Skip to content
Agentmart
Submit a tool

debugging

Systematic debugging workflow using Approved Logs pattern.

Skill by franciscsimon

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/franciscsimon-debugging

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Systematic debugging workflow using Approved Logs pattern. Adds logging first, reads output, forms hypothesis, then verifies. Use when tracking down bugs.

Use cases: productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/debugging

What's inside

Skill name
debugging
Description
Systematic debugging workflow using Approved Logs pattern. Adds logging first, reads output, forms hypothesis, then verifies. Use when tracking down bugs.
License
MIT
Instructions
44 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Debugging

## Workflow

1. **Reproduce the bug**
   ```bash
   # Run the failing test or trigger the bug
   npm test -- --grep "failing test"
   ```
   If you can't reproduce it, you can't fix it.

2. **Add logging at the boundary**
   Add `console.log` at the entry and exit of the suspected function:
   ```typescript
   console.log("[DEBUG] functionName input:", JSON.stringify(args));
   // ... function body ...
   console.log("[DEBUG] functionName output:", JSON.stringify(result));
   ```

3. **Read the output** — don't guess, read what actually happened

4. **Form a hypothesis** — "The bug is because X returns Y when it should return Z"

5. **Narrow down** — add more logging between entry and exit to find the exact line

6. **Verify the hypothesis** — write a test that fails because of the bug:
   ```typescript
   it("should handle the edge case that caused the bug", () => {
     expect(fn(buggyInput)).toBe(expectedOutput);
   });
   ```

7. **Fix the bug** — make the test pass

8. **Clean up** — remove debug logging, commit fix + test

## Rules

- Say "I don't know" rather than guessing the cause
- Always reproduce before fixing
- Always add a regression test
- Remove all debug logging before committing

From franciscsimon/harness, MIT.

Signals

Stars
1
Forks
1
Open issues
0
Last commit (this folder)
Mar 16, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from franciscsimon

Cite this page

debugging skill. Agent Mart. https://agentmart.dev/skills/franciscsimon-debugging (last updated 2026-10-24)