academic-researcher
Academic research assistant for literature reviews, paper analysis, and scholarly writing.
Use this skill when the user needs to define or revise the project-level research pipeline.
$ npx -y skills add LigphiDonk/Oh-my--paper --skill research-pipeline-planner --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/research-pipeline-plannerContext preview
The summary Claude sees to decide when to auto-load this skill.
Use this skill when the user needs to define or revise the project-level research pipeline.
id: research-pipeline-planner name: Research Pipeline Planner version: 1.0.0 stages: [survey, ideation, experiment, publication, promotion] tools: [read_file, write_file, update_pipeline]
Use this skill when the user needs to define or revise the project-level research pipeline.
1. Read `instance.json`, `.pipeline/docs/research_brief.json`, and `.pipeline/tasks/tasks.json` first if they exist. 2. Keep the pipeline aligned with the five stages: survey, ideation, experiment, publication, promotion. 3. When the user already has results or a draft, move the starting stage forward instead of rebuilding earlier stages. 4. Do not invent citations, datasets, or experimental outcomes. 5. **When entering ideation stage, use the `research-idea-convergence` skill** to generate candidate directions and let the user choose. Never autonomously decide the research direction. 6. Ensure every stage transition involves a user checkpoint — do not skip stages or auto-advance without user confirmation. 7. **严格线性执行**:任务必须按顺序执行,当前任务未完成前不得跳至下一任务。调研未完成 → 不得进入构思;构思未完成 → 不得进入实验。每个阶段的所有任务 done 后才能进入下一阶段。
A Claude Code plugin that turns your terminal into an autonomous research lab — literature survey, experiment execution, paper writing, all in one pipeline.
Academic research assistant for literature reviews, paper analysis, and scholarly writing.
This skill should be used when the user asks to "run initial analysis", "analyze single-cell data", "QC my data", "run…