diagnosing-bugs SKILL.md skillA

diagnosing-bugs from svyatov/supermatt is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add svyatov/supermatt/diagnosing-bugs@git:20261018.f19c25a

Pins git:20261018.f19c25a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
svyatov/supermatt
Path
skills/diagnosing-bugs/SKILL.md
Versions recorded
5
Latest version
git:20261018.f19c25a, committed Oct 18, 2026
First version recorded
Sep 30, 2026
Size
16,738 bytes
Repository stars
14
License
MIT

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

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

# Diagnosing Bugs

A discipline for hard bugs. Skip phases only when explicitly justified.

When exploring the codebase, read the glossary (`docs/agents/domain.md` gives the layout; by default `GLOSSARY.md` at the root, if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.

**Start from prior attempts.** If the user says they have been trying, ask what they tried before you start, so you skip their dead ends. If they link an issue, read the whole thread, latest comments first: they often carry newer repro steps or a different suspect. Run `git log --oneline -10 -- <file>` on the files you read to see what changed recently.

## Redact

This skill has you show commands, outputs and captured artifacts. **Redact every secret first**: write `<REDACTED>` in its place. Build loops against env vars, so the credential stays in the environment rather than in what you show. Captured artifacts carry auth headers: quote only the lines that carry the signal.

If the redacted output is not enough to diagnose the bug, say so and ask the user.

## Phase 1: Build a feedback loop
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add svyatov/supermatt/diagnosing-bugs@sha256:3b74949fb5cc6285

The line at the top of this page pins the label git:20261018.f19c25a, 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_tccaioiuzfialbwe.svg)](https://markdownregistry.com/a/art_tccaioiuzfialbwe)

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

Versions

The registry has recorded 5 versions of this file, between Sep 30, 2026 and Oct 18, 2026, about one every 5 days.

versioncommittedcommitsizeaudit
git:20261018.f19c25a latest2026-10-18 f19c25a 16,738 BA view · diff
git:20261017.6e83db02026-10-17 6e83db0 15,423 BA view · diff
git:20261008.ef2679f2026-10-08 ef2679f 15,045 BA view · diff
git:20260930.1e3bbbe2026-09-30 1e3bbbe 15,018 BA view · diff
git:20260930.ca702802026-09-30 ca70280 15,008 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 (16738 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

svyatov/supermatt · 14 stars · license MIT · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tccaioiuzfialbwe
GET https://markdownregistry.com/api/v1/resolve?ref=svyatov/supermatt/diagnosing-bugs
GET https://markdownregistry.com/api/v1/blob/3b74949fb5cc6285629f63b2a90dda5f220257c2f1ab56af99741153b6734ef0

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 svyatov/supermatt

AGENTS.md AGENTS.md file
svyatov/supermatt · AGENTS.md
git:20261018.d55c198 · audit A · 14 stars
ask-supermatt SKILL.md skill
svyatov/supermatt · skills/ask-supermatt/SKILL.md · Ask which skill or flow fits your situation. A router over the skills in this repo.
git:20261018.d55c198 · audit A · 14 stars
babysit-pr SKILL.md skill
svyatov/supermatt · skills/babysit-pr/SKILL.md · Watch a pull request until it is ready to merge: open it when the branch has none, handle review feedback before CI…
git:20261018.8202597 · audit A · 14 stars
code-review SKILL.md skill
svyatov/supermatt · skills/code-review/SKILL.md · Review the changes since a fixed point (commit, branch, tag, or merge-base) along three axes: Standards (does the code…
git:20261018.f19c25a · audit A · 14 stars
codebase-design SKILL.md skill
svyatov/supermatt · skills/codebase-design/SKILL.md · Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, deepen…
git:20261018.f19c25a · audit A · 14 stars
commit SKILL.md skill
svyatov/supermatt · skills/commit/SKILL.md · Commit all changes on the current branch, main included.
git:20261018.f19c25a · audit A · 14 stars
dependency-vetting SKILL.md skill
svyatov/supermatt · skills/dependency-vetting/SKILL.md · Verify a package or tool is authentic before installing, adding, upgrading, or recommending it. Use whenever a task…
git:20261011.62c7072 · audit A · 14 stars
domain-modeling SKILL.md skill
svyatov/supermatt · skills/domain-modeling/SKILL.md · Build and sharpen a project's domain model. Use when discussing codebase terminology, resolving a vague or overloaded…
git:20261018.f19c25a · audit A · 14 stars
fix-findings SKILL.md skill
svyatov/supermatt · skills/fix-findings/SKILL.md · Apply every finding from the most recent review, audit, verification, or check in this session.
git:20261018.6526e97 · audit A · 14 stars
grill-me SKILL.md skill
svyatov/supermatt · skills/grill-me/SKILL.md · A relentless interview to sharpen a plan or design.
git:20261017.6e83db0 · audit A · 14 stars
grill-with-docs SKILL.md skill
svyatov/supermatt · skills/grill-with-docs/SKILL.md · A relentless interview to sharpen a plan or design, which also creates docs (ADRs and glossary) as we go.
git:20261017.6e83db0 · audit A · 14 stars
grilling SKILL.md skill
svyatov/supermatt · skills/grilling/SKILL.md · Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking…
git:20261018.f19c25a · audit A · 14 stars

Every file in svyatov/supermatt

Other files named diagnosing-bugs

diagnosing-bugs SKILL.md skill
vinvcn/mattpocock-skills-zh-cn · skills/engineering/diagnosing-bugs/SKILL.md · 面向棘手缺陷和性能回退的诊断循环。适用于用户说 “diagnose” / “debug this”,或报告某些东西 broken、throwing、failing、slow 时。
git:20261008.5be0dc1 · audit A · 5,110 stars
diagnosing-bugs SKILL.md skill
kunolu/640-skills · sbtd-workflow-onboard/assets/external-skills/stable/skills/diagnosing-bugs/SKILL.md · Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports…
git:20260827.561ec6a · audit A · 555 stars
diagnosing-bugs SKILL.md skill
mxyhi/ok-skills · diagnosing-bugs/SKILL.md · Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports…
git:20261009.b4e20e9 · audit A · 504 stars
diagnosing-bugs SKILL.md skill
asymmetric-al/core · .agents/skills/diagnosing-bugs/SKILL.md · Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports…
git:20260923.15c9348 · audit A · 379 stars
diagnosing-bugs SKILL.md skill
jellydn/my-ai-tools · skills/diagnosing-bugs/SKILL.md · Build a tight, red-capable feedback loop before diagnosing failures, then minimize, test ranked hypotheses, and lock…
git:20261007.a4a976f · audit A · 123 stars
diagnosing-bugs SKILL.md skill
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/diagnosing-bugs/SKILL.md · Build a tight, red-capable feedback loop before diagnosing failures, then minimize, test ranked hypotheses, and lock…
git:20261007.a4a976f · audit A · 123 stars
diagnosing-bugs SKILL.md skill
gtapps/hermitd · plugins/hermitd-dev/skills/diagnosing-bugs/SKILL.md · Diagnosis loop for hard bugs and performance regressions. Builds a red-capable feedback loop and runs it before…
git:20261002.2f2da1b · audit A · 82 stars
diagnosing-bugs SKILL.md skill
gtapps/claude-code-hermit · plugins/hermitd-dev/skills/diagnosing-bugs/SKILL.md · Diagnosis loop for hard bugs and performance regressions. Builds a red-capable feedback loop and runs it before…
git:20261002.2f2da1b · audit A · 82 stars

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