Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add GongLingRui/screen-creative-skills --skill file-referencegit clone --depth 1 https://github.com/GongLingRui/screen-creative-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gonglingrui/screen-creative-skills/file-reference)<a href="https://agentmods.dev/skills/gonglingrui/screen-creative-skills/file-reference"><img src="https://agentmods.dev/badge/skills/gonglingrui/screen-creative-skills/file-reference/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gonglingrui/screen-creative-skills/file-reference"><img src="https://agentmods.dev/badge/skills/gonglingrui/screen-creative-skills/file-reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.01201 |
| Opus 5 | $0.00022 | $0.00600 |
| Sonnet 5 | $0.00009 | $0.00240 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
file-reference scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
86% identical to drama-evaluator — 159 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
文件引用解析专家
功能
处理和分析用户上传的文件引用，提取关键信息并提供结构化输出与应用建议。
使用场景
- 解析用户在对话中引用的本地文件或URL链接。
- 从文件中提取核心信息，支持智能体理解和利用文件内容。
- 为短剧策划提供文件内容的应用建议，辅助创作。
- 自动化处理各类文件引用，提升工作流效率。
支持的引用格式
@符号引用
@文件1- 文档文件引用@图片1- 图片文件引用@pdf文档- PDF文档引用
自然语言引用
- "第一个文件"、"第二个文件" - 序号引用
- "最新上传的文件" - 时间引用
- "那个图片文件" - 类型引用
核心能力
- 文件引用解析: 准确识别和解析各种文件引用格式（@符号、自然语言）。
- 内容提取: 从引用的文件中提取关键信息和核心内容。
- 结构化输出: 将文件内容以结构化方式呈现，便于理解和利用。
- 应用建议: 针对文件内容提供在短剧策划中的具体应用建议。
输入要求
- 文件引用: 用户提供的文件引用（如
@剧本初稿.docx或 "刚刚上传的图片"）。 - 分析需求（可选）: 指定需要从文件中提取的特定信息或分析重点。
输出格式
## 文件引用分析报告
### 引用摘要
- 引用类型: [@符号引用/自然语言引用]
- 文件类型: [文档/图片/PDF/其他]
- 文件名称: [文件名]
### 文件内容概览
[简要描述文件的主要内容和核心信息]
### 关键信息提取
1. [关键信息点1]
2. [关键信息点2]
3. [关键信息点3]
### 短剧策划应用建议
1. **人物设定**: [如何用于人物角色设计]
2. **情节设计**: [如何用于情节结构规划]
3. **商业化**: [如何用于商业化元素设计]
约束条件
- 确保文件内容分析的准确性和全面性。
- 重点关注与竖屏短剧策划相关的内容，避免无关信息。
- 提供具体、可操作的应用建议，辅助用户创作决策。
- 避免在输出中引入任何幻觉或不实信息。
示例
参见 {baseDir}/references/examples.md 目录获取更多详细示例:
examples.md- 包含各种文件类型（如文档、图片、PDF）引用解析和应用建议的详细示例。
详细文档
参见 {baseDir}/references/examples.md 获取关于文件引用解析的详细指导与案例。
版本历史
| 版本 | 日期 | 变更 |
|---|---|---|
| 2.1.0 | 2026-01-11 | 优化 description 字段，使其更精简并符合命令式语言规范；模型更改为 opus；优化功能、支持的引用格式、核心能力、输入要求、输出格式的描述，使其更符合命令式语言规范；添加使用场景、约束条件、示例和详细文档部分。 |
| 2.0.0 | 2026-01-11 | 按官方规范重构 |
| 1.0.0 | 2026-01-10 | 初始版本 |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 127 lines · 43 tokens per session scan A fb5a556bd911
file-reference is a skill published in the GitHub repository GongLingRui/screen-creative-skills (393 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,201 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to drama-evaluator, differing in 159 lines, and is treated as a copy.
Other skills, from other repositories
voice-extractor
Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta function-word vector, MATTR lexical diversity, sentence-length burstiness, Biber Dimension-1 register…
press-clip
Turn a live article URL into a press clip that looks like the real coverage — the publication's own logo, fonts, photos and layout kept intact, the ads and clutter removed, and (for a roundup) just the client's section. Renders to PDF. You inspect each site and tailor the removal; the bundled script carries no…
a0-development
Development guide for extending Agent Zero from current source and DOX. Use for framework architecture, tools, extensions, API/WebUI handlers, agent profiles, prompts, skills, projects, runtime boundaries, and contribution workflow. Load the focused reference files before giving implementation guidance.
frontmcp-development
Use when building any FrontMCP server component other than a tool (for tools, use create-tool). Covers @Resource static resources and parameterized URI templates; @Prompt reusable prompts (RAG, multi-turn); @Provider singleton dependency-injection providers (database pools, API clients); @Agent autonomous LLM agents…
catalog-collection
Catalog and classify materials using standard library systems. Covers descriptive cataloging, subject headings, call number assignment using Dewey Decimal and Library of Congress Classification, MARC record basics, shelf organization, and authority control for consistent access points. Use when organizing a personal…
build-parameterized-report
Create parameterized Quarto or R Markdown reports that can be rendered with different inputs to generate multiple variations. Covers parameter definitions, programmatic rendering, and batch generation. Use when generating the same report for different departments, regions, or time periods; creating client-specific…