Zero Shot Audit

by jongwony

Zero Shot Audit is an AI Engineering skill for Claude Code, published by jongwony in epistemic-protocols.

161 stars15 forkson jongwony/epistemic-protocolsAdded 2026/09/08+1% in starsRepository updated 2026/09/08

View source on GitHub Download repo ZIP

ai-collaborationclaude-codeepistemologymetacognitionplugin

Install in seconds

Install Zero Shot Audit

Copy Zero Shot Audit into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/jongwony/epistemic-protocols/tree/main/epistemic-cooperative/skills/zero-shot ~/.claude/skills/zero-shot

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/jongwony/epistemic-protocols.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: epistemic-cooperative/skills/zero-shot/SKILL.md in jongwony/epistemic-protocols
Installs to: ~/.claude/skills/zero-shot
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What Zero Shot Audit does

Zero Shot Audit reviews LLM-facing prose for few-shot anchoring and example lists that narrow a principle’s application. Use it to spot read-only findings in skill, agent, or output-style instructions.

Zero Shot Audit is cataloged under AI Engineering on DirSkills. Zero Shot Audit comes from a repository tagged ai-collaboration, claude-code, epistemology, metacognition and plugin.

Documentation

README

Excerpt

Zero-Shot Audit

A semantic audit of LLM-facing prose for the Zero-Shot Instruction Preference: state principles, not anchoring examples. Read-only — it emits structured findings and writes no fixes. The human author decides which to rewrite, mark as scope-clarifying, or dismiss.

Purpose

Surface few-shot patches that anchor the model to specific instances rather than letting it apply the principle to novel contexts. Anchoring drift survives deterministic structural checks — it is a meaning-level pattern, so a semantic reviewer catches what literal pattern matching cannot.

This is the opening of the README. Read the full README on GitHub.

Commands Zero Shot Audit provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/zero-shot

Frequently asked about Zero Shot Audit

What else does jongwony publish alongside Zero Shot Audit?
Zero Shot Audit is one of 25 skills that DirSkills catalogs from jongwony/epistemic-protocols, the repository it ships in. Its siblings there include Aitesis Protocol, Analogia Protocol and Contextualize. Each one is a separate skill with its own page in this directory, installs the same way Zero Shot Audit does, and is maintained by jongwony in that same repository. The rest of the collection is listed on the jongwony/epistemic-protocols page.
How does Zero Shot Audit compare to other AI Engineering skills?
Zero Shot Audit ranks #3453 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Zero Shot Audit against them. Open each page to compare what they document and how they install.