sampling pipeline to collect drafts, artifact storage under an output directory, and guidance for consistent collection and reporting to ensure reliable cross-provider comparisons.

How do I compare prompt packs across different AI providers for YAML generation?▼

Comparing prompt packs involves running a corpus-collection cycle across providers like ChatGPT, Gemini, and Claude, then rerunning the manual-draft-check to produce artifact-backed metrics and failure summaries for analysis.

Does YAML workflow verification work with ChatGPT, Gemini, and Claude draft outputs?▼

Yes, the verification process supports ChatGPT, Gemini, and Claude by applying a provider-aware sampling pipeline to collect drafts and rerun the manual-draft-check to surface failure taxonomy for each provider.

What is the best way to debug YAML workflow failures in AI-generated drafts?▼

The best way to debug YAML workflow failures is to rerun the /api/manual-draft-check against collected AI draft corpora to surface a detailed failure taxonomy, which then feeds directly into debug-app corpus tracking tables.

Do I need YAML to run AI corpus verification for prompt testing?▼

Yes, YAML is a required dependency to run AI corpus verification, as the Skill validates autoreport's manual YAML workflow and hardens YAML flows by analyzing external-AI draft outputs and comparing prompt packs.

Related Skills

Explore More Data & Analytics Skills→
tiankong0101-bytetiankong0101-byte

ask

Route prompts to local Claude, Codex, or Gemini CLIs and store responses as artifacts.

Community
Intermediate
gyy0592gyy0592
7

gen-report-detailed

Generate detailed 13-section markdown experiment reports from flame_moonshot training logs and metrics.

Community
Advanced
ovachieverovachiever
52

tensorboard

Visualize ML training metrics and debugging signals via interactive dashboards.

Community
Intermediate
ThrookieThrookie
2

prompt-optimizer

Analyze draft prompts and map them to ECC components for optimized output.

Community
Advanced