Research Planning
Turn a vague research topic or paper idea into a structured plan, architecture, task DAG, and experiment outline before implementation.
Overview
research-planning is an agent skill most often used in Idea (also Validate scope, Build pm) that designs research plans, paper architectures, and experiment outlines from a topic or idea.
Install
npx skills add https://github.com/lingzhi227/agent-research-skills --skill research-planningWhat is this skill?
- 4-stage planning flow: overall plan, architecture (incl. Mermaid), logic design with dependencies, and configuration/hyp
- Produces paper architecture, methodology outlines, dependency-ordered task lists, UML-style diagrams, and experiment des
- Grounded in Paper2Code, AI-Researcher, and AgentLaboratory planning prompts via bundled references
- Accepts topic, idea description, or paper-to-reproduce as $0 argument-hint input
- 4-stage planning approach (overall plan, architecture, logic design, configuration)
Adoption & trust: 724 installs on skills.sh; 114 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have a research topic but no ordered methodology, architecture, tasks, or paper structure for your agent or lab notebook to execute against.
Who is it for?
Starting a new ML or systems research thread, reproducing a paper, or briefing an agent lab with schemas and milestones.
Skip if: Quick product feature specs with no experiments, or teams that only need a one-page PRD without methodology or eval design.
When should I use this skill?
Use when starting a new research project or paper; argument-hint topic-or-idea.
What do I get? / Deliverables
You receive a structured research plan with architecture diagrams, dependency-ordered tasks, and config guidance ready for implementation or writing-plans-style execution.
- Overall research plan
- Architecture and logic designs with diagrams
- config.yaml-oriented hyperparameter spec
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
New research projects start in Idea when the question, significance, and feasibility must be clarified before validation or build. Research subphase fits methodology design, literature context, and experiment planning—not yet production coding.
Where it fits
Frame the core question, significance, and available datasets before any implementation sprint.
Define evaluation metrics and minimal experiments to prove the idea is worth a full build.
Hand agents a dependency-ordered task list and file architecture from the logic-design stage.
Map planned benchmarks and ablations from the plan into a reproducibility checklist before release.
How it compares
Use for academic and experiment-first planning instead of generic SaaS brainstorming without metrics or file-level architecture.
Common Questions / FAQ
Who is research-planning for?
Solo researchers, PhD students, and indie builders running agent-assisted labs who need Paper2Code-style structure before coding or drafting.
When should I use research-planning?
In Idea (research) when defining a new project; in Validate (scope) to lock methodology before a prototype; in Build (pm) when breaking a approved plan into dependency-ordered agent tasks.
Is research-planning safe to install?
It is documentation and prompt workflow only; check this page’s Security Audits panel and your agent’s file access when pointing at local papers or secrets in config.
SKILL.md
READMESKILL.md - Research Planning
# Research Planning Create comprehensive research plans and paper architectures from a research topic or idea. ## Input - `$0` — Research topic, idea description, or paper to reproduce ## References - Planning prompts from Paper2Code, AI-Researcher, AgentLaboratory: `~/.claude/skills/research-planning/references/planning-prompts.md` - Output schemas and templates: `~/.claude/skills/research-planning/references/output-schemas.md` ## Workflow ### Step 1: Understand the Research Context - Read any provided papers, code, or references - Identify the core research question and its significance - Assess available resources (datasets, compute, existing code) ### Step 2: Generate Research Plan Use the 4-stage planning approach (adapted from Paper2Code): 1. **Overall Plan** — Strategic overview: methodology, key experiments, evaluation metrics 2. **Architecture Design** — File structure, system design, Mermaid class/sequence diagrams 3. **Logic Design** — Task breakdown with dependencies, required packages, shared knowledge 4. **Configuration** — Extract or specify hyperparameters, training details, config.yaml ### Step 3: Structure the Paper Design the paper structure with section-by-section plan: - Abstract, Introduction, Background, Related Work, Methods, Experiments, Results, Discussion/Conclusion - For each section: key points to cover, required figures/tables, target word count ### Step 4: Create Task Dependency Graph - Order tasks by dependency (data → model → training → evaluation → writing) - Identify parallelizable tasks - Flag risks and potential failure modes ## Output Format ```json { "research_question": "...", "methodology": "...", "paper_structure": { "sections": ["Abstract", "Introduction", ...], "section_plans": { "Introduction": "..." } }, "task_list": [ {"task": "...", "depends_on": [], "priority": 1} ], "baselines": ["..."], "datasets": ["..."], "evaluation_metrics": ["..."], "risks": ["..."] } ``` ## Rules - Each plan component must be detailed and actionable - Include specific implementation references when available - Ensure all components work together coherently - Always include a testing/evaluation plan - Flag ambiguities explicitly rather than making assumptions ## Related Skills - Upstream: [idea-generation](../idea-generation/), [literature-review](../literature-review/) - Downstream: [experiment-design](../experiment-design/), [paper-assembly](../paper-assembly/) - See also: [atomic-decomposition](../atomic-decomposition/) # Research Planning Prompts Reference ## Paper2Code: 4-Turn Planning Conversation ### Turn 1 — Overall Plan **System:** ``` You are an expert researcher and strategic planner with a deep understanding of experimental design and reproducibility in scientific research. You will receive a research paper or idea description. Your task is to create a detailed and efficient plan to implement the methodology described. Instructions: 1. Align with the Paper/Idea: Your plan must strictly follow the methods, datasets, model configurations, hyperparameters, and experimental setups described. 2. Be Clear and Structured: Present the plan in a well-organized and easy-to-follow format, breaking it down into actionable steps. 3. Prioritize Efficiency: Optimize the plan for clarity and practical implementation while ensuring fidelity to the original design. ``` **User:** ``` ## Research Context {research_description} ## Task 1. We want to implement the method described above. 2. Before writing any code, outline a comprehensive plan that covers: - Key details from the Methodology - Important aspects of E