Extract
alirezarezvani/claude-skills
Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples.
Process and analyze user-uploaded file references, extract key information, and provide application recommendations.
MITAuto-check passed
Install File Reference
$ npx skills add VanGong1999/screen-creative-skills --skill file-reference -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VanGong1999/screen-creative-skills file-reference --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/VanGong1999/screen-creative-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/english-version/category/tools/file-reference .claude/skills/file-reference && 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 "file-reference" agent skill from https://github.com/VanGong1999/screen-creative-skills/tree/master/english-version/category/tools/file-reference into .claude/skills/file-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "file-reference", 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/VanGong1999/screen-creative-skills/tree/master/english-version/category/tools/file-referenceType 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 VanGong1999/screen-creative-skills --skill file-reference -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VanGong1999/screen-creative-skills file-reference --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VanGong1999/screen-creative-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/english-version/category/tools/file-reference .agents/skills/file-reference && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "file-reference" agent skill from https://github.com/VanGong1999/screen-creative-skills/tree/master/english-version/category/tools/file-reference into .agents/skills/file-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "file-reference", 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 VanGong1999/screen-creative-skills --skill file-reference -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VanGong1999/screen-creative-skills file-reference --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VanGong1999/screen-creative-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/english-version/category/tools/file-reference .cursor/skills/file-reference && 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 "file-reference" agent skill from https://github.com/VanGong1999/screen-creative-skills/tree/master/english-version/category/tools/file-reference into .cursor/skills/file-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "file-reference", 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/VanGong1999/screen-creative-skills.git --path english-version/category/tools/file-reference--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 VanGong1999/screen-creative-skills --skill file-reference -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VanGong1999/screen-creative-skills file-reference --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VanGong1999/screen-creative-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/english-version/category/tools/file-reference .gemini/skills/file-reference && 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 "file-reference" agent skill from https://github.com/VanGong1999/screen-creative-skills/tree/master/english-version/category/tools/file-reference into .gemini/skills/file-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "file-reference", 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 VanGong1999/screen-creative-skills file-referenceInstalls 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 VanGong1999/screen-creative-skills --skill file-reference -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VanGong1999/screen-creative-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/english-version/category/tools/file-reference .github/skills/file-reference && 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 "file-reference" agent skill from https://github.com/VanGong1999/screen-creative-skills/tree/master/english-version/category/tools/file-reference into .github/skills/file-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "file-reference", 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 VanGong1999/screen-creative-skills --skill file-reference -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VanGong1999/screen-creative-skills file-reference --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VanGong1999/screen-creative-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/english-version/category/tools/file-reference .opencode/skills/file-reference && 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 "file-reference" agent skill from https://github.com/VanGong1999/screen-creative-skills/tree/master/english-version/category/tools/file-reference into .opencode/skills/file-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "file-reference", 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
file-reference- GitHub stars
- 445
- Used in
- 1 other repo
- Token cost
- ~1.2k tokens
- SKILL.md length
- 320 words
- Files
- 2 (incl. references)
- Skills in repo
- 62
- Repo updated
- First seen
- Licence
- MIT
At a glance
Process and analyze user-uploaded file references, extract key information, and provide application recommendations.
- SKILL.md covers Functionality, Usage Scenarios, Supported Reference Formats and Core Capabilities, plus 6 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
File Reference is an agent skill from VanGong1999/screen-creative-skills. Process and analyze user-uploaded file references, extract key information, and provide application recommendations. Suitable for parsing @symbol references, natural language references, and extracting vertical short drama planning information
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/examples.md`). Compatibility notes: Claude Code 1.0+
The repository describes itself as: Skills for Film and Television Creation Agents|31 个影视创作评估策划Agent Skills｜AI影视自动化工作流｜竖屏短剧长剧IP改编｜情节题材提炼｜剧本小说IP创作策划评估｜人物小传｜拉片人物剧集故事五元素分析｜大纲生成｜. The licence is MIT.
Example prompts
- “/file-reference”
Requirements
- Compatibility (from SKILL.md): Claude Code 1.0+
- Pre-approved tools (allowed-tools): Read
What it can do on your machine
Read from SKILL.md and the folder at commit 6ced54f. 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:
Read
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.
Compatibility
Claude Code 1.0+
From compatibility in the SKILL.md frontmatter.
Context cost
File Reference loads about 1.2k tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 65 tokens; SKILL.md has 320 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 VanGong1999/screen-creative-skills at commit 6ced54f, republished under its MIT licence (© VanGong1999). 320 words, ~1,245 tokens.
Download SKILL.mdSave it as
.claude/skills/file-reference/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- file-reference
- description
- Process and analyze user-uploaded file references, extract key information, and provide application recommendations. Suitable for parsing @symbol references, natural language references, and extracting vertical short drama planning information
- allowed-tools
- Read
- compatibility
- Claude Code 1.0+
- category
- tools
- version
- 2.1.0
- last_updated
- 2026-01-11
- license
- MIT
- maintainer
- Gong Fan
- model
- opus
File Reference Parsing Expert
Functionality
Process and analyze user-uploaded file references, extract key information, and provide structured output with application recommendations.
Usage Scenarios
- Parse local files or URL links referenced by users in conversations
- Extract core information from files to support agent understanding and utilization of file content
- Provide file content application recommendations for short drama planning to assist creation
- Automate processing of various file references to improve workflow efficiency
Supported Reference Formats
@Symbol References
@file1- Document file reference@image1- Image file reference@pdfDocument- PDF document reference
Natural Language References
- "First file", "Second file" - Sequential references
- "Most recently uploaded file" - Time-based references
- "That image file" - Type-based references
Core Capabilities
- File Reference Parsing: Accurately identify and parse various file reference formats (@symbols, natural language)
- Content Extraction: Extract key information and core content from referenced files
- Structured Output: Present file content in a structured format for easy understanding and utilization
- Application Recommendations: Provide specific application recommendations for short drama planning based on file content
Input Requirements
- File Reference: File reference provided by user (e.g.,
@draft.docxor "the image just uploaded") - Analysis Requirements (optional): Specify specific information to extract from the file or analysis focus
Output Format
## File Reference Analysis Report
### Reference Summary
- Reference Type: [@symbol reference/natural language reference]
- File Type: [document/image/PDF/other]
- File Name: [file name]
### File Content Overview
[Briefly describe the main content and core information of the file]
### Key Information Extraction
1. [Key information point 1]
2. [Key information point 2]
3. [Key information point 3]
### Short Drama Planning Application Recommendations
1. **Character Design**: [How to use for character role design]
2. **Plot Design**: [How to use for plot structure planning]
3. **Commercialization**: [How to use for commercial element design]Constraints
- Ensure accuracy and comprehensiveness of file content analysis
- Focus on content relevant to vertical short drama planning, avoid irrelevant information
- Provide specific, actionable application recommendations to assist user creation decisions
- Avoid introducing any hallucinations or false information in output
Examples
See {baseDir}/references/examples.md for more detailed examples:
examples.md- Contains detailed examples of reference parsing and application recommendations for various file types (documents, images, PDFs, etc.)
Detailed Documentation
See {baseDir}/references/examples.md for detailed guidance and cases on file reference parsing.
Version History
| Version | Date | Changes |
|---|---|---|
| 2.1.0 | 2026-01-11 | Optimized description field; changed model to opus; optimized descriptions for functionality, supported reference formats, core capabilities, input requirements, and output format; added usage scenarios, constraints, examples, and detailed documentation sections |
| 2.0.0 | 2026-01-11 | Restructured according to official specifications |
| 1.0.0 | 2026-01-10 | Initial version |
© VanGong1999, 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 (references) in english-version/category/tools/file-reference of VanGong1999/screen-creative-skills.
- SKILL.md
- references/examples.md
Open the folder on GitHubat commit 6ced54f
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in VanGong1999/screen-creative-skills, which our catalogue first saw on October 7, 2026.
Compare with similar skills
File Reference 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 |
|---|---|---|---|---|---|---|
| File Reference this skillVanGong1999/screen-creative-skills | 445 | 1 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Extractalirezarezvani/claude-skills | 28k | — | ~1.4k | Automated safety check: Pass | MIT | |
| File Uploadsdavila7/claude-code-templates | 32k | 4 repos | ~238 | Automated safety check: Pass | MIT | |
| File Upload Accessibilitythedaviddias/Front-End-Checklist | 74k | — | ~418 | Automated safety check: Pass | MIT | |
| Brand Extractnexu-io/open-design | 100k | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Design Extractnexu-io/open-design | 100k | — | ~549 | Automated safety check: Pass | Apache-2.0 |
Similar skills
File Uploads
davila7/claude-code-templates
Expert at handling file uploads and cloud storage. An agent skill from davila7/claude-code-templates.
File Upload Accessibility
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing templates, rendered HTML, or shared components related to Make file uploads accessible.
Brand Extract
nexu-io/open-design
Extract a complete Brand Kit from a live website by driving the in-app browser.
Design Extract
nexu-io/open-design
Extract design tokens (color / typography / spacing) from imported source code, screenshots, or Figma exports into the canonical token bag token-map consumes.
Kg Extract
ruvnet/ruflo
Extract entities and relations from source files to build a knowledge graph
More from VanGong1999/screen-creative-skills
All 62 skills in this repoDrama Creator
VanGong1999/screen-creative-skills
Create vertical short drama scripts covering macro construction, episode writing, precise optimization, and creative ideation using Emotional Spring Theory.
Drama Workflow
VanGong1999/screen-creative-skills
Orchestrate the full plot-point dramatic function analysis pipeline — text preprocessing, parallel segment analysis, result integration, and report generation — for long-form story content.
Novel Evaluator
VanGong1999/screen-creative-skills
Evaluate and score story text across market potential, innovation attributes, and content highlights dimensions, producing structured scoring reports with development recommendations.
Script Evaluator
VanGong1999/screen-creative-skills
Evaluate film and TV scripts across ideological, artistic, and entertainment value dimensions, producing structured scoring reports with follow-up recommendations.
Character Profile
VanGong1999/screen-creative-skills
基于故事文本分析人物特征，生成详细的人物小传。适用于深度理解故事人物设定、为演员塑造角色提供参考、为剧本创作建立人物档案
Story Five Elements
VanGong1999/screen-creative-skills
Analyze five core story elements — genre type, story summary, character biographies, character relationships, and major plot points — producing a structured comprehensive report with optional mind…
Questions about File Reference
What does File Reference do?
Process and analyze user-uploaded file references, extract key information, and provide application recommendations. File Reference is an agent skill from VanGong1999/screen-creative-skills. Process and analyze user-uploaded file references, extract key information, and provide application recommendations.
How do I install File Reference in Claude Code?
Run `npx skills add VanGong1999/screen-creative-skills --skill file-reference -a claude-code`. Or copy the skill folder (english-version/category/tools/file-reference in VanGong1999/screen-creative-skills) into .claude/skills/file-reference in your project. Claude Code loads it when a task matches its description.
How do I install File Reference in Codex?
Run `npx skills add VanGong1999/screen-creative-skills --skill file-reference -a codex`. Or copy the skill folder (english-version/category/tools/file-reference in VanGong1999/screen-creative-skills) into .agents/skills/file-reference in your project. Codex loads it when a task matches its description.
Can I use File Reference 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 VanGong1999/screen-creative-skills --skill file-reference -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/file-reference, .gemini/skills/file-reference, .github/skills/file-reference and .opencode/skills/file-reference in your project.
What does File Reference need to run?
SKILL.md names no scripts, command-line tools or credentials: File Reference is instructions for the agent only. Its frontmatter pre-approves these tools: Read. Compatibility (from SKILL.md): Claude Code 1.0+.
Does File Reference 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 File Reference 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 File Reference use?
File Reference is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does File Reference use?
About 1.2k 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. Its references folder adds about 560 tokens, read only when the agent opens those files.
What are the alternatives to File Reference?
Skills that share tags, products or a category with File Reference: Extract (alirezarezvani/claude-skills, 28k stars), File Uploads (davila7/claude-code-templates, 32k stars), File Upload Accessibility (thedaviddias/Front-End-Checklist, 74k stars) and Brand Extract (nexu-io/open-design, 100k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains File Reference?
VanGong1999 (a GitHub user) maintains it in VanGong1999/screen-creative-skills, which has 445 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on May 26, 2026.
Source: VanGong1999/screen-creative-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.