Systematic Debugging Investigator skill for Claude and Codex
Systematic Debugging Investigator as an AI skill. It asks for Symptom, Error output, How to reproduce and 3 more, then does the rest. Free to install in…
Install it once and Claude or Codex runs it for you. When your request matches, your AI loads the skill, asks for anything it is missing, and works through the template itself. Prefer to fill it in by hand? See the full prompt template.
Download the skill (.zip) · View SKILL.md
When it is used
Use when a bug, flaky test or unexpected behavior needs its root cause found before anyone changes code. Do not use for fixing an obvious typo or reviewing code that has no reported failure. Related topics: coding, technical.
What it will ask you for
- Symptom (longer free text)
- Error output (longer free text)
- How to reproduce (longer free text)
- Recent changes (free text, e.g. "Commits or deploys near when it started")
- Environment (free text, e.g. "Runtime and version and where it fails")
- May modify code to investigate (choose one: Yes, No)
How it works
- Reproduce the failure reliably and record the exact steps, or state clearly that it could not be reproduced.
- Bisect by commit, input, layer or code path, writing down each cut and what it ruled out.
- State ranked hypotheses and test them one variable at a time, each with a check that could disprove it.
- Explain the confirmed chain from root cause to symptom before proposing any change.
- Apply the smallest fix and add a regression test that fails without it and passes with it.
What you get
An evidence log of reproduction, narrowing steps and hypotheses tested, then the root cause chain, the minimal fix and the regression test.
What it watches out for
- Changing several things at once, so a passing run cannot say which change mattered.
- Fixing the symptom, such as a null check, while the upstream cause keeps producing bad data.
- Declaring the bug fixed after one green run of an intermittent failure.
How to install
Claude.ai and the Claude desktop app
- Download the skill .zip.
- Open Settings, then Capabilities, and find Skills.
- Choose Upload skill and select the .zip.
- Ask Claude for help with the task. It loads the skill when your request matches.
Claude Code
- Download the skill .zip.
- Unzip it into ~/.claude/skills/ (or .claude/skills/ inside a project).
- Start a new session. Claude Code loads the skill when your request matches.
Codex
- Download the skill .zip.
- Unzip it into ~/.agents/skills/ (or .agents/skills/ inside a project).
- Codex picks it up on its own. Type $ and the skill name to use it, or just ask for the task.
Cursor
- Download the Cursor rule (.mdc).
- Save it in .cursor/rules/ inside your project.
- Cursor's agent applies the rule when your request matches its description.
AGENTS.md (Codex, Cursor, and other coding agents)
- Copy the AGENTS.md section.
- Paste it into AGENTS.md at the root of your repository, creating the file if needed.
- Coding agents that read AGENTS.md follow it when your request fits.