Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/iflow-ai/iflow-skillsnpx agentmods add skills/iflow-ai/iflow-skills/reportsWrote 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/iflow-ai/iflow-skills/reports)<a href="https://agentmods.dev/skills/iflow-ai/iflow-skills/reports"><img src="https://agentmods.dev/badge/skills/iflow-ai/iflow-skills/reports/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/iflow-ai/iflow-skills/reports"><img src="https://agentmods.dev/badge/skills/iflow-ai/iflow-skills/reports.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 | $0.00059 | $0.05744 |
| Opus 5 | $0.00030 | $0.02872 |
| Sonnet 5 | $0.00012 | $0.01149 |
| Haiku 4.5 | $0.00006 | $0.00574 |
Grade A, and why
happy-notes-reports 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 12d 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 — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reports (内容生成)
Prerequisites: see root
../SKILL.mdfor setup, credentials, andiflow_api()helper.
基于知识库中选定的文件，生成多种类型的内容产出。这是 iflow 的核心差异化能力。
完整数据结构和接口参数详见 references/api.md。
十二种产出类型
| type 值 | 产出类型 | 说明 | 预估耗时 | 等待策略 |
|---|---|---|---|---|
PDF |
PDF 报告 | 生成 PDF 格式报告 | 10-20分钟 | 异步，不阻塞 |
DOCX |
Word 报告 | 生成 Word 格式报告 | 10-20分钟 | 异步，不阻塞 |
MARKDOWN |
Markdown 报告 | 生成 Markdown 格式报告（支持 7 种类型变体，见「query 内容传达指引」） | 10-20分钟 | 异步，不阻塞 |
PPT |
演示文稿 | 支持 preset："商务" / "卡通" |
15-30分钟 | 异步，不阻塞 |
XMIND |
思维导图 | — | 15-30分钟 | 异步，不阻塞 |
PODCAST |
播客 | 支持时长（3-30 分钟）、单/双口、10 种音色、调性（由 query 描述，LLM 自动推断） | 10-20分钟 | 异步，不阻塞 |
VIDEO |
视频（有声 PPT 讲解） | TTS 旁白 + PPT 页面演示 | 15-30分钟 | 异步，不阻塞 |
HHVIDEO |
AI 视频（v2 新增） | 支持 T2V / I2V / Seed 三种模式，通过 videoConfig 显式配置 |
5-15分钟 | 异步，不阻塞 |
QUIZ |
多选题（v2 新增） | 自动生成 N 道题，含 4 选项 + 正确答案 + 解释；题量/难度由 query 描述 | 5-10分钟 | 异步，不阻塞 |
GRAPH |
信息图（v2 新增） | 单张数据可视化图；风格（minimal/cartoon/cool）+ 尺寸（方/横/竖）由 query 描述 | 5-10分钟 | 异步，不阻塞 |
TRANSLATION |
文件翻译（v2 新增） | 支持 PDF/DOCX/MD/TXT 互译，10 种语言；源/目标语言由 query 描述 | 5-20分钟 | 异步，不阻塞 |
PPT_EDIT |
PPT 增量编辑（v2 新增） | 基于已有 PPT + 用户编辑指令做修改；依赖前序 PPT 上下文 | 10-20分钟 | 异步，不阻塞 |
注意:
DOCX/MARKDOWN都是报告的不同输出格式。用户没指定格式时默认使用
VIDEOvsHHVIDEO：VIDEO是 TTS 旁白 + PPT 页面演示（"有声 PPT"）；HHVIDEO是真正的 AI 视频生成。用户说"做个视频"时倾向于HHVIDEO；说"配音演示"、"讲解视频"时用VIDEO。
意图识别与参数映射
| 用户说的 | type | preset | 说明 |
|---|---|---|---|
| "生成报告"/"写份报告" | PDF |
— | 未指定格式时默认 PDF |
| "导出 Word" | DOCX |
— | — |
| "生成 Markdown 报告" | MARKDOWN |
— | — |
| "写篇博客"/"做篇公众号文章" | MARKDOWN |
— | 通过 query 完整传达"博客/公众号"等关键词，下游 LLM 会识别为 blog_article 类型 |
| "深度研究"/"调研报告" | MARKDOWN |
— | 下游识别为 deep_research 类型 |
| "文献综述"/"文献回顾" | MARKDOWN |
— | 下游识别为 literature_review 类型 |
| "审稿意见"/"论文 review" | MARKDOWN |
— | 下游识别为 shadow_review 类型 |
| "高管简报"/"执行摘要"/"给老板看的总结" | MARKDOWN |
— | 下游识别为 executive_summary 类型 |
| "学习指南"/"教学材料"/"考点整理" | MARKDOWN |
— | 下游识别为 study_guide 类型 |
| "按 SWOT 写"/"分 5 段" | MARKDOWN |
— | 下游识别为 custom_format 自定义结构 |
| "做个PPT"/"生成演示文稿" | PPT |
"商务" |
默认商务风格 |
| "做个活泼的PPT"/"卡通风格" | PPT |
"卡通" |
关键词触发 |
| "生成播客"/"做个播客" | PODCAST |
— | 用户提到的时长/音色/单双口/调性需完整保留在 query |
| "做个 10 分钟的女声轻松风格播客" | PODCAST |
— | query 必须包含"10 分钟""女声""轻松"，不能简化 |
| "生成思维导图"/"画个脑图" | XMIND |
— | — |
| "生成视频"/"做个视频" | HHVIDEO |
— | 默认走 HHVIDEO（AI 视频）；如果用户明确说"讲解视频/配音演示"才用 VIDEO |
| "做个 AI 视频"/"生成短视频" | HHVIDEO |
— | 默认 T2V 文生视频，传 --video-images 切 I2V/Seed |
| "用这几张图生成视频" | HHVIDEO |
— | 传 --video-images --video-image-type reference（I2V） |
| "用这张图作为开头做视频" | HHVIDEO |
— | 传 --video-images --video-image-type first_frame（Seed） |
| "出几道题"/"做个测验"/"考考我" | QUIZ |
— | 用户说的题量/难度（"10 道"/"难一点"）必须完整传到 query |
| "做张信息图"/"数据可视化" | GRAPH |
— | 用户说的风格（卡通/极简/酷炫）和尺寸（方/横/竖）必须完整传到 query |
| "翻译这个文档"/"译成英文"/"中译英" | TRANSLATION |
— | 用户说的源/目标语言必须完整传到 query |
| "修改这页 PPT"/"重做第 N 页" | PPT_EDIT |
— | 依赖前序 PPT 上下文，需要 Agent 知道当前会话已经生成过 PPT |
| "同时生成报告和PPT" | 多个 | — | 并行提交 |
| "帮我总结一下" | PDF |
— | 总结 = 报告，通过 query 描述总结要求 |
| "对比分析这两篇论文" | PDF |
— | 通过 query 传达分析要求 |
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.
- 12d ago First seen · 365 lines · 59 tokens per session scan A dacae0bf7c52
happy-notes-reports is a skill published in the GitHub repository iflow-ai/iflow-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 5,744 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.