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 agentmods add skills/seed-forge/harness-ai-kit/work-exportnpx skills add seed-forge/harness-ai-kit --skill work-exportgit clone --depth 1 https://github.com/seed-forge/harness-ai-kitWrote 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/seed-forge/harness-ai-kit/work-export)<a href="https://agentmods.dev/skills/seed-forge/harness-ai-kit/work-export"><img src="https://agentmods.dev/badge/skills/seed-forge/harness-ai-kit/work-export.svg" alt="Measured on agentmods" 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 | $0.00093 | $0.01239 |
| Opus 5 | $0.00046 | $0.00620 |
| Sonnet 5 | $0.00019 | $0.00248 |
| Haiku 4.5 | $0.00009 | $0.00124 |
Grade A, and why
work-export 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 4d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
work-export
用途
作为 work 命名空间的通用 Outflow 基座,提供从内容(Markdown / 结构化数据 / 大纲)到目标格式文档的统一导出管线。
本技能不实现格式生成逻辑,而是编排社区上游技能(docx/pdf/xlsx/pptx),提供:
- 统一的格式选择决策树
- 标准化的输出校验流程
- 与
work-markitdown(Inflow)形成闭环
依赖
- depends:
docx(md→docx)、pdf(md→pdf)、xlsx(data→xlsx)、pptx(outline→pptx) - 协作:
work-markitdown(Inflow 侧)、work-convert(格式互转) - 被依赖:
work-sc-*场景技能
适用场景
- 从 Markdown 内容导出为 Word 文档(报告、手册、合同等)
- 从 Markdown 内容导出为 PDF
- 从结构化数据导出为 Excel 表格
- 从大纲/结构导出为 PowerPoint 演示文稿
- 为
work-sc-*场景技能提供底层导出能力
不适用场景
- 需要精确格式控制的专业排版 → 直接调用社区上游
docx/pdf技能 - 文件格式互转(docx→pdf)→ 用
work-convert - 解析/读取文档内容 → 用
work-markitdown
格式选择决策树
用户需要导出什么格式?
├─ Word (.docx)
│ → 调用 docx 社区上游技能
│ → docx-js 生成 / pandoc 转换
├─ PDF (.pdf)
│ → 调用 pdf 社区上游技能
│ → reportlab 生成 / soffice 转换
├─ Excel (.xlsx)
│ → 调用 xlsx 社区上游技能
│ → openpyxl 生成
├─ PowerPoint (.pptx)
│ → 调用 pptx 社区上游技能
│ → pptxgenjs 生成
└─ 多种格式
→ 按依赖顺序:源文档 → 派生导出
→ 例:先生成 docx,再从 docx 转 pdf
工作流
Markdown → Word
- 确认 Markdown 源文件内容已确认
- 调用
docx技能生成.docx - 校验:在 Office/WPS 中打开确认格式正确
Markdown → PDF
- 确认 Markdown 源文件内容已确认
- 选择管线:
- 直接生成:
reportlab/md-to-pdf - 经 docx 中转:先生成 docx →
soffice --convert-to pdf
- 直接生成:
- 校验:渲染页面确认排版
数据 → Excel
- 确认数据源(CSV / JSON / 数据库查询结果)
- 调用
xlsx技能生成.xlsx - 校验:打开确认公式无错误、格式正确
大纲 → PowerPoint
- 确认大纲结构(标题/要点层级)
- 调用
pptx技能生成.pptx - 校验:缩略图预览确认布局
统一输出校验
每种格式导出后 MUST 执行:
| 格式 | 校验项 |
|---|---|
| docx | Office/WPS 打开无报错,标题/段落格式正确 |
| 页数正确,无截断/空白页,中文无乱码 | |
| xlsx | 公式无 #REF!/#VALUE! 错误,表头对齐 |
| pptx | 缩略图预览,文字不溢出,图片显示正常 |
与 work 生态的协作
内容 (Markdown/数据/大纲)
│
▼
work-export (本技能:内容→目标格式)
│
├─→ docx (社区上游:Word 生成)
├─→ pdf (社区上游:PDF 生成)
├─→ xlsx (社区上游:Excel 生成)
└─→ pptx (社区上游:PPT 生成)
推荐输出格式
执行完毕后按以下结构输出:
状态:✅ 成功 / ⚠️ 部分成功 / ❌ 失败
| <输入→输出文件/格式/路径> | <值/状态> | 说明 |
|---|
下一步:<可执行动作>
约束
- 不实现格式生成逻辑,完全依赖社区上游技能
- 多格式导出时按依赖顺序执行(源文档 → 派生导出)
- 每次导出后 MUST 输出校验结果和文件路径
- 中文文档默认使用思源黑体或微软雅黑
What ships with it
3 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.
- 4d ago First seen · 128 lines · 93 tokens per session scan A 58fff875d5c9
work-export is a skill published in the GitHub repository seed-forge/harness-ai-kit (21 stars, last pushed 7d ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,239 once invoked, about $0.0005 per session on Opus 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.
Other skills, from other repositories
skillshare-changelog
Generate CHANGELOG.md entry from recent commits in conventional format. Also syncs the website changelog page. Use this skill whenever the user asks to: generate a changelog, document what changed between tags, or create a new CHANGELOG entry. If you see requests like "write the changelog for v0.17", "what changed…
skillshare-update-docs
Update website docs to match recent code changes, cross-validating every flag against source. Use this skill whenever the user asks to: update documentation, sync docs with code, document a new flag or command, fix stale docs, or update the README. This skill covers all website/docs/ categories (commands, reference…
weekly-crm-report
Cleans a weekly CRM export and produces a regional sales summary. Activates when the user asks to clean a CRM export, deduplicate sales rows, calculate regional totals, or generate a weekly sales report from a CSV.
cloudbase-document-database-in-wechat-miniprogram
Use CloudBase document database WeChat MiniProgram SDK to query, create, update, and delete data. Supports complex queries, pagination, aggregation, and geolocation queries.
ulw-research
Team-first maximum-saturation research orchestration. ALWAYS asks which final format to render (PDF+DOCX default), then stands up a max-size cooperating team (teamcreate): one member per axis plus skeptic/red-team members for ultradebate/hyperdebate cross-critique, explore/librarian lanes, live journaling, an EXPAND…
dashscope
DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use when generating images via Qwen-Image, narrating via Qwen-TTS, or transcribing with word-level timestamps via Qwen-ASR.