# Coarse Review

> Run the full Coarse peer review pipeline on a PDF. Orchestrates all sub-skills in sequence. Use when asked to review a paper.

- **Type:** Skill
- **Install:** `agentstack add skill-felipe-so-coarse-ink-claude-code-coarse-review`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Felipe-SO](https://agentstack.voostack.com/s/felipe-so)
- **Installs:** 0
- **Category:** [Content & Media](https://agentstack.voostack.com/c/content-and-media)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Felipe-SO](https://github.com/Felipe-SO)
- **Source:** https://github.com/Felipe-SO/coarse-ink-claude-code/tree/main/.claude/skills/coarse-review

## Install

```sh
agentstack add skill-felipe-so-coarse-ink-claude-code-coarse-review
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# /coarse-review — Full Review Pipeline

**Usage**: `/coarse-review papers/paper.pdf`

Runs the complete Coarse review pipeline by invoking each sub-skill in sequence.
All paths are relative to the workspace root `d:/Dropbox/Research/Coarse Reviewer/`.

The argument (`$ARGUMENTS`) is the path to the paper PDF.

Derive the **slug** from the filename: lowercase, spaces→hyphens, no extension.
e.g. `papers/my-paper.pdf` → slug = `my-paper`

Pass the PDF path only to `coarse-extract`. Pass the slug to all subsequent
sub-skills — they work entirely from cache files and never need the PDF again.

---

## Pipeline

Run each sub-skill in order. Wait for each to complete before starting the next.
If a sub-skill fails, stop and report the error — do not skip ahead.

| Step | Sub-skill | What it does | Output |
|------|-----------|--------------|--------|
| 1–2 | `/coarse-extract $ARGUMENTS` | PDF → markdown, parse sections | `_extracted.md`, `_sections.json` |
| 3–6 | `/coarse-classify ` | Classify, calibrate, contributions, literature | `_classification.json`, `_calibration.json`, `_contribution.json`, `_literature.txt` |
| 7–8 | `/coarse-overview ` | Macro overview + assumption check + completeness | `_overview.json` |
| 9–11 | `/coarse-section-review ` | Per-section review + adversarial proof verify + cross-section + compile | `_comments_draft.json` |
| 12–13 | `/coarse-editorial ` | Editorial filter + quote verify (Python) | `_comments_verified.json` |
| 14 | `/coarse-write ` | Write final review markdown | `reviews/-review.md` |

---

## Cache location

All intermediate files are written to `.coarse_cache/_*.json` and
`.coarse_cache/_extracted.md`. If a run is interrupted, you can resume
from any sub-skill without re-running earlier steps — the cache files persist.

---

## Notes

- Each sub-skill re-reads its dependencies from cache at startup, so context
  compression between steps is safe.
- To re-run only part of the pipeline (e.g. redo the editorial filter after
  adjusting a comment), invoke the relevant sub-skill directly.
- See `reference_review.md` for the gold-standard output format.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Felipe-SO](https://github.com/Felipe-SO)
- **Source:** [Felipe-SO/coarse-ink-claude-code](https://github.com/Felipe-SO/coarse-ink-claude-code)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-felipe-so-coarse-ink-claude-code-coarse-review
- Seller: https://agentstack.voostack.com/s/felipe-so
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.