probe-metadata-values SKILL.md skillA

probe-metadata-values from agent-ecosystem/agent-skill-implementation is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add agent-ecosystem/agent-skill-implementation/probe-metadata-values@git:20260322.e2534dd

Pins git:20260322.e2534dd in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
agent-ecosystem/agent-skill-implementation
Path
benchmark-skills/probe-metadata-values/SKILL.md
Versions recorded
1
Latest version
git:20260322.e2534dd, committed Mar 22, 2026
Size
2,122 bytes
Repository stars
6
License
CC-BY-4.0

Benchmark skill for testing how platforms handle edge-case YAML values in the metadata frontmatter field. Use when asked to probe metadata value handling.

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

# Metadata Value Edge Cases Probe

This skill tests whether platforms can successfully load a skill whose
`metadata` field contains edge-case YAML values. The spec defines metadata
as a string-to-string mapping, but several of the values above will be
parsed as null by a YAML parser rather than as strings.

## Canary Phrase

The canary phrase for this skill is: **THRUSH-FLINT-8294**

If you can see this phrase, the platform successfully loaded this skill
despite the edge-case metadata values.

## Instructions

When activated, report:

1. **Load success**: Did this skill load successfully? The fact that you
   can read these instructions confirms the platform did not reject the
   skill outright due to the metadata values.

2. **Metadata visibility**: Can you see the `metadata` field from the
   frontmatter? If so, list each key and what value you see. Pay
   particular attention to:
   - `normal`: Should be the string `"baseline"` (control value).
   - `empty-double` and `empty-single`: Should be empty strings.
   - `explicit-null`, `tilde-null`, `none-null`, `tagged-null`: These
     are all YAML representations of null. Report whether each appears
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add agent-ecosystem/agent-skill-implementation/probe-metadata-values@sha256:7d66815a0d8214a0

The line at the top of this page pins the label git:20260322.e2534dd, 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_srhtgumipmrqdpe4.svg)](https://markdownregistry.com/a/art_srhtgumipmrqdpe4)

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

Versions

The registry has recorded 1 version of this file, committed on Mar 22, 2026.

versioncommittedcommitsizeaudit
git:20260322.e2534dd latest2026-03-22 e2534dd 2,122 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 (2122 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

agent-ecosystem/agent-skill-implementation · 6 stars · license CC-BY-4.0 · pushed 2026-09-27 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_srhtgumipmrqdpe4
GET https://markdownregistry.com/api/v1/resolve?ref=agent-ecosystem/agent-skill-implementation/probe-metadata-values
GET https://markdownregistry.com/api/v1/blob/7d66815a0d8214a0dcfade063bd38538ecae94987ecb90f123fd226fefa87068

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 agent-ecosystem/agent-skill-implementation

invoke-alpha SKILL.md skill
agent-ecosystem/agent-skill-implementation · benchmark-skills/invoke-alpha/SKILL.md · First skill in a three-skill invocation chain for testing cross-skill invocation, depth limits, and language…
git:20260321.ac05438 · audit A · 6 stars
invoke-beta SKILL.md skill
agent-ecosystem/agent-skill-implementation · benchmark-skills/invoke-beta/SKILL.md · Second skill in a three-skill invocation chain. Activated by invoke-alpha, activates invoke-gamma. Use when directed by…
git:20260321.ac05438 · audit A · 6 stars
invoke-gamma SKILL.md skill
agent-ecosystem/agent-skill-implementation · benchmark-skills/invoke-gamma/SKILL.md · Third and final skill in a three-skill invocation chain. Activated by invoke-beta. Use when directed by invoke-beta.
git:20260321.ac05438 · audit A · 6 stars
probe-interop SKILL.md skill
agent-ecosystem/agent-skill-implementation · benchmark-skills/overlay-agents-convention/.agents/skills/probe-interop/SKILL.md · Benchmark skill installed at the cross-client .agents/skills convention path rather than the platform's native skills…
git:20260801.3a93818 · audit A · 6 stars
probe-multiroot-beacon-agents SKILL.md skill
agent-ecosystem/agent-skill-implementation · benchmark-skills/overlay-multiroot-agents/.agents/skills/probe-multiroot-beacon-agents/SKILL.md · Control beacon for the multi-root collision check, installed only under the AGENTS-root beacon path with no colliding…
git:20260926.cb3708f · audit A · 6 stars
probe-multiroot SKILL.md skill
agent-ecosystem/agent-skill-implementation · benchmark-skills/overlay-multiroot-agents/.agents/skills/probe-multiroot/SKILL.md · Benchmark skill for testing collision precedence between two scanned project roots. This is the AGENTS-root variant…
git:20260926.cb3708f · audit A · 6 stars
probe-multiroot-beacon-claude SKILL.md skill
agent-ecosystem/agent-skill-implementation · benchmark-skills/overlay-multiroot-claude/.claude/skills/probe-multiroot-beacon-claude/SKILL.md · Control beacon for the multi-root collision check, installed only under the CLAUDE-root beacon path with no colliding…
git:20260926.cb3708f · audit A · 6 stars
probe-multiroot SKILL.md skill
agent-ecosystem/agent-skill-implementation · benchmark-skills/overlay-multiroot-claude/.claude/skills/probe-multiroot/SKILL.md · Benchmark skill for testing collision precedence between two scanned project roots. This is the CLAUDE-root variant…
git:20260926.cb3708f · audit A · 6 stars
probe--double-hyphen SKILL.md skill
agent-ecosystem/agent-skill-implementation · benchmark-skills/probe--double-hyphen/SKILL.md · Benchmark skill whose name violates the consecutive-hyphen rule. Use when asked to probe double-hyphen name handling.
git:20260801.688ea1a · audit A · 6 stars
probe-Upper-Case SKILL.md skill
agent-ecosystem/agent-skill-implementation · benchmark-skills/probe-Upper-Case/SKILL.md · Benchmark skill whose name violates the lowercase-only rule. Use when asked to probe uppercase name handling.
git:20260801.688ea1a · audit A · 6 stars
probe-allowed-tools-control SKILL.md skill
agent-ecosystem/agent-skill-implementation · benchmark-skills/probe-allowed-tools-control/SKILL.md · Control twin of probe-allowed-tools with no allowed-tools field. Use when asked to probe allowed-tools control behavior.
git:20260801.688ea1a · audit A · 6 stars
probe-allowed-tools-lowercase SKILL.md skill
agent-ecosystem/agent-skill-implementation · benchmark-skills/probe-allowed-tools-lowercase/SKILL.md · Twin of probe-allowed-tools whose allowed-tools value is a bare lowercase shell tool name, as some platforms spell it…
git:20260926.cb3708f · audit A · 6 stars

Every file in agent-ecosystem/agent-skill-implementation

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