🇺🇸English

Research Ideation

A goal-driven workflow for finding important research problems, designing novel solutions, and building deep field understanding through structured paper reading.

When to Use This Skill

• User wants to find a research direction or brainstorm research ideas
• User needs to do a literature review or map a research field
• User asks about evaluating whether an idea is novel or worth pursuing
• User wants to read papers more effectively or build a systematic reading habit
• User mentions "research ideation", "find a problem", "literature tree", "novelty check", "paper reading"

Goal-Driven Research Workflow

Follow these five steps in order. Each step builds on the previous one.

Step 1: Define a Long-Term Research Goal

Start with a goal that has both scientific and practical value. The goal should be ambitious enough to sustain multiple papers, but concrete enough to guide daily decisions.

Ask: "What is the ultimate form of this research direction? What would the world look like if this problem were fully solved?"

Step 2: Build a Literature Tree

Map the field by constructing two complementary trees:

• Novelty tree : Classify existing work by milestone tasks, representative pipelines, and novel modules. This reveals WHERE the field has gaps.
• Challenge-insight tree : Collect technical challenges and the insights/techniques that address them. This reveals WHICH problems lack good solutions.

See references/literature-tree.md for the full construction method and four types of novelty.

Step 3: Select a Problem

Find tasks with genuine research space. The key question: "Is this problem worth solving, or has a well-established solution already claimed this territory?"

Use the well-established solution check (4 levels) to decide whether to proceed or switch problems. Actively seek new failure cases rather than improving on known benchmarks.

See references/problem-selection.md for the full selection framework.

Step 4: Design a Solution

Novel techniques are creative combinations of existing methods, not simple concatenations. Use two design patterns:

• Cross-domain transfer : Find papers in completely different domains that solve a technically similar problem, then adapt their solution.
• Problem decomposition : Break the problem into sub-problems, solve each via cross-domain transfer, then combine.

See references/solution-design.md for the full design methodology and knowledge distillation pipeline.

Step 5: Validate and Iterate

Run experiments on representative data. Use results to refine your understanding. If the approach fails, return to Step 3 or Step 4 with updated knowledge from the failure.

Output artifacts : Research direction summary (problem statement, proposed approach, novelty claim, key risks) — this becomes the input to idea-tournament or paper-planning.

See the experiment-craft skill for systematic debugging when experiments don't work as expected.

Counterintuitive Ideation Rules

Prioritize these rules before regular ideation:

1. Problem selection matters more than solution design : Choosing WHAT to solve has more impact than HOW you solve it. A great solution to an unimportant problem is still unimportant.
2. Pursue new failure cases, not incremental improvements : Don't improve a technique on its original setting. Find new settings where it breaks — new failure cases on new data are contributions even if the technique itself isn't novel.
3. If a well-established solution exists, switch problems : Solving an already-solved problem wastes time regardless of your angle. Improvement space is too small.
4. Technology is creative combination, not concatenation : Novel techniques combine existing methods in non-obvious ways. Simple A-to-B pipelines are not contributions — if direct concatenation worked, the problem would have no technical challenge.
5. When a breakthrough tool appears, apply it to YOUR roadmap : Don't improve the tool itself on its original benchmarks. Use it to solve YOUR milestone tasks — this produces high-impact work because you combine the tool's power with your domain expertise.
6. A paper without real contribution wastes your time : Even if accepted, it doesn't advance the field or earn respect. Do work that genuinely moves the needle.

Structured Paper Reading

Turn reading into structured Q&A using a paper parsing tree. Three levels of depth:

Write a structured summary for every paper you read. Use the template at assets/paper-summary-template.md.

See references/paper-reading.md for the full reading methodology and habit-building guidance.

Handoff to Idea Tournament or Planning

When you have a research direction but want to explore multiple concrete approaches, pass to idea-tournament for tree-structured generation and Elo ranking before planning.

When ideation is complete — you have a problem, a proposed solution approach, and supporting literature — pass these artifacts to paper-planning:

Reference Navigation

Weekly Installs

69

Repository

evoscientist/evoskills

GitHub Stars

105

First Seen

9 days ago

Security Audits

Gen Agent Trust HubPassSocketPassSnykWarn

Installed on

cursor69

gemini-cli69

github-copilot69

amp69

cline69

codex69