# Rca

> Root cause analysis for bugs, incidents, failed tests, build errors, outages, and unexpected behavior. Use when the user asks for RCA, root cause, why something failed, or asks to diagnose a problem from code, logs, tests, traces, tickets, or terminal output.

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

## Install

```sh
agentstack add skill-kaynetik-skills-rca
```

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

## About

# Root Cause Analysis

## Goal

Find the most likely root cause from available evidence. Stay brief, explicit, and falsifiable.

## Method

1. Identify the context: language, framework, runtime, toolchain, environment, and failure mode.
2. Separate observed facts from assumptions. Do not invent missing logs, code paths, services, timings, or user actions.
3. Trace backward from the symptom to the earliest credible cause.
4. Prefer causes supported by code, logs, tests, config, version changes, or reproducible behavior.
5. If evidence is incomplete, say what is unknown and name the next smallest check.

## Output

Use this format unless the user asks otherwise:

```markdown
Root cause: 

Evidence:
- 
- 

Fix:
- 

Confidence:  because 
```

## Rules

- Be concise. Do not pad with process language.
- Do not speculate beyond the evidence. Label hypotheses as hypotheses.
- Do not recommend broad rewrites unless the evidence points there.
- Do not hide uncertainty.
- When multiple causes are plausible, rank them by evidence and propose one discriminating check.

## Source & license

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

- **Author:** [kaynetik](https://github.com/kaynetik)
- **Source:** [kaynetik/skills](https://github.com/kaynetik/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-kaynetik-skills-rca
- Seller: https://agentstack.voostack.com/s/kaynetik
- 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%.