Benchmark Paper Template
HKUSTDial/Supervisor-Skills
Structures benchmark and evaluation papers around five pillars, with a completeness audit, an Introduction logic chain, a section skeleton and a pre-submission checklist.
Chains research-refine and experiment-plan to turn a vague research direction into a focused proposal and a claim-driven experiment roadmap.
Install Research Refine Pipeline
$ npx skills add zjYao36/Auto-Research-Refine --skill research-refine-pipeline -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zjYao36/Auto-Research-Refine research-refine-pipeline --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/zjYao36/Auto-Research-Refine.git skills-src && mkdir -p .claude/skills && cp -r skills-src/research-refine-pipeline .claude/skills/research-refine-pipeline && rm -rf skills-srcUse ~/.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/
Install the "research-refine-pipeline" agent skill from https://github.com/zjYao36/Auto-Research-Refine/tree/main/research-refine-pipeline into .claude/skills/research-refine-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-refine-pipeline", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/zjYao36/Auto-Research-Refine/tree/main/research-refine-pipelineType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add zjYao36/Auto-Research-Refine --skill research-refine-pipeline -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zjYao36/Auto-Research-Refine research-refine-pipeline --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zjYao36/Auto-Research-Refine.git skills-src && mkdir -p .agents/skills && cp -r skills-src/research-refine-pipeline .agents/skills/research-refine-pipeline && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "research-refine-pipeline" agent skill from https://github.com/zjYao36/Auto-Research-Refine/tree/main/research-refine-pipeline into .agents/skills/research-refine-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-refine-pipeline", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zjYao36/Auto-Research-Refine --skill research-refine-pipeline -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zjYao36/Auto-Research-Refine research-refine-pipeline --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zjYao36/Auto-Research-Refine.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/research-refine-pipeline .cursor/skills/research-refine-pipeline && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "research-refine-pipeline" agent skill from https://github.com/zjYao36/Auto-Research-Refine/tree/main/research-refine-pipeline into .cursor/skills/research-refine-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-refine-pipeline", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/zjYao36/Auto-Research-Refine.git --path research-refine-pipeline--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add zjYao36/Auto-Research-Refine --skill research-refine-pipeline -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zjYao36/Auto-Research-Refine research-refine-pipeline --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zjYao36/Auto-Research-Refine.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/research-refine-pipeline .gemini/skills/research-refine-pipeline && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "research-refine-pipeline" agent skill from https://github.com/zjYao36/Auto-Research-Refine/tree/main/research-refine-pipeline into .gemini/skills/research-refine-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-refine-pipeline", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install zjYao36/Auto-Research-Refine research-refine-pipelineInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add zjYao36/Auto-Research-Refine --skill research-refine-pipeline -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/zjYao36/Auto-Research-Refine.git skills-src && mkdir -p .github/skills && cp -r skills-src/research-refine-pipeline .github/skills/research-refine-pipeline && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "research-refine-pipeline" agent skill from https://github.com/zjYao36/Auto-Research-Refine/tree/main/research-refine-pipeline into .github/skills/research-refine-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-refine-pipeline", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zjYao36/Auto-Research-Refine --skill research-refine-pipeline -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install zjYao36/Auto-Research-Refine research-refine-pipeline --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zjYao36/Auto-Research-Refine.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/research-refine-pipeline .opencode/skills/research-refine-pipeline && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "research-refine-pipeline" agent skill from https://github.com/zjYao36/Auto-Research-Refine/tree/main/research-refine-pipeline into .opencode/skills/research-refine-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-refine-pipeline", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
research-refine-pipeline- GitHub stars
- 128
- Used in
- 5 other repos
- Token cost
- ~1.4k tokens
- SKILL.md length
- 520 words
- Files
- 2
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- None found
At a glance
Chains research-refine and experiment-plan to turn a vague research direction into a focused proposal and a claim-driven experiment roadmap.
- Works in 6 steps: Triage the Starting Point → Method Refinement Stage → Planning Gate → …
- Going from a vague research direction to a proposal and experiment plan in one pass
- SKILL.md covers Overview, Core Rule, Default Outputs and Workflow, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This skill is for someone who wants a single run from a rough research idea to both a refined method and a detailed experiment plan. It composes two sibling skills, research-refine for method refinement and experiment-plan for claim-driven validation, and reads their files only when stage-specific detail is needed. Its core rule is to stabilize the thesis first and only then turn it into experiments.
The first phase triages the starting point: the problem, rough approach, constraints, resources and target venue, plus a check on whether an existing refine-logs/FINAL_PROPOSAL.md still matches the request. A stale or missing proposal triggers the full refinement stage, which keeps the problem anchor, prefers the smallest adequate mechanism and one dominant contribution, and ends only when the thesis, rejected complexity, key claims, must-run ablations and remaining risks are explicit. A planning gate comes before the experiment stage.
Default outputs go to the refine-logs folder: a final proposal, a review summary, a refinement report, an experiment plan, an experiment tracker and a pipeline summary that says what to run next.
When your agent uses it
- Going from a vague research direction to a proposal and experiment plan in one pass
- Reusing an existing refined proposal and planning its experiments
- Producing a pipeline summary of what to run next
Example prompts
- “Take my idea about sparse attention for long documents and produce the final proposal and the experiment plan.”
- “Run the full research pipeline on my notes, reusing the existing proposal if it still fits.”
- “Refine my method for few-shot segmentation, then plan the experiments end to end.”
Requirements
- The research-refine and experiment-plan skills installed alongside this one
- Pre-approved tools (allowed-tools): Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent, mcp__codex__codex, mcp__codex__codex-reply
Workflow steps
6 steps, taken from the step headings in SKILL.md.
- Triage the Starting Point
- Method Refinement Stage
- Planning Gate
- Experiment Planning Stage
- Integration Summary
- Present a Brief Summary to the User
What it can do on your machine
Read from SKILL.md and the folder at commit a1f1449. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
Bash(*)ReadWriteEditGrepGlobWebSearchWebFetchAgentmcp__codex__codex
…and 1 more on the same allowed-tools line.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
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 Pipeline loads about 1.4k tokens when it runs. Until then it costs about 88 tokens; SKILL.md has 520 words of instructions outside code blocks.
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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent, mcp__codex__codex, mcp__codex__c
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
Without a licence we can't republish the file, so here is its outline and opening line. It has 520 words (~1,409 tokens).
- name
- research-refine-pipeline
- allowed-tools
- Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent, mcp__codex__codex, mcp__codex__codex-reply
Files
SKILL.md and 1 other file in research-refine-pipeline of zjYao36/Auto-Research-Refine.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit a1f1449
Used in 5 other repositories
We found 10 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 5 other GitHub owners. This page covers the copy in zjYao36/Auto-Research-Refine, which our catalogue first saw on October 7, 2026.
- AI4Scientist/nano-scientistskills/research-refine-pipelineskills/skills-codex/research-refine-pipeline
- OpenLAIR/dr-clawskills/aris-research-refine-pipeline
- wanshuiyin/Auto-claude-code-research-in-sleepskills/research-refine-pipelineskills/skills-codex/research-refine-pipeline
- brycewang-stanford/Auto-Empirical-Research-Skillsskills/42-wanshuiyin-ARIS/skills/research-refine-pipelineskills/42-wanshuiyin-ARIS/skills/skills-codex/research-refine-pipeline
- Tai609/NebulaMatruntime/skills-bundle/aris-research-refine-pipelineruntime/aris/skills-nebulamat/aris-research-refine-pipeline+1 more
Compare with similar skills
Research Refine Pipeline 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Research Refine Pipeline this skillzjYao36/Auto-Research-Refine | 128 | 5 repos | ~1.4k | Automated safety check: Notes | None | |
| Benchmark Paper TemplateHKUSTDial/Supervisor-Skills | 8.8k | — | ~2.8k | Automated safety check: Pass | CC-BY-4.0 | |
| Scholar Evaluationjimmc414/Kosmos | 595 | 1 repos | ~2.5k | Automated safety check: Pass | None | |
| Academic Researchvoidful/academic-skills | 135 | — | ~887 | Automated safety check: Pass | MIT | |
| Academic Writingwentorai/Research-Claw | 858 | — | ~896 | Automated safety check: Pass | Custom licence | |
| Research Paper WritingRedWoodOG/Hermes-Desktop | 177 | 6 repos | ~16k | Automated safety check: Notes | MIT |
Similar skills
Scholar Evaluation
jimmc414/Kosmos
Systematic framework for evaluating scholarly and research work based on the ScholarEval methodology.
Academic Research
voidful/academic-skills
Complete academic research skill suite covering the full pipeline: paper reading (read/explain papers with storytelling), idea generation (brainstorm research directions), experiment design (plan…
Academic Writing
wentorai/Research-Claw
Academic writing expert specializing in scholarly papers, literature reviews, research methodology, and thesis writing with strict academic standards.
Research Paper Writing
RedWoodOG/Hermes-Desktop
End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission.
Bgpt Paper Search
agent-skills-hub/agent-skills-hub
Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server.
More from zjYao36/Auto-Research-Refine
Claim-Driven Experiment Planner
zjYao36/Auto-Research-Refine
Turns a refined research proposal into a claim-to-evidence-to-run-order roadmap instead of a sprawling benchmark wishlist.
Research Refine
zjYao36/Auto-Research-Refine
Turns a vague research direction into a focused, problem-anchored method plan through up to five review rounds with a second model.
Related
Categories
Questions about Research Refine Pipeline
What does Research Refine Pipeline do?
Chains research-refine and experiment-plan to turn a vague research direction into a focused proposal and a claim-driven experiment roadmap. This skill is for someone who wants a single run from a rough research idea to both a refined method and a detailed experiment plan. It composes two sibling skills, research-refine for method refinement and experiment-plan for claim-driven validation, and reads their files only when stage-specific detail is needed.
When should I use Research Refine Pipeline?
Research Refine Pipeline fits situations like: going from a vague research direction to a proposal and experiment plan in one pass; reusing an existing refined proposal and planning its experiments; producing a pipeline summary of what to run next.
How do I install Research Refine Pipeline in Claude Code?
Run `npx skills add zjYao36/Auto-Research-Refine --skill research-refine-pipeline -a claude-code`. Or copy the skill folder (research-refine-pipeline in zjYao36/Auto-Research-Refine) into .claude/skills/research-refine-pipeline in your project. Claude Code loads it when a task matches its description.
How do I install Research Refine Pipeline in Codex?
Run `npx skills add zjYao36/Auto-Research-Refine --skill research-refine-pipeline -a codex`. Or copy the skill folder (research-refine-pipeline in zjYao36/Auto-Research-Refine) into .agents/skills/research-refine-pipeline in your project. Codex loads it when a task matches its description.
Can I use Research Refine Pipeline 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 zjYao36/Auto-Research-Refine --skill research-refine-pipeline -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-pipeline, .gemini/skills/research-refine-pipeline, .github/skills/research-refine-pipeline and .opencode/skills/research-refine-pipeline in your project.
What does Research Refine Pipeline need to run?
SKILL.md names no scripts, command-line tools or credentials: Research Refine Pipeline is instructions for the agent only. Our summary lists: The research-refine and experiment-plan skills installed alongside this one. Its frontmatter pre-approves these tools: Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent, mcp__codex__codex, mcp__codex__codex-reply.
Does Research Refine Pipeline 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 Pipeline safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Research Refine Pipeline use?
No licence was found for Research Refine Pipeline or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Research Refine Pipeline use?
About 1.4k tokens (SKILL.md is roughly 5.6k 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 Pipeline?
Skills that share tags, products or a category with Research Refine Pipeline: Benchmark Paper Template (HKUSTDial/Supervisor-Skills, 8.8k stars), Scholar Evaluation (jimmc414/Kosmos, 595 stars), Academic Research (voidful/academic-skills, 135 stars) and Academic Writing (wentorai/Research-Claw, 858 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Research Refine Pipeline?
zjYao36 (a GitHub user) maintains it in zjYao36/Auto-Research-Refine, which has 128 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on March 16, 2026.
Source: zjYao36/Auto-Research-Refine on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.