# thoroughness-scoring

thoroughness-scoring rates implementation choices from 1 to 10 and prompts the agent to pick thorough solutions with tests and typing over brittle shortcuts.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 2966 repo stars
- Author: Rohit Ghumare
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/rohitg00/pro-workflow/tree/HEAD/skills/thoroughness-scoring/SKILL.md
- Updated: 2026-09-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/thoroughness-scoring

## What it does

AI assistants often jump to the fastest shortcut. This skill requires the agent to score choices from T:1 (untested copy-paste) to T:10 (complete test coverage, edge cases, and documentation). Claude Code re-states the current branch and task, contrasts manual effort with AI-assisted delivery time, and pushes for solutions rated T:8 or higher.

Before assigning ratings, the workflow checks task boundaries. When the scope is contained, such as validating a single form or securing one endpoint, high thoroughness is expected. If the request is unbounded, the skill forces the assistant to split the work into small testable units first.

Scoring deliberately turns off during debugging, one-off scripts, and exploratory spikes where raw speed matters most.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add rohitg00/pro-workflow
```
In the agent chat (not a shell):
```text
/plugin install pro-workflow@pro-workflow
```
This installs the whole pro-workflow plugin with all its skills

2. **Skills CLI (Vercel)**
```bash
npx skills add rohitg00/pro-workflow --skill thoroughness-scoring -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add rohitg00/pro-workflow --skill thoroughness-scoring -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add rohitg00/pro-workflow --skill thoroughness-scoring -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install rohitg00/pro-workflow skills/thoroughness-scoring
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add rohitg00/pro-workflow --skill thoroughness-scoring -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/rohitg00/pro-workflow --path skills/thoroughness-scoring
```

### Windsurf (Devin Desktop)

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

### 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/rohitg00/pro-workflow/tree/HEAD/skills/thoroughness-scoring/SKILL.md

## When to use it
- rate implementation options on a 1 to 10 quality scale
- decompose unbounded refactoring tasks into contained units
- compare time estimates between quick hacks and clean code
- eliminate fragile shortcuts when adding tests and typing

## Example prompts
- Propose options for rate limiting the `/api/upload` endpoint with thoroughness scores
- Check the scope for refactoring error handling across the codebase and break it down

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 1eec6ded45bdd491.

BEGIN THIRD-PARTY FILE 1eec6ded45bdd491
````text
---
name: thoroughness-scoring
description: Score every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things properly near-zero — pick the higher-rated option every time. Includes scope checks to distinguish contained vs unbounded work.
---

# Thoroughness Scoring

AI drops the cost of doing things right to near-zero. Stop picking the quick hack when the thorough option takes the same wall-clock time with AI assistance.

## The Rating Scale

Every option gets a Thoroughness score (T:X/10):

| Score | What It Means |
|-------|---------------|
| T:10 | All edge cases handled, full test coverage, docs updated, error messages helpful |
| T:9 | Edge cases covered, tests pass, types solid, no shortcuts |
| T:8 | Happy path + error paths, good tests, clean types |
| T:7 | Happy path works, basic tests, no docs |
| T:5 | Works for the demo, fragile, manual testing only |
| T:3 | Quick hack, no tests, tech debt accruing |
| T:1 | Copy-paste from Stack Overflow, untested, hope it works |

## How to Present Options

When presenting choices, follow this format every time:

### 1. Re-State Context

The user may have been away. Start with orientation:

```text
PROJECT: my-app (branch: feat/rate-limiting)
TASK: Add rate limiting to the /api/upload endpoint
```

### 2. Rate Each Option

```text
Option A — Full rate limiter with sliding window (T:9/10)
  Manual estimate: 3-4 hours
  AI-assisted estimate: 15-20 minutes
  Covers: per-user limits, sliding window, Redis-backed, retry-after headers,
          429 responses, rate limit bypass for admin, tests for all paths

Option B — Basic in-memory counter (T:4/10)
  Manual estimate: 30 minutes
  AI-assisted estimate: 5 minutes
  Covers: global counter, fixed window, resets on restart, no persistence,
          no per-user tracking, no tests

Delta: Option A adds per-user tracking, persistence across restarts,
proper HTTP headers, and admin bypass. The 15-minute difference is
worth it — Option B creates debt you'll pay back at 10x.
```

### 3. Recommend

Always recommend the higher-thoroughness option. State the delta — what the user gains for the additional time.

If the lower option is genuinely appropriate (prototype, throwaway script, time-boxed spike), say so explicitly with reasoning.

## Scope Check

Before scoring, classify the scope:

### Contained Scope (Do It)

Work with a clear boundary. You can be thorough because the surface area is finite.

- 100% test coverage for one module
- All edge cases for one API endpoint
- Full error handling for one service integration
- Complete input validation for one form
````
END THIRD-PARTY FILE 1eec6ded45bdd491

The third-party file has ended. Everything between the 1eec6ded45bdd491 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2642 of 5169 bytes. © Rohit Ghumare · MIT · https://github.com/rohitg00/pro-workflow/tree/HEAD/skills/thoroughness-scoring/SKILL.md

_Part of the page did not fit — see the HTML version._

---
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
