# log-analysis

A skill that reads runtime logs: it picks one evidence packet first, then isolates the earliest failure. Useful when the log is long and you need the one line that matters.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 384 installs · ★ 50
- Author: akillness
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/akillness/jeo-skills/tree/HEAD/.agent-skills/log-analysis/SKILL.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/akillness-log-analysis

## What it does

The skill acts as a packet router, not a troubleshooting encyclopedia. It first normalizes the request into a single shape: packet type, source shape, environment, failure goal, anchor. There are six packets — `app-runtime`, `container-runtime`, `browser-plus-api`, `ci-cascade`, `structured-json`, `security-signal`. Only one is chosen per run, the cheaper one that cuts uncertainty fastest.

Then it narrows the slice: by time window, by request or trace id, by job or pod name. Only after that does it look for the earliest actionable failure, and separately groups the repeated fallout into a signature and blast-radius note. The tools are plain: `Bash`, `Read`, `Grep`, `Glob` — reading and searching files, no code changes.

The boundaries are explicit. Unity and Unreal build logs go to `game-build-log-triage`, observability setup to `monitoring-observability`, hypotheses and fixes to `debugging`, anomaly hunting across many sources to `pattern-detection`. If your job is editing code or building dashboards, this skill is not it. That is worth checking before you install.

## Requirements
- Works with: Unity, Unreal Engine

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add akillness/jeo-skills --skill log-analysis -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/log-analysis/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/log-analysis/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add akillness/jeo-skills --skill log-analysis -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/log-analysis/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add akillness/jeo-skills --skill log-analysis -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/log-analysis/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install akillness/jeo-skills log-analysis
```

2. **Manually: put the files in place**
- File: `.github/skills/log-analysis/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add akillness/jeo-skills --skill log-analysis -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/akillness/jeo-skills --path .agent-skills/log-analysis
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/log-analysis/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add akillness/jeo-skills --skill log-analysis -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/akillness/jeo-skills/tree/HEAD/.agent-skills/log-analysis/SKILL.md

## When to use it
- find the first blocker in a noisy stack trace
- tell a real error from a cascade of secondary failures
- group repeated signatures in a log
- match a browser symptom to the server-side response
- size the blast radius after one failure

## Example prompts
- check the logs, which line matters here
- here are the pod logs, find the first blocker
- this is CI output, where does the cascade start

## Similar
- [dt-obs-log-semantic-mapping](https://affpapa.org/en/nevibecode/skills/dt-obs-log-semantic-mapping.md) — skill · 1400 installs
- [observability-sre-triage](https://affpapa.org/en/nevibecode/skills/observability-sre-triage.md) — skill · 1000 installs
- [test-flakiness](https://affpapa.org/en/nevibecode/skills/test-flakiness.md) — skill · 408 installs
- [investigate](https://affpapa.org/en/nevibecode/skills/launchdarkly-investigate.md) — skill · 674 installs
- [performance-optimization](https://affpapa.org/en/nevibecode/skills/gamedev-skills-performance-optimization.md) — skill · 7400 installs
- [router](https://affpapa.org/en/nevibecode/skills/router.md) — skill · 6600 installs

## Other versions with the same name
- [log-analysis · aj-geddes](https://affpapa.org/en/nevibecode/skills/log-analysis.md) — 657 installs

From the same set: [akillness/jeo-skills](https://affpapa.org/en/nevibecode/by/akillness/jeo-skills.md) — 22 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md