# Diagnose

> Debug bugs, failing tests, regressions, flaky behavior, unexpected output, or broken behavior with a reproducible evidence loop.

- **Type:** Skill
- **Install:** `agentstack add skill-jesse-merhi-skills-diagnose`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [jesse-merhi](https://agentstack.voostack.com/s/jesse-merhi)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [jesse-merhi](https://github.com/jesse-merhi)
- **Source:** https://github.com/jesse-merhi/skills/tree/main/skills/diagnose

## Install

```sh
agentstack add skill-jesse-merhi-skills-diagnose
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Diagnose

Do not start with a fix. Start by making the failure observable and repeatable.

## Workflow

1. State the symptom in one sentence.
2. Find or create the fastest deterministic feedback loop.
3. Reproduce the failure before editing production code.
4. Rank hypotheses by evidence, not plausibility.
5. Instrument surgically only where it answers a specific question.
6. Fix the smallest proven cause.
7. Add or update regression coverage when the failure was real behavior.
8. Verify with the original failing command and the affected broader command set.
9. 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](https://github.com/jesse-merhi)
- **Source:** [jesse-merhi/skills](https://github.com/jesse-merhi/skills)
- **License:** MIT

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

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-jesse-merhi-skills-diagnose
- Seller: https://agentstack.voostack.com/s/jesse-merhi
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.