diagnose

Disciplined diagnosis loop for a hard bug or performance regression — reproduce → minimize → hypothesize → instrument → fix the cause → regression-test.

Skill by jhlee0409

IndexedMIT★ 2

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/jhlee0409-diagnose

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.

About

Disciplined diagnosis loop for a hard bug or performance regression — reproduce → minimize → hypothesize → instrument → fix the cause → regression-test. Use when something is broken / throwing / failing or regressed, or when the user says "diagnose this", "debug this", "버그 진단", "왜 안 되지", "디버깅".

Use cases: testing

Reviews

Write a review

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/diagnose

Tools it pre-approves 6

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

Read,
Grep,
Glob,
Bash,
Edit,
Write

What's inside

Skill name: diagnose
Description: Disciplined diagnosis loop for a hard bug or performance regression — reproduce → minimize → hypothesize → instrument → fix the cause → regression-test. Use when something is broken / throwing / failing or regressed, or when the user says "diagnose this", "debug this", "버그 진단", "왜 안 되지", "디버깅".
License: MIT
Allowed tools: Read,, Grep,, Glob,, Bash,, Edit,, Write
Instructions: 26 lines in SKILL.md · view on GitHub

Before installing

Pre-approves some shell commands

Files (1)

SKILL.md

SKILL.md (first lines)

# diagnose

Don't guess-and-patch. Find the real cause, then fix it.

## Loop
1. **Reproduce** — get a reliable, minimal repro. A bug you can't reproduce, you
   can't confirm you fixed. Capture the exact failing command + output.
2. **Minimize** — strip the repro to the smallest input / path that still fails.
   The minimal case usually names the cause.
3. **Hypothesize** — state ONE falsifiable hypothesis ("X is null because Y returns
   early when Z"), not a vibe — a claim a check can disprove.
4. **Instrument** — add the cheapest probe (a log, an assert, a breakpoint) that
   confirms or kills the hypothesis. Let evidence decide, not intuition. Killed →
   back to step 3.
5. **Fix the cause**, not the symptom. A narrow patch that hides the symptom while
   the cause remains is a stopgap — label it as one if you must ship it.
6. **Regression-test** — write a test that fails before the fix and passes after,
   so the bug can't silently return.

## Discipline
- Verify against the REAL system (a real query / real run), never inferred from
  code alone.
- One hypothesis at a time; record what you ruled out.
- "Looks fixed" is not fixed — the regression test (red → green) is the proof.

From jhlee0409/omni-harness-kit, MIT.

Signals

Stars: 2
Forks: 1
Open issues: 0
Last commit (this folder): Jun 26, 2026 (4 months ago)
Last release: Jul 22, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/jhlee0409/omni-harness-kit
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from jhlee0409

Cite this page

diagnose skill. Agent Mart. https://agentmart.dev/skills/jhlee0409-diagnose (last updated 2026-10-24)