# session-analyzer

Checks a completed Claude Code session against a target SKILL.md, including agent and hook activity, file changes, and errors. Use it to spot gaps between the expected and observed workflow.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1300 installs · ★ 19
- Author: ai-native-camp
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ai-native-camp/camp-2/tree/HEAD/.claude/skills/session-analyzer/SKILL.md
- Updated: 2026-03-22
- HTML: https://affpapa.org/en/nevibecode/skills/session-analyzer

## What it does

Give the skill a session ID and the path to the `SKILL.md` you want to check. It compares the documented workflow with session evidence, including subagent, hook, and tool activity, operation order, file creation or deletion, and errors. The resulting report includes findings and a PASS or FAIL verdict.

The skill looks for session records under `~/.claude/`. Its scripts, `find-session-files.sh`, `extract-subagent-calls.sh`, and `extract-hook-events.sh`, help locate records and pull out events. You can also provide extra checks. A missing debug log limits the analysis, and the logs it examines belong to Claude Code sessions.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add ai-native-camp/camp-2 --skill session-analyzer -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add ai-native-camp/camp-2 --skill session-analyzer -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add ai-native-camp/camp-2 --skill session-analyzer -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install ai-native-camp/camp-2 session-analyzer
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add ai-native-camp/camp-2 --skill session-analyzer -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/ai-native-camp/camp-2 --path .claude/skills/session-analyzer
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add ai-native-camp/camp-2 --skill session-analyzer -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/ai-native-camp/camp-2/tree/HEAD/.claude/skills/session-analyzer/SKILL.md

## When to use it
- compare a completed run with a target `SKILL.md`
- check whether expected agents and hooks ran
- spot missing calls or steps in the wrong order
- verify expected files were created or removed
- produce a report with a PASS or FAIL verdict

## Example prompts
- Check session `3cc71c9f-d27a-4233-9dbc-c4f07ea6ec5b` against `.claude/skills/specify/SKILL.md`.
- Compare the hook and subagent activity in this session with `.claude/skills/review/SKILL.md`.
- Check whether the expected file was created, and add this criterion: the reviewer must run before the plan is saved.

## Similar
- [improve-codebase-architecture](https://affpapa.org/en/nevibecode/skills/improve-codebase-architecture.md) — skill · 1163035 installs
- [design-taste-frontend](https://affpapa.org/en/nevibecode/skills/design-taste-frontend.md) — skill · 678700 installs
- [tdd](https://affpapa.org/en/nevibecode/skills/tdd.md) — skill · 1141062 installs
- [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs
- [agent-browser](https://affpapa.org/en/nevibecode/skills/vercel-labs-agent-browser.md) — skill · 1200000 installs
- [prototype](https://affpapa.org/en/nevibecode/skills/prototype.md) — skill · 986201 installs

From the same set: [ai-native-camp/camp-2](https://affpapa.org/en/nevibecode/by/ai-native-camp/camp-2.md) — 2 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