Diagnose
Debug bugs, failing tests, regressions, flaky behavior, unexpected output, or broken behavior with a reproducible evidence loop.
Install
$ agentstack add skill-jesse-merhi-skills-diagnose ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-jesse-merhi-skills-diagnose) 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
Diagnose
Do not start with a fix. Start by making the failure observable and repeatable.
Workflow
- State the symptom in one sentence.
- Find or create the fastest deterministic feedback loop.
- Reproduce the failure before editing production code.
- Rank hypotheses by evidence, not plausibility.
- Instrument surgically only where it answers a specific question.
- Fix the smallest proven cause.
- Add or update regression coverage when the failure was real behavior.
- Verify with the original failing command and the affected broader command set.
- Report using [reporting.md](references/reporting.md).
Required Discipline
- If you cannot reproduce the failure, say what you tried and narrow the next
probe.
- For each hypothesis, name the observation that would confirm or falsify it.
- Remove temporary instrumentation before completion.
- Do not patch around an unknown cause.
- If a proposed fix is speculative, label it as such and keep digging.
Context Pointers
- Use [feedback-loop.md](references/feedback-loop.md) for reproduction and
instrumentation options.
- Use [guardrails.md](references/guardrails.md) for what not to claim or change
without evidence.
- Use [reporting.md](references/reporting.md) for final output shape.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: jesse-merhi
- Source: jesse-merhi/skills
- 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.