zero-shot SKILL.md skillA

zero-shot from jongwony/epistemic-protocols is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jongwony/epistemic-protocols/zero-shot@git:20260713.ac1eae9

Pins git:20260713.ac1eae9 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jongwony/epistemic-protocols
Path
epistemic-cooperative/skills/zero-shot/SKILL.md
Versions recorded
4
Latest version
git:20260713.ac1eae9, committed Jul 13, 2026
First version recorded
Jun 18, 2026
Size
6,725 bytes
Repository stars
175
License
MIT

Use when the user asks to "check zero-shot", "audit few-shot anchoring", "find example anchoring", or invokes /zero-shot. Read-only audit of LLM-facing prose: principle over anchoring examples.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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.

## Inputs

**Manual invocation only** (interactive `/zero-shot`):
- The caller passes target file paths or a glob; with no argument, the skill enumerates the in-scope set under the working tree HEAD.
- Files are read at their working-tree state — the post-edit, pre-commit content the author is about to ship.

## Scope

**In scope** (LLM-facing prose where this principle applies):
- Skill instruction files (`*/skills/*/SKILL.md`), considered outside formal/definition blocks
- Agent system-prompt files (`*/agents/*.md`)
- Output-style files
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jongwony/epistemic-protocols/zero-shot@sha256:264d1ed8a2f4c6e9

The line at the top of this page pins the label git:20260713.ac1eae9, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_yumh6jbn6oeabixb.svg)](https://markdownregistry.com/a/art_yumh6jbn6oeabixb)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Jun 18, 2026 and Jul 13, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
git:20260713.ac1eae9 latest2026-07-13 ac1eae9 6,725 BA view · diff
git:20260713.e2497fe2026-07-13 e2497fe 6,657 BA view · diff
git:20260712.25789bf2026-07-12 25789bf 6,637 BA view · diff
git:20260618.b0877722026-06-18 b087772 6,629 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6725 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

jongwony/epistemic-protocols · 175 stars · license MIT · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_yumh6jbn6oeabixb
GET https://markdownregistry.com/api/v1/resolve?ref=jongwony/epistemic-protocols/zero-shot
GET https://markdownregistry.com/api/v1/blob/264d1ed8a2f4c6e94404403adf44357d316652a9e916e478c723403d982d42a0

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from jongwony/epistemic-protocols

AGENTS.md@.claude/principles AGENTS.md file
jongwony/epistemic-protocols · .claude/principles/AGENTS.md
git:20261004.309cd39 · audit A · 175 stars
CLAUDE.md@.claude/principles CLAUDE.md file
jongwony/epistemic-protocols · .claude/principles/CLAUDE.md
git:20260804.5f2d14a · audit B · 175 stars
encapsulation SKILL.md skill
jongwony/epistemic-protocols · .claude/skills/encapsulation/SKILL.md · This skill should be used when the user asks to "audit plugin encapsulation", "check self-containment semantics", "find…
git:20260812.1f50d34 · audit A · 175 stars
formal-review SKILL.md skill
jongwony/epistemic-protocols · .claude/skills/formal-review/SKILL.md · This skill should be used when the user asks to "formal review", "formal lens review", or invokes /formal-review. A…
git:20261004.2323a31 · audit A · 175 stars
outcome SKILL.md skill
jongwony/epistemic-protocols · .claude/skills/outcome/SKILL.md · This skill should be used when the user asks to "run the outcome eval", "paired bare vs protocol", "which decisions did…
git:20261015.46b405a · audit A · 175 stars
realize SKILL.md skill
jongwony/epistemic-protocols · .claude/skills/realize/SKILL.md · This skill should be used when the user asks to "run the eval", "test whether the protocol actually works at runtime"…
git:20261015.46b405a · audit A · 175 stars
rederive SKILL.md skill
jongwony/epistemic-protocols · .claude/skills/rederive/SKILL.md · This skill should be used when a contributor names a skill whose Lean contract is to be re-derived — a core protocol…
git:20261102.43de7b7 · audit A · 175 stars
release SKILL.md skill
jongwony/epistemic-protocols · .claude/skills/release/SKILL.md · Release for this repo — CalVer tag + narrative prepend.
git:20261015.ef40fb2 · audit A · 175 stars
verify SKILL.md skill
jongwony/epistemic-protocols · .claude/skills/verify/SKILL.md · This skill should be used when the user asks to "verify protocols", "check consistency before commit", "validate…
git:20261014.426da72 · audit A · 175 stars
AGENTS.md AGENTS.md file
jongwony/epistemic-protocols · AGENTS.md
git:20261104.265d6fb · audit A · 175 stars
CLAUDE.md CLAUDE.md file
jongwony/epistemic-protocols · CLAUDE.md
git:20260515.f43f2ee · audit B · 175 stars
AGENTS.md@aitesis AGENTS.md file
jongwony/epistemic-protocols · aitesis/AGENTS.md
git:20260927.c7b710c · audit A · 175 stars

Every file in jongwony/epistemic-protocols

Browse by kind, by grade A, or by owner.