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 endearqb/endearqb-skills --skill endearqb-lab-report-writergit clone --depth 1 https://github.com/endearqb/endearqb-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/endearqb/endearqb-skills/endearqb-lab-report-writer)<a href="https://agentmods.dev/skills/endearqb/endearqb-skills/endearqb-lab-report-writer"><img src="https://agentmods.dev/badge/skills/endearqb/endearqb-skills/endearqb-lab-report-writer/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/endearqb/endearqb-skills/endearqb-lab-report-writer"><img src="https://agentmods.dev/badge/skills/endearqb/endearqb-skills/endearqb-lab-report-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00256 | $0.05906 |
| Opus 5.5 | $0.00102 | $0.02362 |
| Sonnet 5.5 | $0.00051 | $0.01181 |
| Haiku 4.5 | $0.00026 | $0.00591 |
Grade A, and why
lab-report-writer 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lab Report Writer — 期刊风格实验报告撰写 Skill
概览
本skill覆盖四类场景：理工科实验课、科研论文级记录、工程技术报告、竞赛展示报告。
核心流程：信息采集 → 文献搜索 → Python自动验证 → 撰写结构化内容 → 生成HTML报告
第一步：信息采集与场景识别
识别场景类型
| 场景 | 典型特征 | 报告侧重 |
|---|---|---|
| 实验课报告 | 有实验目的、操作步骤、数据表格 | 规范结构、误差分析、结论 |
| 科研记录 | 有假设、方法对比、统计分析 | 方法严谨性、数据可重复性 |
| 工程技术报告 | 有设计参数、测试标准、性能指标 | 工程可行性、指标达标情况 |
| 竞赛展示 | 有创新点、视觉冲击需求 | 清晰叙事、高质量图表 |
必须从用户处收集的信息
最小信息集（必须有）：
- 实验/项目标题
- 实验目的或研究问题
- 实验方法或操作步骤（文字描述即可）
- 主要结果（数据或文字描述）
增强信息（有则收集）：
- 原始数据表格（CSV、手工记录等）
- 计算公式和推导过程
- 参考文献列表
- 实验装置或流程图描述
- 误差来源分析
- 作者、机构、日期等元数据
信息不完整时的处理策略
- 数据缺失：跳过图表，用文字表述结果，在报告中标注"[图表：数据待补充]"
- 公式缺失：根据领域知识推断，并在报告中说明假设
- 参考文献缺失：生成报告，提醒用户补充
- 元数据缺失：使用占位符（如"[作者姓名]"、"[日期]"）
第一步（补）：生成前确认选项
完成信息采集、场景识别后，在开始任何生成之前，必须调用 ask_user_input 工具向用户确认核心选项（用自然语言简短说明后紧接着调用工具，不要纯文字罗列）。该工具单次最多 3 个问题，因此只询问下表 3 个核心问题；其余两项按默认执行，并在调用前一句话告知"默认仅 HTML、不启用内联编辑，如需更改可直接说明"。
| 问题（类型） | 选项 | 默认 | 变量 → 影响 |
|---|---|---|---|
| 文档模式 (single) | 长文档（分章节，推荐）/ 单文件 | 长文档 | MODE_LONG：false→单文件 report-body.html+--body |
| 可视化内容 (multi) | SVG 流程图 / Chart.js 图表 | 全选 | NEED_SVG/NEED_CHART：false→跳过对应文件与占位符 |
| 报告色彩主题 (single) | 暖墨纸/午夜藏青/净白简约/橄榄学报/砖红工程/石墨极简 | 暖墨纸 | THEME：非默认→加 --theme <值> |
默认项（不询问，用户主动要求才启用）： 附加输出默认仅 HTML（要 Markdown 草稿 → NEED_MD=true，另出 .md 一同 present_files）；HTML 内联编辑默认关闭（要编辑 → EDITABLE=true，加 --editable）。
数据验证跳过（无任何数值）时，
build_html.py另加--no-verify-panel。
主题映射与注入
主题 CSS 完全由 build_html.py 的 --theme 参数处理，Claude 无需读取或内联任何 CSS。THEME=default 时省略该参数，否则加 --theme <值>。
| 用户选项 | --theme |
用户选项 | --theme |
|
|---|---|---|---|---|
| 暖墨纸（默认） | 省略 | 橄榄学报 | olive |
|
| 午夜藏青（深色） | dark |
砖红工程 | engineering |
|
| 净白简约 | clean |
石墨极简 | graphite |
用户在
ask_user_input之前已指定主题时，"报告色彩主题"一题的默认高亮改为对应项。完整主题注入说明见references/html-build-guide.md；仅自定义非预置风格时才读style-constitution.md。
第二步：Python数据自动验证
触发判断
| 情形 | 操作 |
|---|---|
| 用户上传CSV文件 | 调用 scripts/auto_verify.py 自动解析并验证 |
| 用户粘贴表格数据（Markdown表格/空格分隔/逗号分隔） | 写入临时CSV，同上处理 |
| 用户提供了具体数值和公式 | 生成专项验证脚本并运行 |
| 用户只有文字描述、无任何数值 | 跳过Python验证，在 build_html.py 命令中添加 --no-verify-panel（不渲染验证面板） |
What ships with it
12 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.
- assets/report.css 20 KB
- assets/report.js 16 KB runs code
- references/common-pitfalls.md 4.5 KB
- references/gbt7714-reference-guide.md 6.3 KB
- references/html-build-guide.md 4.6 KB
- references/html-template.md 9.5 KB
- references/style-constitution.md 15 KB
- references/svg-flowchart-template.md 14 KB
- references/swd-chartjs-examples.md 6.6 KB
- scripts/auto_verify.py 18 KB runs code
- scripts/build_html.py 27 KB runs code
- scripts/verify_data.py 6.5 KB runs code
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.
- 2mo ago First seen · 371 lines · 256 tokens per session scan A fd6858f413d3
lab-report-writer is a skill published in the GitHub repository endearqb/endearqb-skills (19 stars, last pushed 2mo ago), licensed MIT. It adds 256 tokens to every session and 5,906 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
lab-report-writer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lab-report-writerendearqb/endearqb-skills | Skill | 19 | 2mo ago | MIT | A | 256 | Claude Code, Codex |
| cardputer-buddyanthropics/claude-plugins-official | Skill | 46k | today | Apache-2.0 | A | 109 | Claude Code |
| migrate-to-rustgoogle/skills | Skill | 23k | today | Apache-2.0 | A | 166 | Claude Code, Codex |
| pdfagentscope-ai/QwenPaw | Skill | 37k | yesterday | Apache-2.0 | A | 95 | Claude Code, Codex |
| ink-custom-brush-builderandroid/skills | Skill | 10k | 2d ago | Apache-2.0 | A | 159 | Claude Code |
| readtw93/Waza | Skill | 7.5k | 5d ago | MIT | A | 61 | Claude Code |
| docx-comment-replyforyourhealth111-pixel/Vibe-Skills | Skill | 3.8k | today | Apache-2.0 | A | 39 | Claude Code, Codex |