analyze-codebase-bugs

SkillFiles & storage

Run a structured bug-focused code review for selected files, folders, or the whole workspace.

Use analyze-codebase-bugs in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add analyze-codebase-bugs and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the analyze-codebase-bugs skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

analyze-codebase-bugsStart free

What this skill tells your AI

The instructions your AI receives, as published by danielsogl/copilot-workflow-demo in .apm/skills/analyze-codebase-bugs/SKILL.md and read by Ahel’s review.

Analyze the codebase for real defects and regression risks.

Input:

  • Treat the skill argument as scope (for example: a feature folder, changed files, or a specific flow).
  • If no scope is provided, analyze the most relevant production code paths in the workspace.

Primary objective:

  • Find concrete bugs, broken behavior, risky assumptions, and missing tests.
  • Prioritize findings by severity.
  • Avoid style-only feedback unless it causes runtime, data, security, accessibility, or maintenance risk.

Required workflow:

  1. Gather context with targeted code search and file reads.
  2. Validate behavior assumptions from code, tests, and configuration.
  3. Report findings first, ordered by severity.
  4. For each finding include:
    • Severity: Critical, High, Medium, or Low
    • Location: exact file path and line link
    • Impact: what breaks and when
    • Evidence: code-level reason
    • Fix suggestion: minimal, safe change
    • Test gap: what test should exist or be updated
  5. After findings, include:
    • Open questions and assumptions
    • Brief change summary only if no critical blockers exist

Output format:

  • Start with section: Findings
  • If there are no findings, state explicitly: No functional bugs found.
  • Then list residual risks and test coverage gaps.
  • Keep the response concise, specific, and actionable.

Quality bar:

  • Do not invent issues without evidence.
  • Do not request broad refactors unless directly needed to fix a defect.
  • Prefer deterministic reproduction hints when possible.

Signals

GitHub stars
39
Forks
6
Last commit
Oct 2026
Advanced
Item type
skill
Key
analyze-codebase-bugs
Source
github.com/danielsogl/copilot-workflow-demo