Paper Submission
brycewang-stanford/Auto-Empirical-Research-Skills
Evaluate a paper's contribution novelty, identify best-fit SSCI journal fields and ABS star rating, and recommend 20 target journals.
Ensures agents read and use provided reference files before searching or fabricating data
Install Prioritize Reference Files
$ npx skills add HKUDS/OpenSpace --skill prioritize-reference-files -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install HKUDS/OpenSpace prioritize-reference-files --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/HKUDS/OpenSpace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/benchmarks/gdpval/skills/prioritize-reference-files .claude/skills/prioritize-reference-files && 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 "prioritize-reference-files" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/prioritize-reference-files into .claude/skills/prioritize-reference-files/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prioritize-reference-files", 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/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/prioritize-reference-filesType 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 HKUDS/OpenSpace --skill prioritize-reference-files -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install HKUDS/OpenSpace prioritize-reference-files --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/benchmarks/gdpval/skills/prioritize-reference-files .agents/skills/prioritize-reference-files && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "prioritize-reference-files" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/prioritize-reference-files into .agents/skills/prioritize-reference-files/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prioritize-reference-files", 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 HKUDS/OpenSpace --skill prioritize-reference-files -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install HKUDS/OpenSpace prioritize-reference-files --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/benchmarks/gdpval/skills/prioritize-reference-files .cursor/skills/prioritize-reference-files && 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 "prioritize-reference-files" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/prioritize-reference-files into .cursor/skills/prioritize-reference-files/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prioritize-reference-files", 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/HKUDS/OpenSpace.git --path benchmarks/gdpval/skills/prioritize-reference-files--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 HKUDS/OpenSpace --skill prioritize-reference-files -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install HKUDS/OpenSpace prioritize-reference-files --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/benchmarks/gdpval/skills/prioritize-reference-files .gemini/skills/prioritize-reference-files && 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 "prioritize-reference-files" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/prioritize-reference-files into .gemini/skills/prioritize-reference-files/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prioritize-reference-files", 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 HKUDS/OpenSpace prioritize-reference-filesInstalls 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 HKUDS/OpenSpace --skill prioritize-reference-files -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .github/skills && cp -r skills-src/benchmarks/gdpval/skills/prioritize-reference-files .github/skills/prioritize-reference-files && 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 "prioritize-reference-files" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/prioritize-reference-files into .github/skills/prioritize-reference-files/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prioritize-reference-files", 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 HKUDS/OpenSpace --skill prioritize-reference-files -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install HKUDS/OpenSpace prioritize-reference-files --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/benchmarks/gdpval/skills/prioritize-reference-files .opencode/skills/prioritize-reference-files && 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 "prioritize-reference-files" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/prioritize-reference-files into .opencode/skills/prioritize-reference-files/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prioritize-reference-files", 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
prioritize-reference-files- GitHub stars
- 7.7k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 515 words
- Files
- 2
- Skills in repo
- 199
- Repo updated
- First seen
- Licence
- MIT
At a glance
Ensures agents read and use provided reference files before searching or fabricating data
- Works in 5 steps: Scan Task Context for Reference Files → Read Reference Files First → Extract and Validate Data → …
- Tasks that involve Web search
- SKILL.md covers Purpose, Core Principle, Workflow and Anti-Patterns to Avoid, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Prioritize Reference Files is an agent skill from HKUDS/OpenSpace. Ensures agents read and use provided reference files before searching or fabricating data
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.
It sits in Documents & Office, covering Web search. The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.
When your agent uses it
- Tasks that involve Web search
Example prompts
- “Use the prioritize-reference-files skill to ensure agents read and use provided reference files before searching or fabricating data”
- “/prioritize-reference-files”
Requirements
- Python 3
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 3827781. 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 (its code samples are bash and python).
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
Prioritize Reference Files loads about 1.3k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 515 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 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 HKUDS/OpenSpace at commit 3827781, republished under its MIT licence (© HKUDS). 515 words, ~1,256 tokens.
Download SKILL.mdSave it as
.claude/skills/prioritize-reference-files/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- prioritize-reference-files
- description
- Ensures agents read and use provided reference files before searching or fabricating data
Prioritize Reference Files
Purpose
This skill ensures that when reference files are provided in task context, you MUST read and extract data from them FIRST before attempting web searches or generating synthetic data. Ignoring available structured data leads to fabricated outputs and incorrect results.
Core Principle
Reference files in context > Web search > Data fabrication (never)
Workflow
Step 1: Scan Task Context for Reference Files
Before taking any action, identify all files provided in the task context:
- Look for file attachments, uploads, or references in the task description
- Common formats:
.xlsx,.csv,.json,.pdf,.docx,.txt - Check for phrases like "attached", "provided", "reference file", "see file"
Step 2: Read Reference Files First
Use the appropriate tool to read each reference file:
# For Excel files
read_file(filetype="xlsx", file_path="path/to/file.xlsx")
# For CSV files
read_file(filetype="csv", file_path="path/to/file.csv")
# For PDF files
read_file(filetype="pdf", file_path="path/to/file.pdf")
# For JSON files
read_file(filetype="json", file_path="path/to/file.json")
# For text files
read_file(filetype="txt", file_path="path/to/file.txt")If read_file fails on .docx files (returns error, empty content, or 'unknown error'):
Fallback Approach 1: Direct zipfile/XML extraction via run_shell
# .docx files are ZIP archives containing XML; extract document.xml directly
unzip -p path/to/file.docx word/document.xml | grep -oP '(?<=<w:t>)[^<]+' | tr '\n' ' 'Or for more complete extraction:
mkdir -p /tmp/docx_extract && cd /tmp/docx_extract && unzip path/to/file.docx && cat word/document.xmlFallback Approach 2: Use shell_agent for complex extraction If direct extraction fails, delegate to shell_agent:
shell_agent(task="Extract text content from path/to/file.docx using zipfile and XML parsing")The agent will attempt multiple extraction methods and report results.
Fallback Approach 3: Verify extraction success before proceeding After any extraction method, confirm content was retrieved:
- Check that output is non-empty and contains expected document structure
- Look for familiar text from the document (headings, known phrases)
- If extraction appears incomplete, try an alternative method
- Document which method succeeded: "Content extracted using [method] after read_file failed"
Important: Never proceed to data fabrication if reference files exist but read_file fails. Always attempt at least one fallback extraction method first.
Step 3: Extract and Validate Data
After reading:
- Parse the content to understand the data structure
- Identify relevant fields/columns for your task
- Verify the data is complete and usable
- Note any limitations or missing information
Step 4: Use Reference Data as Primary Source
- Base all outputs on the reference file data
- Only supplement with web search if reference data is incomplete
- NEVER fabricate data when reference files exist
- If reference data is insufficient, explicitly state what's missing
Show full SKILL.md (186 more words)Show less
Step 5: Document Data Source
In your outputs, acknowledge the source:
- "Data sourced from [filename]"
- "Based on provided reference file: [filename]"
- This confirms you used the actual provided data
Anti-Patterns to Avoid
❌ Ignoring reference files and searching the web instead ❌ Fabricating data when structured data is available ❌ Assuming file contents without reading them ❌ Using outdated web data when current reference files exist ❌ Giving up after read_file fails without trying fallback extraction methods
Example
Task Context: "Create a property listings report. See Massabama_active_listings.xlsx for current data."
Correct Approach:
1. Read Massabama_active_listings.xlsx first
2. Extract property addresses, prices, specifications
3. Generate report using actual listing data
4. Note: "Data sourced from Massabama_active_listings.xlsx"Incorrect Approach:
1. Search web for "Massabama property listings"
2. Fabricate property data from search results
3. Create report with unverified/generated dataVerification Checklist
Before completing any task with reference files:
- I have identified all reference files in the task context
- I have read each reference file using appropriate tools
- I have extracted relevant data from the files
- My output is based on the reference file data
- I have documented the data source in my output
When Web Search is Appropriate
Only search the web when:
- Reference files don't exist for the required data
- Reference files are incomplete AND supplemental info is needed
- You need to verify or update time-sensitive information
- You explicitly state what the reference files lack
© HKUDS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in benchmarks/gdpval/skills/prioritize-reference-files of HKUDS/OpenSpace.
- SKILL.md
- .skill_id
Open the folder on GitHubat commit 3827781
Compare with similar skills
Prioritize Reference Files 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 |
|---|---|---|---|---|---|---|
| Prioritize Reference Files this skillHKUDS/OpenSpace | 7.7k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Paper Submissionbrycewang-stanford/Auto-Empirical-Research-Skills | 4.5k | — | ~3.4k | Automated safety check: Notes | Custom licence | |
| Nemo RetrieverNVIDIA/skills | 3.5k | — | ~583 | Automated safety check: Pass | Apache-2.0 | |
| Jev SEOAgriciDaniel/jev-seo | 515 | — | ~2.5k | Automated safety check: Notes | MIT | |
| Harness Useautonomous-ai/Physical-AI-Operating-System | 381 | — | ~8k | Automated safety check: Pass | Apache-2.0 | |
| IngestPrismer-AI/PrismerCloud | 1.6k | — | ~934 | Automated safety check: Pass | MIT |
Similar skills
- Official
Nemo Retriever
NVIDIA/skills
A skill your agent uses when searching, extracting, ingesting, or querying a document collection with the NeMo Retriever 26.8.1 CLI, including local LanceDB indexes and deployed Retriever services.
Jev SEO
AgriciDaniel/jev-seo
Full live SEO audit of any website from its homepage URL, powered by Jev (TypeSafe's System One model).
Harness Use
autonomous-ai/Physical-AI-Operating-System
Delegate digital work to agents on the computer paired through Harness; discover Store packages and prepare an agent when needed.
Ingest
Prismer-AI/PrismerCloud
Turn external web URLs into LLM-ready content — load + cache web pages (HQCC compression) and search the web.
Skywork Document
aiskillstore/marketplace
Generate professional documents in multiple formats (docx, pdf, html, md) from scratch or based on user files.
More from HKUDS/OpenSpace
All 199 skills in this repoAudio Track Production Workflow
HKUDS/OpenSpace
Walks through producing a master audio track plus stems in Python, from checking a reference file and timing sections by BPM to effects, a zip archive and final verification.
Cascade Failure Recovery
HKUDS/OpenSpace
Handle cascading data retrieval tool failures by falling back to embedded knowledge generation
Sandbox Code Execution Fallback
HKUDS/OpenSpace
Gives an agent a workaround when its code-execution sandbox keeps failing: save the Python script to a file and run it through the shell instead.
Code Execution Fallback
HKUDS/OpenSpace
A recovery routine for agents whose sandboxed code runner keeps failing: save the Python script to disk, then run it through the shell and read the output.
Code Execution Fallback and Path Anchoring
HKUDS/OpenSpace
Fallback ladder for failed sandboxed code runs, plus the habit of fixing the working directory first so generated files land in the right place.
Code Execution Fallback E81068
HKUDS/OpenSpace
Fallback workflow for executing Python code when executecodesandbox fails repeatedly
Related
Questions about Prioritize Reference Files
What does Prioritize Reference Files do?
Ensures agents read and use provided reference files before searching or fabricating data. Prioritize Reference Files is an agent skill from HKUDS/OpenSpace.
When should I use Prioritize Reference Files?
Prioritize Reference Files fits situations like: tasks that involve Web search.
How do I install Prioritize Reference Files in Claude Code?
Run `npx skills add HKUDS/OpenSpace --skill prioritize-reference-files -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/prioritize-reference-files in HKUDS/OpenSpace) into .claude/skills/prioritize-reference-files in your project. Claude Code loads it when a task matches its description.
How do I install Prioritize Reference Files in Codex?
Run `npx skills add HKUDS/OpenSpace --skill prioritize-reference-files -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/prioritize-reference-files in HKUDS/OpenSpace) into .agents/skills/prioritize-reference-files in your project. Codex loads it when a task matches its description.
Can I use Prioritize Reference Files 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 HKUDS/OpenSpace --skill prioritize-reference-files -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prioritize-reference-files, .gemini/skills/prioritize-reference-files, .github/skills/prioritize-reference-files and .opencode/skills/prioritize-reference-files in your project.
What does Prioritize Reference Files need to run?
SKILL.md names no scripts, command-line tools or credentials: Prioritize Reference Files is instructions for the agent only. Our summary lists: Python 3.
Does Prioritize Reference Files 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 Prioritize Reference Files 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 Prioritize Reference Files use?
Prioritize Reference Files 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 Prioritize Reference Files use?
About 1.3k tokens (SKILL.md is roughly 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 Prioritize Reference Files?
Skills that share tags, products or a category with Prioritize Reference Files: Paper Submission (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Nemo Retriever (NVIDIA/skills, 3.5k stars), Jev SEO (AgriciDaniel/jev-seo, 515 stars) and Harness Use (autonomous-ai/Physical-AI-Operating-System, 381 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Prioritize Reference Files?
HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,743 GitHub stars. The repository holds 199 skills in this directory. The repository was last updated on August 12, 2026.
Source: HKUDS/OpenSpace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.