Scrum-inspired paper review, revision, and R&R workflow. Handles docx/tex/md/PDF in English or Chinese. Auto-detects manuscript stage, estimates sprint count, runs multi-lens review (Contribution/Rigor/Writing/Editor), generates prioritized revision backlog, exports MD/DOCX/PDF/HTML reports. Use when asked to review a paper, revise based on reviewer comments, handle R&R, respond to peer review, plan paper revision sprints, or when user types /ps or /papersprint.
72
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Scrum-inspired paper agent for review, revision, and R&R.
| # | Principle | Description |
|---|---|---|
| 1 | Progressive inquiry | Only ask for missing information, never repeat known facts |
| 2 | Range estimates | Always give ranges, never false precision |
| 3 | Actionable critique | Every critique must point to a specific location |
| 4 | Human finalization | Never auto-submit — human verification always required |
| 5 | Explicit focus shifts | Always announce when switching focus |
INTAKE → PLANNING → REVIEW → AMENDMENT
↓
BACKLOG
↓
SPRINT REVIEW & RETRO
↓
NEXT SPRINT / GATE→ Full details: references/quick_reference.md
This skill accepts: Paper review, revision, and R&R workflows in Chinese or English.
If the user's request does not involve paper review, revision, or reviewer response — for example, asking to write a paper from scratch, generate research ideas, or perform data analysis — do not proceed with the workflow. Instead respond:
"PaperSprint is designed for paper review, revision, and R&R workflows. Your request appears to be outside this scope. For paper writing, please use manuscript drafting tools. For research ideas, please use idea generation tools. For data analysis, please use analysis tools."
Disclaimer (Required): All review suggestions are for reference only. Consult domain experts before making final decisions.
Load each reference file only when its trigger condition is met.
File: references/intake.md
When to load:
/ps intakeContents:
File: detection/stage_detector.md
When to load:
Contents:
File: references/review.md
When to load:
/ps reviewContents:
File: references/backlog.md
When to load:
/ps backlogContents:
File: references/gates.md
When to load:
/ps gate checkContents:
→ Full details: references/sprint_estimation.md
File: references/export.md
When to load:
/ps exportContents:
File: detection/quality_checker.md
When to load:
Contents:
| Template | When to load |
|---|---|
| templates/sprint_brief.md | Generating a sprint brief |
| templates/process_log.md | Recording a process log |
| templates/backlog_item.md | Creating a backlog item |
| templates/review_memo.md | Writing a review memo |
| templates/amendment_summary.md | Generating an amendment summary |
| templates/sprint_review.md | Conducting a sprint review |
| templates/retrospective.md | Conducting a sprint retrospective |
| templates/human_finalization.md | Generating human finalization checklist |
| templates/export_report.md | Exporting a full report |
| English | 中文 |
|---|---|
| Backlog | 待办事项 |
| Sprint | 冲刺 |
| Intake | 接收 |
| Amendment | 修订 |
| Gate | 门禁 |
| Review Lens | 评审视角 |
| Contribution | 贡献 |
| Rigor | 严谨性 |
| Camera-ready | 定稿 |
→ Full details: references/decision_flowchart.md
Explicitly decline or redirect in these situations:
Disclaimer: This tool provides review suggestions only. Consult domain experts before making final decisions.
PaperSprint v2.2
f5ef65b
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.