debugging SKILL.md skillA

debugging from calebnewtonusc/chewbacca is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add calebnewtonusc/chewbacca/debugging@git:20260921.84800ca

Pins git:20260921.84800ca in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
calebnewtonusc/chewbacca
Path
skills/debugging/SKILL.md
Versions recorded
2
Latest version
git:20260921.84800ca, committed Sep 21, 2026
First version recorded
Sep 16, 2026
Size
2,972 bytes
Repository stars
9
License
MIT

Find the root cause of a bug instead of guessing at it. Use when the user reports something broken, pastes an error or a stack trace, says this used to work, asks why is this happening, why is this failing, or what is wrong with this. Also use to trace how data flows through a codebase, follow a request end to end, or find where a value is being lost or changed. Also fires on: stack trace, traceback, exception, crash, crashed, segfault, null pointer, undefined, regression, reproduce, bisect…

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

# Debugging

The protocol exists because the failure mode is universal: changing several
things at once, then not knowing which one helped.

## The order, and do not skip

**1. Read the error exactly.** Every word. `undefined` and `null` are different
bugs with different causes. "Cannot read property x of undefined" names the
property and that is usually the whole answer.

**2. Go to the file and line in the trace before doing anything else.** Not a
grep for something similar. The actual frame. If there is no stack trace, get one
before theorizing; a bug report without one is a rumor.

**3. Check the assumption.** Print the variable. Is it the shape you believed? Most
bugs are a value being a different type, a different case, or absent, and are
invisible to reasoning about the code because the code reads correctly.

**4. Search the exact message.** Framework, exact string, year. Someone has hit it.

**5. Check for a breaking change.** Read the migration guide for the version
actually installed, not the version remembered.

**6. `git diff` against the last working state.** The bug lives in the diff. This
step alone solves most "it used to work" reports and it is the one most often
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add calebnewtonusc/chewbacca/debugging@sha256:583d01c7b4f4bec4

The line at the top of this page pins the label git:20260921.84800ca, 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_ejjbvdtmxmczfsbm.svg)](https://markdownregistry.com/a/art_ejjbvdtmxmczfsbm)

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

Versions

The registry has recorded 2 versions of this file, between Sep 16, 2026 and Sep 21, 2026, about one every 4 days.

versioncommittedcommitsizeaudit
git:20260921.84800ca latest2026-09-21 84800ca 2,972 BA view · diff
git:20260916.65678eb2026-09-16 65678eb 2,806 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 (2972 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

calebnewtonusc/chewbacca · 9 stars · license MIT · pushed 2026-10-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ejjbvdtmxmczfsbm
GET https://markdownregistry.com/api/v1/resolve?ref=calebnewtonusc/chewbacca/debugging
GET https://markdownregistry.com/api/v1/blob/583d01c7b4f4bec485e01ec9336bc11c5a1cbdddb096875b589011c2d38f02ad

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 calebnewtonusc/chewbacca

AGENTS.md AGENTS.md file
calebnewtonusc/chewbacca · AGENTS.md
git:20261001.9741b50 · audit A · 9 stars
CLAUDE.md CLAUDE.md file
calebnewtonusc/chewbacca · CLAUDE.md
git:20261001.9741b50 · audit A · 9 stars
CLAUDE.md@hud CLAUDE.md file
calebnewtonusc/chewbacca · hud/CLAUDE.md
git:20260923.73d65e9 · audit A · 9 stars
agent-setup SKILL.md skill
calebnewtonusc/chewbacca · skills/agent-setup/SKILL.md · Finish the parts of this kit's install that need a browser or a permission dialog: screen and accessibility grants…
git:20260904.ee0eb1b · audit A · 9 stars
asa SKILL.md skill
calebnewtonusc/chewbacca · skills/asa/SKILL.md · Answer from the A2A Spring 2026 course, 108 hours of workshops on building a business out of AI agents. Use when the…
git:20260921.3f3d9a0 · audit A · 9 stars
audio-brief SKILL.md skill
calebnewtonusc/chewbacca · skills/audio-brief/SKILL.md · Turn a piece of work into something the user can listen to instead of read. Use when they say they want to hear it…
git:20260923.c7250b6 · audit A · 9 stars
call-coach SKILL.md skill
calebnewtonusc/chewbacca · skills/call-coach/SKILL.md · Debrief a sales or client call from its transcript or recording. Use when the user shares a call transcript, mentions a…
git:20261003.ae04bdc · audit A · 9 stars
clay-navigation SKILL.md skill
calebnewtonusc/chewbacca · skills/clay-navigation/SKILL.md · Navigate Clay directly with the built-in UX engine, configure native enrichment and dynamic per-row copy, and preserve…
git:20260923.251cbb2 · audit A · 9 stars
clone-site SKILL.md skill
calebnewtonusc/chewbacca · skills/clone-site/SKILL.md · Rebuild an existing website faithfully: a replica, a design study, or a page that has to match a reference. Use when…
git:20260927.8453493 · audit A · 9 stars
coursework SKILL.md skill
calebnewtonusc/chewbacca · skills/coursework/SKILL.md · Run the user's semester from a machine-readable ledger built out of their syllabi. Use when they mention a class, an…
git:20260921.762277d · audit A · 9 stars
creative-video SKILL.md skill
calebnewtonusc/chewbacca · skills/creative-video/SKILL.md · Make a short vertical video for Instagram Reels, YouTube Shorts or TikTok, or a YouTube creative, from a brief written…
git:20260927.eec6d7a · audit A · 9 stars
deep-research SKILL.md skill
calebnewtonusc/chewbacca · skills/deep-research/SKILL.md · Research a topic, market, company or claim properly, with sources that can be checked. Use when the user asks you to…
git:20260923.fcc7e97 · audit A · 9 stars

Every file in calebnewtonusc/chewbacca

Other files named debugging

debugging SKILL.md skill
code-yeongyu/oh-my-openagent · packages/shared-skills/skills/debugging/SKILL.md · Runs a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and…
git:20260930.888c46f · audit A · 70,648 stars
debugging SKILL.md skill
notque/vexjoy-agent · skills/process/debugging/SKILL.md · Debugging: guided diagnosis of application bugs, and post-mortem of failed agent sessions.
git:20260919.28d30f9 · audit A · 445 stars
debugging SKILL.md skill
romiluz13/cc10x · plugins/cc10x/skills/debugging/SKILL.md · Use when diagnosing a defect or regression: feedback loop FIRST, root cause before fix, blast radius after fix. Covers…
git:20261007.84fdb74 · audit A · 166 stars
debugging SKILL.md skill
autopus-ai/autopus-adk · .omp/skills/debugging/SKILL.md · 체계적 디버깅 및 버그 수정 스킬
git:20260928.877a6b1 · audit A · 111 stars
debugging SKILL.md skill
insajin/autopus-adk · .omp/skills/debugging/SKILL.md · 체계적 디버깅 및 버그 수정 스킬
git:20260928.877a6b1 · audit A · 110 stars
debugging SKILL.md skill
akillness/jeo-skills · .agent-skills/debugging/SKILL.md · Run a reproduce → isolate → verify debugging workflow for concrete bugs, regressions, flaky failures, and…
v2.1 · audit A · 53 stars
debugging SKILL.md skill
mnemosyne-systems/orangu · contrib/skills/debugging/SKILL.md · Investigate a bug methodically before proposing a fix
git:20260620.6528cab · audit A · 50 stars
debugging SKILL.md skill
iliaal/ai-skills · skills/debugging/SKILL.md · Systematic root-cause debugging with verification. Use for errors, stack traces, broken tests, flaky tests…
git:20260926.7b0520a · audit A · 45 stars

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