Bug Detective

What it does

When your agent uses it

• Debugging an error message or stack trace
• Investigating something that is broken with an unclear cause
• Choosing a debugging strategy based on the type of error

Example prompts

• “Debug this: my script raises a KeyError on the second loop iteration.”
• “Something broke after the upgrade and the logs show a ConnectionError, so investigate.”
• “Why is this test failing? Here is the stack trace.”

Workflow steps

12 steps, taken from the step headings in SKILL.md.

1. 1Understand the Problem
2. 2Analyze Error Type
3. 3Locate the Problem Source
4. 4Form and Verify Hypotheses
5. 5Apply Fix
6. 6Indentation Errors
7. 7Mutable Default Arguments
8. 8Closure Issues in Loops
9. 9Modifying a List While Iterating
10. 10Using is for String Comparison
11. 11Forgetting to Call super().init()
12. 12this Binding Issues

What it can do on your machine

Read from SKILL.md and the folder at commit 9037873. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Python and Shell), which the agent can run.

  Shell commands in SKILL.md call:

  • git
  • bash
  • node
  • python
  • pytest

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bug Detective loads about 2.1k tokens when it runs, and up to ~6.1k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 587 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~83

When it runs · the whole SKILL.md, loaded when a task matches

~2.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~6.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Galaxy-Dawn/claude-scholar at commit 9037873, republished under its MIT licence (© Galaxy-Dawn). 587 words, ~2,128 tokens.

name

bug-detective

description

This skill should be used when the user asks to "debug this", "fix this error", "investigate this bug", "troubleshoot this issue", "find the problem", "something is broken", "this isn't working", "why is this failing", or reports errors/exceptions/bugs. Provides systematic debugging workflow and common error patterns.

version

0.1.0

1. What is the exact error message?
2. Which file and line does the error occur at?
3. How can this issue be reproduced? Provide detailed steps.
4. What was the expected result? What actually happened?
5. What recent changes might have introduced this issue?

Hypothesis: [problem description] causes [error phenomenon]

Verification steps:
1. [verification method 1]
2. [verification method 2]

Expected results:
- If hypothesis is correct: [expected phenomenon]
- If hypothesis is wrong: [expected phenomenon]

# ❌ No spaces allowed in assignment
name = "John"  # Error: tries to run 'name' command

# ✅ Correct assignment
name="John"

# ❌ Missing spaces in conditional test
if[$name -eq 1]; then  # Error

# ✅ Correct
if [ $name -eq 1 ]; then

# ❌ Variables not expanded inside single quotes
echo 'The value is $var'  # Output: The value is $var

# ✅ Use double quotes
echo "The value is $var"  # Output: The value is actual_value

# ❌ Using backticks for command substitution (confusing)
result=`command`

# ✅ Use $()
result=$(command)

# ❌ Unquoted variable, empty value causes errors
rm -rf $dir/*  # If dir is empty, deletes all files in current directory

# ✅ Always quote variables
[ -n "$dir" ] && rm -rf "$dir"/*

# Or use set -u to prevent undefined variables
set -u  # or set -o nounset

# ❌ Pipe creates subshell, outer variable unchanged
cat file.txt | while read line; do
    count=$((count + 1))  # Outer count won't change
done
echo "Total: $count"  # Outputs 0

# ✅ Use process substitution or redirection
while read line; do
    count=$((count + 1))
done < file.txt
echo "Total: $count"  # Correct output

# ❌ Incorrect array access
arr=(1 2 3)
echo $arr[1]  # Outputs 1[1]

# ✅ Correct array access
echo ${arr[1]}  # Outputs 2
echo ${arr[@]}  # Outputs all elements
echo ${#arr[@]} # Outputs array length

# ✅ Use `=` inside POSIX `[` tests and `==` inside Bash `[[ ]]` tests
if [ "$name" = "John" ]; then
if [[ "$name" == "John" ]]; then

# ❌ Using -eq for numeric comparison instead of =
if [ $age = 18 ]; then  # Wrong

# ✅ Use arithmetic operators for numeric comparison
if [ $age -eq 18 ]; then
if (( age == 18 )); then

# ❌ Execution continues after command failure
cd /nonexistent
rm file.txt  # Deletes file.txt in current directory

# ✅ Use set -e to exit on error
set -e  # or set -o errexit
cd /nonexistent  # Script exits here
rm file.txt

# Or check if command succeeded
cd /nonexistent || exit 1

python -m pdb script.py
pytest -x -vv tests/test_target.py

node --inspect-brk app.js
node --trace-warnings app.js

git bisect start
git bisect bad
git bisect good <known-good-commit>

# Run script in debug mode
bash -x script.sh  # Print each command
bash -v script.sh  # Print command source
bash -n script.sh  # Syntax check, no execution

# Enable debugging within a script
set -x  # Enable command tracing
set -v  # Enable verbose mode
set -e  # Exit on error
set -u  # Error on undefined variables
set -o pipefail  # Fail if any command in pipe fails

© Galaxy-Dawn, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (references) in skills/bug-detective of Galaxy-Dawn/claude-scholar.

• SKILL.md
• examples/debugging-workflow.py
• examples/debugging-workflow.sh
• examples/error-handling-patterns.py
• references/common-patterns.md
• references/debugging-tools.md
• references/javascript-errors.md
• references/python-errors.md
• references/shell-errors.md

Open the folder on GitHubat commit 9037873

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in Galaxy-Dawn/claude-scholar, which our catalogue first saw on October 7, 2026.

• brycewang-stanford/Auto-Empirical-Research-Skillsskills/33-Galaxy-Dawn-claude-scholar/skills/bug-detective