# mel-discipline

Makes the agent walk five stages when writing an analytical deliverable, from scoping to an honest report on what it checked. Useful when a deadline pushes you to cite a source you never opened.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 355 installs · ★ 3
- Author: gasserane
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/gasserane/personal-skills/tree/HEAD/org/mel-discipline/SKILL.md
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/skills/mel-discipline

## What it does

The skill lays out five gates, taken in order. First the agent states the task in one sentence, the decision it feeds, who will read the output, and a verification plan, plus the likeliest way the document could mislead that reader. Then it gathers evidence: supplied materials and its own sources come before any web search, with a search-effort ladder running from one query to ten.

Source handling is strict. Nothing enters the deliverable unless the agent opened it during the session; a citation recalled from memory is dropped or tagged as an unverified URL. Claims about what a source says require opening the document itself, not a news piece about it. At the third gate the agent names the strongest objection to its own recommendation and either answers it or concedes.

Gate four is a checklist over the finished draft: trace every citation, sweep the prose for em dashes, confirm sentence one is the verdict, flag data gaps, recompute the numbers, and check length and register. Each check has to be performed, not reported. Gate five is the honest write-up of what was verified, what was not, and which checks were done by eye. Without a tool to run, some mechanical checks stay manual, and the skill says to admit that.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill mel-discipline -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill mel-discipline -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill mel-discipline -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install gasserane/personal-skills mel-discipline
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill mel-discipline -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/gasserane/personal-skills --path org/mel-discipline
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill mel-discipline -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/gasserane/personal-skills/tree/HEAD/org/mel-discipline/SKILL.md

## When to use it
- ship a brief without pasting a citation from memory
- trace every link before it reaches a director
- name the strongest objection to your own recommendation
- recompute figures from the source instead of trusting them
- keep a working brief inside its word range without losing the verdict

## Example prompts
- Draft the programme evaluation brief, run all five gates and show me the verification report
- Build an indicator set for monitoring; open every source in this session
- Check the draft against the Gate 4 checklist and list what you inspected by eye

## Similar
- [fact-check](https://affpapa.org/en/nevibecode/skills/jwynia-fact-check.md) — skill · 751 installs
- [paper-spine](https://affpapa.org/en/nevibecode/skills/paper-spine.md) — skill · 1200 installs
- [academic-writing](https://affpapa.org/en/nevibecode/skills/poemswe-academic-writing.md) — skill · 1000 installs
- [factchk](https://affpapa.org/en/nevibecode/skills/factchk.md) — skill · 1300 installs
- [paper-review](https://affpapa.org/en/nevibecode/skills/evoscientist-paper-review.md) — skill · 507 installs
- [creative-research](https://affpapa.org/en/nevibecode/skills/creative-research.md) — skill · 487 installs

From the same set: [gasserane/personal-skills](https://affpapa.org/en/nevibecode/by/gasserane/personal-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