Academic Research Skills

1---
2title: Academic Research Skills
3description: AI-augmented academic research pipeline with integrity verification
4version: 3.14.0
5license: CC BY-NC 4.0
6---
7 
8# Academic Research Skills for GitHub Copilot
9 
10AI-augmented research pipeline for academic writing, literature review, and peer review.
11 
12**Core principle:** AI is your copilot, not the pilot. Humans focus on substantive decisions; AI handles grunt work (references, formatting, verification).
13 
14## Quick Start
15 
16Try `/ars-plan` — describe your paper, get Socratic structure guidance.
17 
18**Key commands:** `/ars-lit-review`, `/ars-outline`, `/ars-full`, `/ars-reviewer`, `/ars-citation-check`
19 
20## Setup & Installation
21 
22→ **[SETUP.md](../docs/SETUP.md)** for plugin, local symlink, API keys, and optional tools
23 
24## Architecture & Components
25 
26- **Deep Research** — 13-agent team, PRISMA support, intent detection
27- **Paper Writing** — 12-agent pipeline, style calibration, citation verification
28- **Peer Review** — 7-agent multi-perspective review, quality rubrics
29- **Pipeline** — 10-stage orchestration, claim verification, material passports
30 
31→ **[ARCHITECTURE.md](../docs/ARCHITECTURE.md)** for full flow diagrams and dependency graph
32 
33## Integrity & Safety
34 
35Addresses AI research failure modes (Kong et al. 2026, arXiv:2605.18661):
36- 7-mode blocking checklist for common AI failures
37- Claim-level audits with locator anchors
38- Trust-chain frontmatter for provenance
39- FNR/FPR calibration on custom measures
40 
41⚠️ **Permission modes:** for unattended pipeline runs, Auto mode is the recommended setting (a server-side classifier still gates dangerous escalations). `--dangerously-skip-permissions` removes all safety checks and is only appropriate for isolated, no-internet sandboxes. See [PERFORMANCE.md](../docs/PERFORMANCE.md#recommended-claude-code-settings) for full context before changing modes.
42 
43## Contributing
44 
45→ **[CONTRIBUTING.md](../CONTRIBUTING.md)** for PR workflow, acceptance criteria, development guidelines
46 
47## Docs
48 
49| Topic | Link |
50|-------|------|
51| **Setup & Installation** | [SETUP.md](../docs/SETUP.md) |
52| **Architecture** | [ARCHITECTURE.md](../docs/ARCHITECTURE.md) |
53| **Performance & Costs** | [PERFORMANCE.md](../docs/PERFORMANCE.md) |
54| **Design Philosophy** | [POSITIONING.md](../POSITIONING.md) |
55| **Contributing** | [CONTRIBUTING.md](../CONTRIBUTING.md) |
56| **Citation** | [CITATION.cff](../CITATION.cff) |
57 
58## License
59 
60CC BY-NC 4.0 (non-commercial use) • DOI: [10.5281/zenodo.20696614](https://doi.org/10.5281/zenodo.20696614)
61 
62---
63 
64**This tool helps you write *better*, not helps you hide that you used AI. Integrity is non-negotiable.**
65