/install ars-academic-pipeline
Academic Pipeline — 10-Stage End-to-End (Hermes Edition)
📄 License: CC BY-NC 4.0 · Copyright (c) 2026 Cheng-I Wu
🔗 Original: Imbad0202/academic-research-skills
🔄 Adaptation: Orchestration pipeline implemented via delegate_task instead of Claude Code's internal agent system. All agent definitions, references, and quality standards preserved unchanged from original. This adaptation is distributed under the same CC BY-NC 4.0 license.
Orchestrates the full academic workflow from research idea to publication-ready output.
10 Stages
| Stage | Skill Used | Key Output |
|---|---|---|
| 1. Planning | intake + mode selection | Project Plan with stage gating |
| 2. Research | deep-research (full/quick) | RQ Brief + Methodology + Bibliography + Synthesis |
| 3. Paper Draft | academic-paper (full) | Complete paper draft |
| 4. Peer Review | academic-paper-reviewer (full) | 5-panel review + Editorial Decision |
| 5. Revision | academic-paper (revision) | Revised draft + tracked changes |
| 6. Polish | academic-paper (revision) | Final polished manuscript |
| 7. Ethics Check | academic-paper-reviewer (quick) | Ethics clearance |
| 8. AI Disclosure | academic-paper (disclosure) | Venue-specific AI statement |
| 9. Format | academic-paper (format-convert) | LaTeX/DOCX/PDF + cover letter |
| 10. Deliver | file output | Publication package |
Hermes Execution
The orchestrator (main Hermes agent):
- Stage 1: Clarify user intent → select modes → create Project Plan
- Stage 2-6: Sequential delegate_task calls, each loading the relevant skill
- Stage 7-9: Lightweight parallel or sequential based on dependencies
- Stage 10: Write final package to disk
Key Checkpoints
- Stage 1→2: User approves Project Plan
- Stage 2→3: Research report accepted by user
- Stage 4→5: Review decision received
- Stage 6→7: Polished draft ready
Resume Support
Pipeline state stored in ~/.hermes/sessions/. User can resume with:
Continue the academic pipeline from Stage 4
Usage Patterns
Full pipeline:
Take "AI impact on HE quality assurance" through the full pipeline to publication-ready manuscript
Partial pipeline:
Start from Stage 3 with my existing deep-research output
Resume:
Resume pipeline from Stage 5 with reviewer comments: [comments]
Integration with Hindsight Memory
Pipeline state and key outputs are retained to Hindsight for long-term tracking:
hindsight memory retain --content "[stage_output]" --tags "pipeline,stage-N"
Critical Rules
- ⚠️ Each stage MUST complete before the next begins
- ⚠️ User confirmation at all IRON RULE checkpoints
- ⚠️ Ground truth isolation: review stage must NOT see author identity
Security & Privacy
Orchestration disclosure: This pipeline orchestrates multiple skills (research → writing → review) via delegate_task. All content passes through the AI provider's workflow. Use only with topics you are comfortable processing through AI.
Tool access: This pipeline delegates to sub-skills which independently control their own tool access. No stage is granted terminal, web, or system tools beyond what each sub-skill permits.
Agent files: All agents/ directories across sub-skills contain academic prompt templates, NOT system prompt overrides.
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install ars-academic-pipeline - 安装完成后，直接呼叫该 Skill 的名称或使用
/ars-academic-pipeline触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
Academic Pipeline 是什么？
10-stage end-to-end research-to-publication pipeline orchestrator on Hermes Agent. Stages: planning → deep-research → academic-paper → academic-paper-reviewe... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 100 次。
如何安装 Academic Pipeline？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ars-academic-pipeline」即可一键安装，无需额外配置。
Academic Pipeline 是免费的吗？
是的，Academic Pipeline 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Academic Pipeline 支持哪些平台？
Academic Pipeline 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 Pipeline？
由 Andy Ren（@andyrenxu7255）开发并维护，当前版本 v1.0.2。