xpozpublic/xpoz-agent-skills · skills/ai-answer-trace/SKILL.md

ai-answer-trace skillA

ai-answer-trace is agent-read markdown (skill) from xpozpublic/xpoz-agent-skills: Ask Claude, ChatGPT, and Gemini a question and capture the full trace behind the answer (the search queries each engine ran, the pages it retrieved, and the sources it cited, span by span). Use when asked to "trace an AI answer", "see what AI engines cite", "check AI citations", "which sources does ChatGPT/Claude/Gemini use", "why does the AI recommend X", or for any GEO (Generative Engine Optimization) measurement..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add xpozpublic/xpoz-agent-skills/ai-answer-trace@v2026-08-26
Exact content
mdr add xpozpublic/xpoz-agent-skills/ai-answer-trace@sha256:1cb6265e99a24528

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_5te6ur3bi6vbrtvi.svg)](https://markdownregistry.com/a/art_5te6ur3bi6vbrtvi)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v2026-08-26 latest2026-09-09 d18bc4b 24,091 BA view · diff
v2026-08-262026-08-26 236e0c7 24,622 BA view · diff
v2026-08-262026-08-26 df16b1c 24,548 BA view · diff
v2026-08-262026-08-26 f034f52 24,417 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (24091 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

xpozpublic/xpoz-agent-skills · 15 stars · license MIT · pushed 2026-09-09 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_5te6ur3bi6vbrtvi
GET https://markdownregistry.com/api/v1/resolve?ref=xpozpublic/xpoz-agent-skills/ai-answer-trace
GET https://markdownregistry.com/api/v1/blob/1cb6265e99a24528b309bb1d3135cd89ab19ad0f44d7d481ac2297cb4b2a915f