Home / flowerf19 / agents-skills · GitHub

debug-investigator SKILL.md skillA

debug-investigator from flowerf19/agents-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add flowerf19/agents-skills/debug-investigator@git:20261031.8028dfa

Pins git:20261031.8028dfa in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: flowerf19/agents-skills
Path: debug-investigator/SKILL.md
Versions recorded: 6
Latest version: git:20261031.8028dfa, committed Oct 31, 2026
First version recorded: Jul 16, 2026
Size: 2,833 bytes
Repository stars: 3
License: MIT

Find why a failure happens before proposing a fix. Use when the user asks to diagnose or debug a bug, failing test, build error, slow behavior, or unexpected result, or when an approved fix needs investigation. Diagnosis alone does not give permission to edit code.

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

# Debug investigator

Explain what failed, why it failed, and where the smallest fix belongs.

Keep the repository unchanged for diagnosis-only requests. Use existing tests, read-only inspection, or isolated temporary checks. Do not change production data or expose secrets. Add a tracked reproduction test only when the task allows it. An approved end-to-end fix can continue to coding after the cause is confirmed.

## Step 1: Capture the failure

1. Record expected and actual behavior, inputs, errors, and environment.
2. Try the smallest reproduction. State whether the failure was reproduced.
3. Check current behavior against accepted requirements. Do not assume a mocked flow or old document describes the real failure.

## Step 2: Trace the cause

1. Follow data and calls through the affected modules to the returned result.
2. Find the first point where behavior differs from the requirement.
3. Compare recent changes and a working flow when useful. Do not copy unrelated business rules from it.
4. For async or stored state, inspect relevant event order, cancellation, concurrent updates, restart, and logs. A success response alone does not prove the operation finished.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add flowerf19/agents-skills/debug-investigator@sha256:1d15ed2b748caeb9

The line at the top of this page pins the label git:20261031.8028dfa, 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](https://markdownregistry.com/badge/art_cljlqy6wxdatkcub.svg)](https://markdownregistry.com/a/art_cljlqy6wxdatkcub)

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

Versions

The registry has recorded 6 versions of this file, between Jul 16, 2026 and Oct 31, 2026, about one every 21 days.

version	committed	commit	size	audit
git:20261031.8028dfa latest	2026-10-31	8028dfa	2,833 B	A	view · diff
git:20261018.9e4ec92	2026-10-18	9e4ec92	2,703 B	A	view · diff
git:20261001.5256e9e	2026-10-01	5256e9e	3,035 B	A	view · diff
git:20261001.1ab73e9	2026-10-01	1ab73e9	3,441 B	A	view · diff
git:20261001.f1e72be	2026-10-01	f1e72be	2,840 B	A	view · diff
git:20260716.c3bf1e2	2026-07-16	c3bf1e2	1,959 B	A	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 (2833 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

flowerf19/agents-skills · 3 stars · license MIT · pushed 2026-10-31 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_cljlqy6wxdatkcub
GET https://markdownregistry.com/api/v1/resolve?ref=flowerf19/agents-skills/debug-investigator
GET https://markdownregistry.com/api/v1/blob/1d15ed2b748caeb91b87a5054d596d82df8f53429c59425ca5b345778fc24fa3

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.