# ae-things-review

The ae-things-review Claude Code skill reviews workspace tasks for scope changes, missing progress records, ownership and completion evidence. Run it against a space, an assignee or selected tasks.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 165 installs · ★ 23 repo stars
- Author: ThinkingAIAgenticEngine
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ThinkingAIAgenticEngine/ae-cli/tree/HEAD/skills/ae-things-review/SKILL.md
- Updated: 2026-10-22
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/ae-things-review

## What it does

The skill gathers task details with `ae-cli things` and checks the original goal, scope changes, progress entries, ownership and evidence of completion. It separates recorded results from entries that do not establish progress. Diagnosis is read-only by default; statuses and assignees stay unchanged.

Each report gives a risk category, the goal baseline, dated evidence links, confidence and up to three priority actions. Broad scopes are screened first, with detailed review capped at 20 tasks per batch. Unread files cannot count as accepted deliverables, and incomplete collection limits conclusions to the facts retrieved. Reports identify the timezone for timestamps. Private history is read only when the user has access.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add ThinkingAIAgenticEngine/ae-cli --skill ae-things-review -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add ThinkingAIAgenticEngine/ae-cli --skill ae-things-review -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add ThinkingAIAgenticEngine/ae-cli --skill ae-things-review -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install ThinkingAIAgenticEngine/ae-cli skills/ae-things-review
```

2. **Manually: put the files in place**
- File: `.github/skills/ae-things-review/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add ThinkingAIAgenticEngine/ae-cli --skill ae-things-review -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/ThinkingAIAgenticEngine/ae-cli --path skills/ae-things-review
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add ThinkingAIAgenticEngine/ae-cli --skill ae-things-review -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/ThinkingAIAgenticEngine/ae-cli/tree/HEAD/skills/ae-things-review/SKILL.md

## When to use it
- compare a task's current goal with its original one
- spot scope changes that lack a recorded explanation
- separate meaningful progress from repeated status entries
- check whether ownership and next steps are clear
- compare delivered outputs with acceptance criteria

## Example prompts
- Review tasks in the current space and summarize shared issues.
- Check this assignee's tasks for scope changes and completion evidence.
- Review tasks `id-a` and `id-b`, with supporting facts and priority actions.

## Similar
- [things-mac](https://affpapa.org/en/nevibecode/skills/things-mac.md) — skill · 5200 installs
- [cmux-customization](https://affpapa.org/en/nevibecode/skills/cmux-customization.md) — skill · 7000 installs
- [recoup-platform-build-os](https://affpapa.org/en/nevibecode/skills/recoup-platform-build-os.md) — skill · 5200 installs
- [youmind](https://affpapa.org/en/nevibecode/skills/youmind.md) — skill · 905 installs
- [design-everyday-things](https://affpapa.org/en/nevibecode/skills/design-everyday-things.md) — skill · 6100 installs
- [matter-workspace](https://affpapa.org/en/nevibecode/skills/matter-workspace.md) — skill · 633 installs

From the same set: [thinkingaiagenticengine/ae-cli](https://affpapa.org/en/nevibecode/by/thinkingaiagenticengine/ae-cli.md) — 25 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
