testing-the-gaia-agent SKILL.md skillB

testing-the-gaia-agent from amd/gaia is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add amd/gaia/testing-the-gaia-agent@git:20261015.61a3033

Pins git:20261015.61a3033 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
amd/gaia
Path
.claude/skills/testing-the-gaia-agent/SKILL.md
Versions recorded
6
Latest version
git:20261015.61a3033, committed Oct 15, 2026
First version recorded
Sep 12, 2026
Size
26,152 bytes
Repository stars
1,593
License
MIT

Test the flagship GAIA agent end-to-end through the Go TUI — launch it, drive it without colliding with other agents, run the capability ladder, verify skills really call their tools instead of fabricating, and check the permission gate. Use when validating the gaia agent, its skills, or the TUI chat view.

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

# Testing the flagship GAIA agent through the TUI

Companion to `driving-the-tui` (which covers the control API mechanics). This one
covers **what to test and how to know it actually worked** — written from a full
session of driving the live agent, including every trap that cost an hour.

## The ladder tests capabilities. Users have conversations.

Read this before trusting a green ladder. Every rung below is a **self-contained
prompt** — it names its repo, its numbers, its subject. So the ladder ran green
for a whole day while the TUI agent had **no conversation history at all**: every
turn reached the model as system prompt + current question, nothing else. The
bug surfaced the moment a real user typed a follow-up:

> **triage amd/gaia** → three issues listed
> **"cool, can you print issue 2975?"** → *"I need to know which repository it belongs to"*

Three things hid it, and all three are worth knowing:

1. **L3 looks like proof of continuity and is not.** "What is my favourite
   colour?" passes across turns via the persistent *memory store*, a different
   mechanism entirely. Its green tick actively masked the gap.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add amd/gaia/testing-the-gaia-agent@sha256:fc16587ba555baac

The line at the top of this page pins the label git:20261015.61a3033, 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_iwux3dcztvecml2b.svg)](https://markdownregistry.com/a/art_iwux3dcztvecml2b)

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

Versions

The registry has recorded 6 versions of this file, between Sep 12, 2026 and Oct 15, 2026, about one every 7 days.

versioncommittedcommitsizeaudit
git:20261015.61a3033 latest2026-10-15 61a3033 26,152 BB view · diff
git:20261006.5d9308c2026-10-06 5d9308c 25,702 BB view · diff
git:20261005.56446952026-10-05 5644695 25,612 BB view · diff
git:20261004.fb70c192026-10-04 fb70c19 25,606 BB view · diff
git:20260912.a07b87e2026-09-12 a07b87e 24,295 BB view · diff
git:20260912.40410792026-09-12 4041079 22,792 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No link to a raw IP address (matched: http://127.0.0.1:13305)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (26152 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 script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

amd/gaia · 1,593 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_iwux3dcztvecml2b
GET https://markdownregistry.com/api/v1/resolve?ref=amd/gaia/testing-the-gaia-agent
GET https://markdownregistry.com/api/v1/blob/fc16587ba555baac8d9e0657719cc8cb4af74d89d30b0ad9812ed0d9686f0ae3

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 amd/gaia

adding-eval-scorecard SKILL.md skill
amd/gaia · .claude/skills/adding-eval-scorecard/SKILL.md · Adopt the per-agent eval scorecard for a GAIA hub agent: write the harness→payload adapter, run the eval to produce a…
git:20261019.46c2736 · audit A · 1,593 stars
agent-hub-release SKILL.md skill
amd/gaia · .claude/skills/agent-hub-release/SKILL.md · Cut or wire the frozen-binary + npm release of an agent GAIA itself ships (the email/flagship CI pipeline: freeze ->…
git:20261019.c4b5352 · audit A · 1,593 stars
analyzing-claude-sessions SKILL.md skill
amd/gaia · .claude/skills/analyzing-claude-sessions/SKILL.md · Analyze your own local Claude Code session transcripts to find what you actually use the agent for, how effective it…
git:20260922.b869e9a · audit A · 1,593 stars
benchmarking-the-agent SKILL.md skill
amd/gaia · .claude/skills/benchmarking-the-agent/SKILL.md · Measure the flagship GAIA agent against Claude Code and across models — quality, truthfulness, steps, tokens, time and…
git:20260928.3afaf2e · audit A · 1,593 stars
driving-the-tui SKILL.md skill
amd/gaia · .claude/skills/driving-the-tui/SKILL.md · Use when testing or validating the GAIA TUI (tui/) by actually running it — driving screens, clicking and scrolling…
git:20261012.2435ea7 · audit B · 1,593 stars
gaia-build-agent SKILL.md skill
amd/gaia · .claude/skills/gaia-build-agent/SKILL.md · Build a new GAIA agent with the SDK end-to-end: scaffold the package, write the Agent subclass, register @tool…
git:20261019.46c2736 · audit A · 1,593 stars
gaia-executive-presentation SKILL.md skill
amd/gaia · .claude/skills/gaia-executive-presentation/SKILL.md · Generate an EXECUTIVE slide presentation (leadership / decision-maker audience) from a source document as…
git:20260926.670aa14 · audit A · 1,593 stars
gaia-release SKILL.md skill
amd/gaia · .claude/skills/gaia-release/SKILL.md · Cut a GAIA release end-to-end: draft notes, open release PR, run pre-tag verification, push the tag, monitor the…
git:20261019.c5cfa83 · audit A · 1,593 stars
gaia-technical-presentation SKILL.md skill
amd/gaia · .claude/skills/gaia-technical-presentation/SKILL.md · Generate a TECHNICAL slide presentation (engineering audience) from a source document as self-contained HTML that…
git:20260926.670aa14 · audit A · 1,593 stars
gaia-testing SKILL.md skill
amd/gaia · .claude/skills/gaia-testing/SKILL.md · GAIA's multi-tier regression harness — runs unit, integration, and real-world (on-machine) tiers and brings back…
git:20261016.1b15173 · audit A · 1,593 stars
gaia-tui-manual SKILL.md skill
amd/gaia · .claude/skills/gaia-tui-manual/SKILL.md · The GAIA terminal UI (gaia-tui) — how to build it, launch it with a real pty, drive it through the loopback control…
git:20261018.65415ee · audit A · 1,593 stars
github-issue-response SKILL.md skill
amd/gaia · .claude/skills/github-issue-response/SKILL.md · Respond to a GitHub issue, PR comment, discussion reply, or review on amd/gaia. Use when writing any reply that will be…
git:20261018.65415ee · audit A · 1,593 stars

Every file in amd/gaia

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