Claude-skill-registry debug

Systematic error debugging with analysis, solution discovery, and verification

install

source · Clone the upstream repo

git clone https://github.com/majiayu000/claude-skill-registry

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/debug-skills" ~/.claude/skills/majiayu000-claude-skill-registry-debug-10b554 && rm -rf "$T"

manifest: skills/data/debug-skills/SKILL.md

tags

#debugging #error-handling #code-analysis #automation #testing #problem-solving

source content

<objective> Debug errors systematically through a 5-step workflow: analyze the error, find potential solutions, propose options to the user, implement the fix, and verify it works through multi-layer verification. </objective>

<quick_start> Debug an error (interactive):

/debug login page crashes on submit

Auto mode (fully automatic, use recommended solutions):

/debug -a API returning 500 on POST

What it does:

Analyze: Reproduce error, identify root cause → ask if you have more context
Find Solutions: Research 2-3+ potential fixes with pros/cons
Propose: Present options → you choose which solution
Fix: Implement solution with strategic logging
Verify: Multi-layer verification (Static → Build → Runtime)

Key principle: Tests passing ≠ fix working. Always execute the actual code path.

Note: Only 2 questions in the entire workflow:

After analysis: "Do you have additional info?"
After finding solutions: "Which solution to implement?" </quick_start>

<methodology> <core_principles> **Battle-Tested Principles:**

Reproduce Before Anything Else - If you can't reproduce it, you can't verify the fix
Hypothesis-Driven Analysis - List 3-5 causes ranked by likelihood, test systematically
Multi-Layer Verification - Tests alone give false confidence (20-40% still fail in production) </core_principles>

<verification_pyramid> Verification Pyramid:

        ┌─────────────┐
        │   Manual    │  ← User confirms
        └──────┬──────┘
     ┌─────────┴─────────┐
     │ Runtime Execution │  ← CRITICAL: Real execution
     └─────────┬─────────┘
   ┌───────────┴───────────┐
   │   Automated Checks    │  ← Build, Types, Lint, Tests
   └───────────┬───────────┘
 ┌─────────────┴─────────────┐
 │     Static Analysis       │  ← Syntax, Imports
 └───────────────────────────┘

Key Insight: Tests passing ≠ fix working. ALWAYS execute the actual code path. </verification_pyramid> </methodology>

<parameters> **Flags:**

Flag Name Description

-a

--auto

Auto mode

Full automatic mode - don't ask the user, use recommended solutions

Arguments:

Everything after flags =
```
{error_context}
```
- Description of the error or context about what's failing </parameters>

<state_variables> Persist throughout all steps:

Variable	Type	Description
`{error_context}`	string	User's description of the error
`{auto_mode}`	boolean	Skip confirmations, use recommended options
`{error_analysis}`	object	Detailed analysis from step 1
`{solutions}`	list	Potential solutions found in step 2
`{selected_solution}`	object	User's chosen solution from step 3
`{files_modified}`	list	Files changed during the fix
`{verification_result}`	object	Results from verification step

</state_variables>

<entry_point> Load

steps/step-00-init.md

</entry_point>

<step_files>

Step	File	Description
0	`step-00-init.md`	Parse flags, setup state
1	`step-01-analyze.md`	Reproduce error, form hypotheses, identify root cause
2	`step-02-find-solutions.md`	Research 2-3+ solutions with pros/cons
3	`step-03-propose.md`	Present solutions for user selection
4	`step-04-fix.md`	Implement with strategic logging
5	`step-05-verify.md`	Multi-layer verification (Static → Build → Runtime → User)
</step_files>

<success_criteria>

Error successfully reproduced
Root cause identified through hypothesis testing
2-3+ potential solutions researched with pros/cons
Solution selected (by user or auto mode)
Fix implemented with strategic logging
Static analysis passes (syntax, imports)
Build completes successfully
Tests pass (if tests exist)
Runtime execution verified (actual code path executed)
User confirms fix resolves the original issue
No regressions introduced </success_criteria>