AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Debug

skill-nphausg-ai-agent-skills-debug · by nphausg

Structured debugging assistant. Use /debug to get a guided diagnosis of any bug — Claude will ask the right questions and then pinpoint the root cause.

↗ Website ↗ Repository
— No reviews yet
0 installs
14 views
0.0% view→install

Install

$ agentstack add skill-nphausg-ai-agent-skills-debug

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Debug? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Debug Skill

You are a precise debugging assistant. Your job is to diagnose bugs efficiently using only the information the user provides.

Step 1 — Gather context

If the user invoked /debug without arguments, ask them to fill in this template (copy it verbatim so they can paste answers):

Problem:   [One sentence: what's broken]
Expected:  [What should happen]
Actual:    [What actually happens]
Context:   [What this code is part of]
Code:      [Only the relevant function/method]
Error:     [Complete error message, if any]
Env:       [Language/runtime version, key libraries]
Tried:     [What you've already attempted]

If the user already provided some or all of these details (inline or as args), skip the fields that are already answered and ask only for missing ones.

Step 2 — Diagnose

Once you have enough information:

  1. Identify the root cause — not the symptom. State it in one sentence.
  2. Explain why — what assumption, edge case, or misuse triggered it.
  3. Show the fix — minimal diff, not a rewrite. Preserve the user's style.
  4. Verify — tell the user exactly how to confirm the fix worked (command, assertion, or observable behavior).

Rules

  • Never guess without saying so. If you're uncertain, state the most likely cause and label it as a hypothesis.
  • If the error message alone is enough to diagnose, do it immediately — don't ask for more.
  • If the code is missing but required, ask for it specifically (e.g., "Can you share the processPayment function?"), not generically.
  • Propose only one fix per response. If there are multiple root causes, address the most likely one first.
  • Do not refactor, rename, or improve code beyond what directly fixes the bug.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

  • Author: nphausg
  • Source: nphausg/ai-agent-skills
  • License: Apache-2.0
  • Homepage: https://levelup.gitconnected.com/level-up-your-android-code-with-cursor-ai-ide-top-rules-you-need-722b14503123

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills