# analysis

Turns a contested situation into a structured brief: the hidden bet, the real disagreement, who pays. Built for news, conflicts and decisions that need a judgment, not a summary.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1400 installs · ★ 2
- Author: microchipgnu
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/microchipgnu/blindspot.news/tree/HEAD/skills/analysis/SKILL.md
- Updated: 2026-05-13
- HTML: https://affpapa.org/en/nevibecode/skills/analysis

## What it does

The `analysis` skill produces judgment briefs instead of summaries. Output sections cover what happened, a one-sentence bottom line, load-bearing assumptions, the actual fork where both sides seem right, what nobody can say out loud, who gets hurt, plausible scenarios and what would change the conclusion. The author forbids naming philosophers or labelling frameworks, so the thinking stands on its own.

The workflow runs in three steps. First find the crux: the thing that, once clear, makes the whole situation make sense. Then pressure-test through angles such as who controls the frame, what motive is disguised, who bears invisible costs and who hides behind having no choice. Those angles never surface in the output. The brief itself comes last.

Aim for 600-900 words, and cut any section that only repeats what the reader already knows. If the unsaid observation is not there, skip it rather than invent one. The skill installs into Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode, landing as a file in the platform's skills directory, for example `~/.claude/skills/analysis/SKILL.md`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add microchipgnu/blindspot.news --skill analysis -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add microchipgnu/blindspot.news --skill analysis -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add microchipgnu/blindspot.news --skill analysis -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install microchipgnu/blindspot.news analysis
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add microchipgnu/blindspot.news --skill analysis -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/microchipgnu/blindspot.news --path skills/analysis
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add microchipgnu/blindspot.news --skill analysis -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/microchipgnu/blindspot.news/tree/HEAD/skills/analysis/SKILL.md

## When to use it
- read a news story and see what the framing hides
- stress-test a strategy before committing to it
- work out why a conflict is stuck
- spot the assumption the whole story rests on
- name who loses under each outcome

## Example prompts
- Run the analysis skill on this situation — what is really going on and what is everyone missing?
- Stress-test my plan with analysis: where does it break?
- Who pays for this decision, and through what mechanism?

## Similar
- [critical-thinking-logical-reasoning](https://affpapa.org/en/nevibecode/skills/critical-thinking-logical-reasoning.md) — skill · 2400 installs
- [swot-analysis](https://affpapa.org/en/nevibecode/skills/swot-analysis.md) — skill · 3000 installs
- [measure-survey-analysis](https://affpapa.org/en/nevibecode/skills/measure-survey-analysis.md) — skill · 634 installs
- [tracelens-analysis-orchestrator](https://affpapa.org/en/nevibecode/skills/tracelens-analysis-orchestrator.md) — skill · 877 installs
- [data-analysis](https://affpapa.org/en/nevibecode/skills/data-analysis.md) — skill · 7900 installs
- [stock-analysis](https://affpapa.org/en/nevibecode/skills/claude-office-skills-stock-analysis.md) — skill · 6900 installs

---
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