Install
$ agentstack add skill-warren830-super-aidlc-debug ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Debug
The user reports: $ARGUMENTS
The Iron Law
No fixes without root-cause investigation first.
Four Phases
1. Investigate (gather symptoms)
- Reproduce the failure. If you cannot reproduce it, you cannot fix it.
- Read the error message, stack trace, or unexpected output.
- Check recent changes:
git log --oneline -10,git diff. - Check logs, test output, build output.
2. Analyze (trace the cause)
- Start from the symptom, trace backward through code.
- Read the actual code at the error location (not just the error message).
- Check: What data flows into this point? What state is expected vs actual?
- Identify the gap between expected and actual behavior.
3. Hypothesize (test ONE thing)
- Form a single, testable hypothesis: "The bug is caused by X because Y."
- Design a test that would prove or disprove this hypothesis.
- Run the test. If disproved, return to Analyze with new information.
- 3-strike rule: After 3 failed hypotheses, step back and question your assumptions about the system.
4. Implement (fix + prove)
- Write a regression test that fails with the bug present.
- Apply the minimal fix.
- Verify the regression test passes.
- Run the full test suite to check for side effects.
Output
## Debug Report
### Symptom
{What was observed}
### Root Cause
{What actually caused it, with evidence}
### Fix Applied
{What was changed, file:line references}
### Regression Test
{Test that prevents recurrence}
### Investigation Log
{What was tried, including dead ends}
After Debug
Consider running /super-aidlc:compound if the bug was non-trivial -- document the root cause and solution for future reference.
Rules
- No shotgun fixes. Do not change random things hoping it works.
- Evidence before claims. "I think it's fixed" is not acceptable. Run the test.
- Minimal fix. Fix the bug, not the surrounding code. Refactoring is a separate task.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: warren830
- Source: warren830/super-aidlc
- License: MIT
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.