sue-overall-audit

Audit SUE skill family definitions for contract drift and cross-tool compatibility.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/dongzhuoyao/deepresearch --skill sue-overall-audit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sue-overall-audit
Source: https://github.com/dongzhuoyao/deepresearch/tree/main/.codex/skills/sue-overall-audit
Command: npx skills add https://github.com/dongzhuoyao/deepresearch --skill sue-overall-audit

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill solves the problem of drift, inconsistency, and contract violations across the SUE scale-up experiment skill family, which can break experiment workflows, waste inode resources, cause compatibility issues with AI coding tools, and prevent the framework from running on different user machines without source code edits.

Core Features & Use Cases

  • Full Family Structural Audit: Scans all canonical .codex/skills/sue-* skill definitions, project memory files, and cross-skill references to catch duplicate sections, stale links, and structural drift.
  • Cross-Tool Compatibility Checks: Verifies that SUE skills are discoverable and invokable from Codex, Kimi, Claude Code, and GLM via correct symlink pointers, flagging global or local real copies that cause stale drift.
  • Contract Compliance Validation: Enforces critical rules including inode-safe output defaults, DeepResearch route independence, config minimization, privacy split boundaries, and pre-submission environment list requirements.
  • Use Case: A team maintaining the SUE framework runs this audit after adding new skills, modifying existing contracts, or pulling repository updates to catch issues before they break user experiment workflows or violate portability requirements.

Quick Start

Use the sue-overall-audit skill to run a full consistency and compliance check on all SUE scale-up experiment skills in your DeepResearch repository.

Frequently Asked Questions about sue-overall-audit

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

FAQPage Schema
How do I audit AI coding skills for contract drift and structural inconsistencies?

To audit AI coding skills for contract drift, you scan canonical skill definitions, project memory files, and cross-skill references to identify duplicate sections, stale links, and structural inconsistencies across the skill family.

What does inode-safe output mean for AI experiment workflows?

Inode-safe output for AI experiment workflows means enforcing default output configurations that prevent excessive file generation, thereby avoiding inode resource exhaustion and maintaining framework portability across user machines.

How do I check if my skills are compatible with multiple AI coding tools like Codex and Claude Code?

To check if skills are compatible with multiple AI coding tools like Codex and Claude Code, you verify that correct symlink pointers exist for discoverability, flagging global or local real copies that cause stale drift.

How do I validate portability requirements for scale-up experiment skills?

To validate portability requirements for scale-up experiment skills, you enforce DeepResearch route independence, config minimization, privacy split boundaries, and AI tool symlink requirements to ensure execution without source code edits.

When should I run a consistency and compliance check on my skill repository?

You should run a consistency and compliance check on your skill repository after adding new skills, modifying existing contracts, or pulling repository updates to catch issues before they break user experiment workflows.

Does the skill compliance audit require a remote sandbox or job submission?

No, the skill compliance audit does not require a remote sandbox or job submission; it scans local skill definitions and memory Markdown files with no remote side effects to validate contract rules.