New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Research Refine

by appleweiping in appleweiping/WEIPING_WIKI

Disciplined idea refinement for research projects. An agent skill from appleweiping/WEIPING_WIKI.

MITAuto-check passedResearch & Science

Install Research Refine

skills CLI
$ npx skills add appleweiping/WEIPING_WIKI --skill research-refine -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install appleweiping/WEIPING_WIKI research-refine --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/aris/skills/research-refine .claude/skills/research-refine && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
research-refine
GitHub stars
119
Token cost
~887 tokens
SKILL.md length
428 words
Files
1
Skills in repo
51
Repo updated
First seen
Licence
MIT

At a glance

Disciplined idea refinement for research projects. An agent skill from appleweiping/WEIPING_WIKI.

  • Works in 5 steps: Problem Decomposition → Literature Stress Test → Feasibility Assessment → …
  • User says research-refine
  • SKILL.md covers Decision Gate, Phase 1 — Problem Decomposition, Phase 2 — Literature Stress Test and Phase 3 — Feasibility Assessment, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Research Refine is an agent skill from appleweiping/WEIPING_WIKI. Disciplined idea refinement for research projects. Takes a raw idea and stress-tests it into a publishable research question with clear novelty, feasibility, and positioning. Use when user says "research-refine", "refine idea", "打磨想法", "refine this research direction", or presents a raw research idea that needs sharpening.

Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Hypothesis generation, Brainstorming and Load testing. The repository describes itself as: knowledge base managed with an LLM workflow. The licence is MIT.

When your agent uses it

  • User says research-refine
  • Refine this research direction
  • Presents a raw research idea that needs sharpening

Example prompts

  • “research-refine”
  • “refine idea”
  • “refine this research direction”
  • “/research-refine”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Problem Decomposition
  2. Literature Stress Test
  3. Feasibility Assessment
  4. Research Question Crystallization
  5. Handoff

What it can do on your machine

Read from SKILL.md and the folder at commit 76fdc42. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Research Refine loads about 887 tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 428 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~887

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from appleweiping/WEIPING_WIKI at commit 76fdc42, republished under its MIT licence (© appleweiping). 428 words, ~887 tokens.

Download SKILL.mdSave it as .claude/skills/research-refine/SKILL.md (or your agent's skills folder).
name
research-refine
description
Disciplined idea refinement for research projects. Takes a raw idea and stress-tests it into a publishable research question with clear novelty, feasibility, and positioning. Use when user says "research-refine", "refine idea", "打磨想法", "refine this research direction", or presents a raw research idea that needs sharpening.

Research Refine

Transform a raw research idea into a publication-ready research question. This is where most bad papers die — skip nothing.

Decision Gate

Before running:

  • Is there a raw idea or direction to refine? (If not, run idea-discovery first)
  • Is the target venue clear? (NeurIPS/ICML/ICLR oral level)
  • Do you have access to the project's refine-logs/ directory?

Phase 1 — Problem Decomposition

Break the idea into atomic claims:

  1. State the core claim in one sentence: "We show that X improves Y by doing Z"
  2. Identify the gap: What existing work fails to do? Why?
  3. Novelty check: Is this a new problem framing (required) or just A+B stitching (forbidden)?
  4. Scope the contribution: Theory? Method? System? Empirical finding?

Output: refine-logs/CLAIM_DECOMPOSITION.md

Phase 2 — Literature Stress Test

Kill the idea before it kills your time:

  1. Search for prior art that already solves this (or claims to)
  2. Find the 3 closest papers — read abstracts + methods
  3. Differentiation matrix: For each close paper, state exactly how your approach differs
  4. Kill argument: Write the strongest reviewer objection. If you can't refute it, pivot.

Quality check: If differentiation from closest work is < 1 fundamental insight, STOP and reformulate.

Output: refine-logs/LITERATURE_STRESS_TEST.md

Phase 3 — Feasibility Assessment

  1. Data: What datasets? Available? Size sufficient for statistical significance (20+ seeds)?
  2. Compute: GPU hours estimate. Can you run full experiments on available hardware?
  3. Baselines: List 8+ baselines (minimum per quality standards). Are implementations available?
  4. Timeline: Weeks to first meaningful result? Weeks to full paper?
  5. Risk factors: What could make this impossible? (data access, compute, theoretical dead-end)

Quality check: If any risk factor has >30% probability of blocking, define a pivot plan.

Output: refine-logs/FEASIBILITY.md

Show full SKILL.md (149 more words)Show less

Phase 4 — Research Question Crystallization

  1. Write the final research question (1 sentence, precise, testable)
  2. Write the hypothesis (falsifiable, with clear success/failure criteria)
  3. Define the evaluation protocol (metrics, datasets, baselines, statistical tests)
  4. Position in the field: One paragraph explaining where this sits relative to SOTA

Quality check: Show to Codex for cross-model review using an explicit context pack through agentmemory signals/actions, or by handing the same context to the current Codex session. Codex must score >=7/10 on novelty and feasibility.

Output: refine-logs/RESEARCH_QUESTION.md

Phase 5 — Handoff

  • Update memory/facts/<project>-status.md with refined research question
  • Next ARIS step: experiment-plan
  • Handoff to: CC (architect) for experiment planning

Hard Rules

  • No A+B stitching (forbidden per quality standards)
  • Must have original problem reframing
  • Kill argument must be attempted honestly — don't softball it
  • If Codex review scores <6 on any dimension, iterate before proceeding
  • Evidence labels: everything in refine-logs is "diagnostic" until experiment-plan passes

© appleweiping, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/aris/skills/research-refine of appleweiping/WEIPING_WIKI.

Open the folder on GitHubat commit 76fdc42

Compare with similar skills

Research Refine next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Research Refine compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Research Refine this skillappleweiping/WEIPING_WIKI119—~887Automated safety check: PassMIT
Academic GrillExekiel179/psyclaw103—~2kAutomated safety check: PassMIT
Scientific Brainstormingspacering-net/codeg3.9k13 repos~2kAutomated safety check: PassMIT
Scientific BrainstormingOleafly/Oleafly2092 repos~3.5kAutomated safety check: PassMIT
Scientific Problem Selectionaws-samples/amazon-bedrock-agents-healthcare-lifesciences2743 repos~2.8kAutomated safety check: PassApache-2.0
Research IdeationGalaxy-Dawn/claude-scholar5.7k2 repos~2.4kAutomated safety check: PassMIT

Similar skills

  • Academic Grill

    Exekiel179/psyclaw

    Stress-test an academic research question, proposal, study design, analysis plan, manuscript claim, review protocol, or AI research project through a one-question-at-a-time interview until its…

    103 GitHub stars~2k tokensUpdated 11 days ago
    Research & ScienceAuto-check passed

  • Scientific Brainstorming

    spacering-net/codeg

    Creative research ideation and exploration. An agent skill from spacering-net/codeg.

    3.9k GitHub starsUsed in 13 repos~2k tokens
    Research & ScienceAuto-check passed

  • Scientific Brainstorming

    Oleafly/Oleafly

    Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial review, and decision logs.

    209 GitHub starsUsed in 2 repos~3.5k tokens
    Research & ScienceAuto-check passed

  • Scientific Problem Selection

    aws-samples/amazon-bedrock-agents-healthcare-lifesciences

    Official

    This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions.

    274 GitHub starsUsed in 3 repos~2.8k tokens
    Research & ScienceAuto-check passed

  • Research Ideation

    Galaxy-Dawn/claude-scholar

    This skill should be used when the user asks to "brainstorm research ideas", "use 5W1H framework", "identify research gaps", "conduct gap analysis", "start research project", "conduct literature…

    5.7k GitHub starsUsed in 2 repos~2.4k tokens
    Research & ScienceAuto-check passed

  • News to Research Idea Briefing

    OpenLAIR/dr-claw

    Clusters the latest news-feed results by topic and writes a briefing of research idea seeds with citations, plus a structured seeds file, without crawling new sources.

    1.2k GitHub stars~1.3k tokensUpdated 22 days ago
    Research & ScienceAuto-check: notes

More from appleweiping/WEIPING_WIKI

All 51 skills in this repo

  • Communication Assistant

    appleweiping/WEIPING_WIKI

    Unified lazy-mode communication assistant for Vipin across WhatsApp, WeChat, QQ, Feishu/Lark, and email.

    119 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Content Refinement Agent

    appleweiping/WEIPING_WIKI

    Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). An agent skill from appleweiping/WEIPING_WIKI.

    119 GitHub stars~3k tokensUpdated 1 mo ago
    Auto-check passed

  • Chrome Automation

    appleweiping/WEIPING_WIKI

    Connect to and control Google Chrome browser using agent-browser with CDP (Chrome DevTools Protocol).

    119 GitHub starsUsed in 1 repo~5.3k tokens
    Auto-check: warnings

  • Email Assistant

    appleweiping/WEIPING_WIKI

    Personal Gmail and Google Workspace email assistant for Vipin.

    119 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed

  • Wechat Video Channel Publish

    appleweiping/WEIPING_WIKI

    A skill your agent uses when the user wants to log into 微信视频号, validate cookie state, upload videos, set scheduled publish time, fill long description, set a cover image, or save drafts through a…

    119 GitHub stars~765 tokensUpdated 1 mo ago
    Auto-check passed

  • Feishu Bridge

    appleweiping/WEIPING_WIKI

    Route Feishu/Lark content access for Codex. An agent skill from appleweiping/WEIPING_WIKI.

    119 GitHub stars~906 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Research Refine

What does Research Refine do?

Disciplined idea refinement for research projects. An agent skill from appleweiping/WEIPING_WIKI. Research Refine is an agent skill from appleweiping/WEIPING_WIKI. Disciplined idea refinement for research projects.

When should I use Research Refine?

Research Refine fits situations like: user says research-refine; refine this research direction; presents a raw research idea that needs sharpening.

How do I install Research Refine in Claude Code?

Run `npx skills add appleweiping/WEIPING_WIKI --skill research-refine -a claude-code`. Or copy the skill folder (.claude/skills/aris/skills/research-refine in appleweiping/WEIPING_WIKI) into .claude/skills/research-refine in your project. Claude Code loads it when a task matches its description.

How do I install Research Refine in Codex?

Run `npx skills add appleweiping/WEIPING_WIKI --skill research-refine -a codex`. Or copy the skill folder (.claude/skills/aris/skills/research-refine in appleweiping/WEIPING_WIKI) into .agents/skills/research-refine in your project. Codex loads it when a task matches its description.

Can I use Research Refine in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add appleweiping/WEIPING_WIKI --skill research-refine -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research-refine, .gemini/skills/research-refine, .github/skills/research-refine and .opencode/skills/research-refine in your project.

What does Research Refine need to run?

SKILL.md names no scripts, command-line tools or credentials: Research Refine is instructions for the agent only.

Does Research Refine access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Research Refine safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Research Refine use?

Research Refine is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Research Refine use?

About 887 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Research Refine?

Skills that share tags, products or a category with Research Refine: Academic Grill (Exekiel179/psyclaw, 103 stars), Scientific Brainstorming (spacering-net/codeg, 3.9k stars), Scientific Brainstorming (Oleafly/Oleafly, 209 stars) and Scientific Problem Selection (aws-samples/amazon-bedrock-agents-healthcare-lifesciences, 274 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Research Refine?

appleweiping (a GitHub user) maintains it in appleweiping/WEIPING_WIKI, which has 119 GitHub stars. The repository holds 51 skills in this directory. The repository was last updated on August 26, 2026.

Source: appleweiping/WEIPING_WIKI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.