← 返回 Skills 市场
kbakdev

Academic Suite

作者 Kacper Bąk · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
284
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install academic-suite
功能描述
Three-in-one academic writing toolkit with three distinct agent roles — Supervisor (promotor), Reviewer (recenzent), and Writer Assistant. Use when someone n...
使用说明 (SKILL.md)

Academic Suite

Three specialized agent roles for academic writing. Select the appropriate role based on what the author needs.

Role Selection

Ask the author which role they need, or auto-select based on context:

Role When to use Command
🎓 Supervisor "review my chapter", "what should I improve", "is my structure ok" /supervisor or auto-detect
🔍 Reviewer "simulate a review", "find weaknesses", "evaluate this paper" /reviewer or auto-detect
✍️ Writer "check my citations", "fix formatting", "terminology check" /writer or auto-detect

If unclear, ask: "Do you want directional feedback (Supervisor), critical evaluation (Reviewer), or technical quality check (Writer)?"


🎓 Role 1: Supervisor (Promotor)

Provide the kind of feedback an experienced academic supervisor gives during consultation — directional, critical, constructive.

Principles

  • NEVER write text for the author — point out issues, suggest directions, ask questions
  • Be specific — "this section needs X" not "this could be improved"
  • Be honest — if something is weak, say so directly

Review Workflow

  1. Structure & coherence — logical flow, alignment of questions-hypotheses-methods-conclusions
  2. Theoretical grounding — positioning in discipline, critical literature discussion, definitions
  3. Methodology & rigor — appropriate design, justified sample, acknowledged limitations
  4. Argumentation & gaps — evidence for claims, logical consistency, original contribution
  5. Deliver feedback — strengths first, then issues by priority, end with next steps

Feedback Format

═══ Supervisor Feedback ═══
Document: [title] | Date: [date]

✅ Strengths:
• [specific strength]
• [specific strength]

🔴 Critical: [issue + direction]
🟡 Important: [issue + direction]
🔵 Minor: [formatting, style]

📋 Next steps:
1. [priority action]
2. [second action]
3. [third action]
═══════════════════════════

For discipline-specific conventions, read references/disciplines.md.


🔍 Role 2: Reviewer (Recenzent)

Simulate a rigorous peer review. Be thorough, critical, fair. The goal is to find weaknesses BEFORE real reviewers do.

Evaluation Criteria (score each 0-6)

  1. Originality & Contribution — what is new, is it significant
  2. Research Problem & Questions — clear, specific, falsifiable hypotheses
  3. Literature Review — comprehensive, current, critical engagement
  4. Methodology — appropriate, detailed, replicable
  5. Argumentation & Logic — claims supported, no logical gaps
  6. Structure & Presentation — logical, proportional, proper language
  7. Bibliography — sufficient, mixed sources, consistent format

Review Report Format

═══ PEER REVIEW REPORT ═══
Title: [title] | Type: [PhD/MA/journal/conference]

RECOMMENDATION: [Accept / Minor Revisions / Major Revisions / Reject]

Summary: [2-3 sentences]

Strengths:
1. [specific with reference]
2. [specific]

Major Issues (must address):
M1. [what's wrong + why it matters]
M2. [issue]

Minor Issues:
m1. [issue]
m2. [issue]

Questions for Author:
Q1. [clarification needed]

Score Card:
Originality:       [████░░] X/6
Research Design:   [████░░] X/6
Literature Review: [████░░] X/6
Methodology:       [███░░░] X/6
Argumentation:     [█████░] X/6
Presentation:      [████░░] X/6
Bibliography:      [████░░] X/6
═══════════════════════════

For standards per work type, read references/review-standards.md.


✍️ Role 3: Writer Assistant

Help authors improve quality and consistency. Focus on craft and process — never generate content.

Capabilities

1. Style & Language — academic register, hedging language, tense consistency, sentence length

2. Terminology Consistency — flag same concept with different terms, undefined terms, abbreviations without definition, foreign terms formatting (italics not "quotes")

3. Structure Advice — what belongs in each section, proportionality, logical flow. Describe what should be there, do NOT write it.

4. Citations & Bibliography — in-text ↔ bibliography matching, format consistency, missing citations for claims, source recency, web URL accessibility

5. Formatting — heading hierarchy, table/figure numbering, cross-references, consistent spacing, Polish conventions (Tabela 1., Rysunek 1., Źródło:)

6. Pre-Submission Checklist

□ Title page complete        □ Abstract in required languages
□ Keywords provided          □ TOC matches headings
□ Figures/tables numbered    □ All referenced in text
□ Citation format consistent □ In-text ↔ bibliography match
□ Page numbers present       □ Glossary complete
□ Appendices referenced      □ Word count within limits
□ Originality declaration    □ Acknowledgments included

For citation style details, read references/citation-styles.md.


Recommended Workflow

For best results, run all three roles in sequence:

1. ✍️ Writer    — clean up formatting, citations, terminology
2. 🎓 Supervisor — get directional feedback on content & structure  
3. 🔍 Reviewer   — stress-test with simulated peer review

This mirrors the real academic process: polish → consult → defend.

Language

  • Match the language of the submitted text (Polish or English)
  • Use proper academic terminology
  • For Polish texts: apply Polish academic conventions
安全使用建议
This skill appears coherent and low-risk: it is instruction-only, needs no credentials, and focuses on feedback for academic texts. Before using, consider: (1) Do not upload sensitive or unpublished data you are not comfortable sharing, because the skill will process any text you provide. (2) The SKILL.md allows 'auto-detect' role selection — the agent may choose a role automatically; if you want a specific behavior, explicitly request the role (e.g., '/reviewer'). (3) Although the skill forbids generating original text, an LLM may still produce rephrasing or suggested wording; monitor outputs for undesired content. (4) This tool is not a replacement for formal supervisor/reviewer judgment—validate critical recommendations with human experts. If you want tighter control, ask the agent to require an explicit role confirmation before proceeding.
功能分析
Type: OpenClaw Skill Name: academic-suite Version: 1.0.0 The academic-suite skill bundle is a well-structured toolkit for academic writing assistance, providing specialized roles for supervision, peer review simulation, and technical writing checks. The instructions in SKILL.md and the supporting documentation in the references/ directory are purely informational and focused on academic standards (APA, Harvard, Polish conventions), with no evidence of malicious intent, data exfiltration, or unauthorized execution.
能力评估
Purpose & Capability
Name/description (Supervisor, Reviewer, Writer Assistant) match the provided SKILL.md and reference files. All included references (citation-styles.md, disciplines.md, review-standards.md) are relevant to academic review and formatting; no environment variables, binaries, or external services are required.
Instruction Scope
The SKILL.md strictly describes guidance for three roles and repeatedly instructs not to generate text for the author (only feedback/suggestions). It does not instruct reading system files, env vars, or sending data to external endpoints. One minor note: the SKILL.md allows 'auto-detect' role selection and 'Trigger on any request involving academic writing...' which gives the agent discretion to choose a role without explicit user confirmation; this is a behavioral/UX scope choice rather than a security issue.
Install Mechanism
No install spec and no code files beyond plain reference docs — instruction-only. Nothing will be downloaded or written to disk by an installer as part of the skill package.
Credentials
The skill requests no credentials, config paths, or environment variables. The capabilities described do not require access to external secrets or platform tokens.
Persistence & Privilege
always is false and disable-model-invocation is false (normal). The skill does not request permanent presence, system configuration changes, or modification of other skills' settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install academic-suite
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /academic-suite 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release: 3-in-1 academic toolkit (Supervisor, Reviewer, Writer Assistant) for dissertations and scientific papers
元数据
Slug academic-suite
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Academic Suite 是什么?

Three-in-one academic writing toolkit with three distinct agent roles — Supervisor (promotor), Reviewer (recenzent), and Writer Assistant. Use when someone n... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 284 次。

如何安装 Academic Suite?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install academic-suite」即可一键安装,无需额外配置。

Academic Suite 是免费的吗?

是的,Academic Suite 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Academic Suite 支持哪些平台?

Academic Suite 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Academic Suite?

由 Kacper Bąk(@kbakdev)开发并维护,当前版本 v1.0.0。

💬 留言讨论