agentleFS
TobiasBlaskTobiasBlask/open-paper-machine/skills/coauthor-engine/SKILL.md

coauthor-engine

Skill18 starsChanged 7 months agoMITView on GitHub

Activate when the user needs to manage multi-author collaboration on a paper. Tracks author contributions using the CRediT taxonomy, manages responsibility assignments, documents the human-AI division of labor, and produces an author contribution statement ready for submission.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before submission (submission-engine may trigger this)

    line 32
  2. Distinctive:

    When documenting AI involvement in the research process

    line 33
  3. Distinctive:

    Note: If AI is listed, typically in acknowledgments, not as author (venue-dependent)

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Orchestration Log: When this skill is activated, append a log entry to outputs/orchestration_log.md:

### Skill Activation: Co-Author Engine
**Timestamp:** [current date/time]
**Actor:** AI Agent (coauthor-engine)
**Input:** [N] authors, task: [contribution tracking / responsibility assignment / CRediT statement]
**Output:** author_contributions.md saved

Co-Author Engine

Core Principle

Modern academic publishing increasingly requires transparent documentation of who did what. The CRediT (Contributor Roles Taxonomy) system standardizes this. For AI-assisted papers, documenting the human-AI division of labor is not optional — it's becoming a requirement at major venues.

When to Activate

  • User says "author contributions", "CRediT statement", "who did what"
  • User says "add co-author", "assign responsibilities", "contribution tracking"
  • Before submission (submission-engine may trigger this)
  • When documenting AI involvement in the research process

Step 1: DEFINE Author Roster

Author Information Template

## Authors

| # | Name | Affiliation | Role | ORCID | Corresponding |
|---|------|-------------|------|-------|--------------|
| 1 | [Name] | [University/Org] | [Senior/Junior/PI] | [ORCID] | [Yes/No] |
| 2 | [Name] | [University/Org] | [Senior/Junior] | [ORCID] | [No] |
| 3 | AI Agent (Claude) | Anthropic | AI Assistant | N/A | No |

Author Order Conventions

  • IS/Business conventions: First author did most work, last author is senior/PI
  • CS conventions: First author did most work, alphabetical otherwise or by contribution
  • Note: If AI is listed, typically in acknowledgments, not as author (venue-dependent)

Step 2: ASSIGN CRediT Roles

CRediT Taxonomy (14 Roles)

For each author (including AI), indicate contribution level:

#CRediT RoleDefinitionAuthor 1Author 2AI Agent
1ConceptualizationIdeas, formulation of research goalsLeadSupporting—
2Data curationManaging, annotating, maintaining dataLead—Supporting
3Formal analysisStatistical, mathematical, computational analysisSupporting—Lead
4Funding acquisitionObtaining financial support—Lead—
5InvestigationConducting the research, data collectionLeadSupportingSupporting
6MethodologyDevelopment or design of methodologyLeadSupportingSupporting
7Project administrationManaging and coordinating the projectLead——
8ResourcesProvision of study materials, tools, computing—Lead—
9SoftwareProgramming, implementation, code——Lead
10SupervisionOversight and leadership responsibility—Lead—
11ValidationVerification and replication of resultsLeadSupportingSupporting
12VisualizationCreating figures, diagrams, plotsSupporting—Lead
13Writing — original draftCreating the initial manuscriptSupporting—Lead
14Writing — review & editingCritical review, commentary, revisionLeadLeadSupporting

Levels: Lead / Supporting / — (not involved)

AI-Specific Contribution Documentation

For the AI agent, document specifically:

## AI Contribution Statement

This paper was produced with the assistance of an AI writing system (Claude,
via the Open Academic Paper Machine). The AI system contributed to:

- **Literature search and synthesis:** Automated multi-database search, deduplication,
  and initial thematic clustering of [N] papers
- **First draft generation:** Initial drafts of all sections following academic
  writing templates, subsequently revised by human authors
- **Figure generation:** [N] figures generated via AI (PaperBanana)
- **Citation verification:** Automated verification of [N] citations against source abstracts
- **LaTeX compilation:** Automated conversion and PDF generation

**Human oversight and quality control:**
- All research questions, theoretical framing, and methodological decisions were
  made by human authors
- All AI-generated text was reviewed, revised, and approved by human authors
- Empirical data collection and analysis were conducted by human authors
- Final manuscript was reviewed and approved by all human co-authors

**AI disclosure:** [Statement per venue requirements, e.g., "In accordance with
[Venue]'s AI policy, we disclose that AI tools were used in the preparation of
this manuscript as described above. All authors take full responsibility for the
content."]

Step 3: TRACK Responsibilities

Task Assignment Matrix

For ongoing collaboration, track who is responsible for what:

## Task Assignment

| Task | Responsible | Deadline | Status |
|------|------------|----------|--------|
| Finalize RQs | Author 1 | [date] | Done |
| Data collection | Author 1 | [date] | In progress |
| Method section review | Author 2 | [date] | Pending |
| Figure 3 redesign | AI Agent | [date] | Done |
| Discussion revision | Author 1 + Author 2 | [date] | Pending |
| Final proofread | Author 2 | [date] | Pending |
| Cover letter | Author 1 | [date] | Pending |
| Submission | Author 1 (corresponding) | [date] | Pending |

Step 4: GENERATE Output

Author Contribution Statement (for manuscript)

Generate venue-appropriate contribution statement:

CRediT format (most journals):

Author Contributions: [Author 1]: Conceptualization (lead), Investigation (lead),
Methodology (lead), Project administration (lead), Validation (lead), Writing —
review & editing (lead). [Author 2]: Conceptualization (supporting), Funding
acquisition (lead), Resources (lead), Supervision (lead), Writing — review &
editing (lead).

Prose format (some journals):

[Author 1] conceived the study, conducted the literature review, designed the
methodology, and wrote the initial manuscript. [Author 2] supervised the project,
provided critical feedback on theoretical framing, and co-edited the final
manuscript. Both authors approved the final version.

Save

FileContent
author_contributions.mdFull CRediT matrix + AI statement + task tracker
Add to paper.texCRediT statement in Author Contributions section
Add to submission/AI disclosure statement for venue requirements

Integration

ScenarioIntegration
Submission-engineProvides author contribution statement for submission
Orchestration logComplements the AI audit trail
Review-engineTracks who addresses which reviewer comment

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.