domains / research / academic-paper-writing / academic-paper

academic-paper

Skill card

combined

The two copies are different versions of the same skill. The first (v3.3.1) is a newer, more complex version that adds a detailed routing core, an escape hatch, and a screening boundary, but its text is truncated before the main execution steps. The second (v2.5) is an older version that provides the complete execution flow, trigger conditions, and agent team definitions, but lacks the advanced routing logic. Because the first copy is missing the core procedure and the second is missing the advanced routing, neither is a complete reproduction of the other, and combining them is necessary to capture the full skill.

Repositories

RepositoryPath
Imbad0202/academic-research-skillsacademic-paper/SKILL.md
brycewang-stanford/Auto-Empirical-Research-Skillsskills/24-Imbad0202-academic-research-skills/academic-paper/SKILL.md

Other copies

RoleRepositoryPath
peerImbad0202/academic-research-skillsacademic-paper/SKILL.md
peerbrycewang-stanford/Auto-Empirical-Research-Skillsskills/24-Imbad0202-academic-research-skills/academic-paper/SKILL.md

Combined skill

---
name: academic-paper
description: "12-agent academic paper writing pipeline with advanced routing. Supports 11 modes, 6 paper types, 5 citation formats, bilingual abstracts, and multi-format output. Includes Style Calibration and Writing Quality Check."
metadata:
  version: "3.3.1"
  last_updated: "2026-08-15"
  status: active
---

# Academic Paper — Academic Paper Writing Agent Team

A general-purpose academic paper writing tool — 12-agent pipeline covering all disciplines.

## Routing Discipline

**Step 0 — Escape hatch check:** If the user's first message begins with `[direct-mode]`, strip the prefix and skip to Step 1.

**Step 1 — Explicit clear intent:** If the user invokes a specific skill or uses an unambiguous trigger keyword, route directly.

**Step 2 — Cross-phase materials:** If the user provides artifacts spanning multiple phases without naming a skill, clarify intent by listing candidate workflows.

**Step 3 — Ambiguous intent:** If no artifacts or clear request are provided, clarify per the intent clarification protocol.

## Execution Flow

1. **Configuration interview** — paper type, discipline, citation format, output format.
2. **Literature search** — systematic search strategy, source screening.
3. **Architecture design** — paper structure, outline, word count allocation.
4. **Argumentation construction** — claim-evidence chains, logical flow.
5. **Full-text drafting** — section-by-section draft, register adjustment.
6. **Citation compliance + bilingual abstract** (parallel).
7. **Peer review** — five-dimension scoring, revision suggestions.
8. **Output formatting** — LaTeX/DOCX/PDF/Markdown.

## Agent Team (12 Agents)

1. `intake_agent` — Configuration interview.
2. `literature_strategist_agent` — Search strategy design.
3. `structure_architect_agent` — Paper structure selection.
4. `argument_builder_agent` — Argument construction.
5. `draft_writer_agent` — Section-by-section full draft writing.
6. `citation_compliance_agent` — Citation compliance.
7. `abstract_writer_agent` — Bilingual abstract generation.
8. `peer_reviewer_agent` — Simulated peer review.
9. `revision_coach_agent` — Revision guidance.
10. `format_converter_agent` — Output formatting.
11. `disclosure_agent` — AI disclosure.
12. `rebuttal_auditor_agent` — Rebuttal audit.

## Writing Quality Features

- **Style Calibration:** Learn the author's writing voice from past papers.
- **Writing Quality Check:** Context-sensitive writing diagnostics applied during self-review.