# verifying-before-done

An agent skill that forces a check on the changed code's real surface and a pasted verify output before any completion claim goes out.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 17800 installs · ★ 6
- Author: riekelt
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/riekelt/principal-engineer/tree/HEAD/plugins/principal-engineer/skills/verifying-before-done/SKILL.md
- Updated: 2026-09-11
- HTML: https://affpapa.org/en/nevibecode/skills/verifying-before-done

## What it does

The trigger is the sentence the agent is about to write: shipped, fixed, all green. This skill makes it earn that sentence. Instead of judging by the diff, the agent exercises the path where the change meets its caller — sets the switched flag, sends the handler its request, hits the error branch — and reports what came back.

A clean suite is treated as suspicious, not reassuring. The skill asks whether the test actually ran and whether it can go red at all; a check that never fires yields a confident and wrong “done”. It also keeps three levels apart: present in the repo, running live, and confirmed in the outside system. Evidence from one never stands in for another.

Before wrapping up, the agent sweeps the diff for stray edits, missing docs and acceptance criteria that were only roughly met. Changes on declared critical paths, plus irreversible migrations, need a reviewer who did not write the code. The skill requires `principal-engineering` as background, so that one goes in first. Destructive operations are not run live: with no safe target, verification happens around them and the untested path gets named.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add riekelt/principal-engineer --skill verifying-before-done -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add riekelt/principal-engineer --skill verifying-before-done -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add riekelt/principal-engineer --skill verifying-before-done -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install riekelt/principal-engineer verifying-before-done
```

2. **Manually: put the files in place**
- File: `.github/skills/verifying-before-done/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add riekelt/principal-engineer --skill verifying-before-done -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/riekelt/principal-engineer --path plugins/principal-engineer/skills/verifying-before-done
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add riekelt/principal-engineer --skill verifying-before-done -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/riekelt/principal-engineer/tree/HEAD/plugins/principal-engineer/skills/verifying-before-done/SKILL.md

## When to use it
- prove a fix by running it rather than reading the diff
- catch a test that never actually executed
- separate deployed from merely committed
- clear a red gate left over from earlier work
- strip unrelated edits from the diff before reporting

## Example prompts
- Run the change at its surface and paste the verify command output.
- The suite is green — show that this test ran and that it can fail.
- Report what is implemented, what is deployed and what is confirmed outside.

## Similar
- [setup-matt-pocock-skills](https://affpapa.org/en/nevibecode/skills/setup-matt-pocock-skills.md) — skill · 1052851 installs
- [ask-matt](https://affpapa.org/en/nevibecode/skills/ask-matt.md) — skill · 766587 installs
- [to-tickets](https://affpapa.org/en/nevibecode/skills/to-tickets.md) — skill · 711230 installs
- [writing-plans](https://affpapa.org/en/nevibecode/skills/writing-plans.md) — skill · 282859 installs
- [caveman-review](https://affpapa.org/en/nevibecode/skills/caveman-review.md) — skill · 411800 installs
- [caveman-compress](https://affpapa.org/en/nevibecode/skills/caveman-compress.md) — skill · 411500 installs

From the same set: [riekelt/principal-engineer](https://affpapa.org/en/nevibecode/by/riekelt/principal-engineer.md) — 9 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