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 A-cat-with-carrots/pm-daily-brief-skill --skill pm-daily-brief-skillgit clone --depth 1 https://github.com/A-cat-with-carrots/pm-daily-brief-skillWrote 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/a-cat-with-carrots/pm-daily-brief-skill/pm-daily-brief-skill)<a href="https://agentmods.dev/skills/a-cat-with-carrots/pm-daily-brief-skill/pm-daily-brief-skill"><img src="https://agentmods.dev/badge/skills/a-cat-with-carrots/pm-daily-brief-skill/pm-daily-brief-skill/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/a-cat-with-carrots/pm-daily-brief-skill/pm-daily-brief-skill"><img src="https://agentmods.dev/badge/skills/a-cat-with-carrots/pm-daily-brief-skill/pm-daily-brief-skill.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 | $0.00207 | $0.05871 |
| Opus 5 | $0.00103 | $0.02936 |
| Sonnet 5 | $0.00041 | $0.01174 |
| Haiku 4.5 | $0.00021 | $0.00587 |
Grade A, and why
pm-daily-brief scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM Daily Brief
为 AI 产品经理生成每日情报简报。目标读者: 你自己。目标用途: 30 分钟内吸收当天产品/技术/趋势信号,辅助产品决策。
触发与定位
用户每天手动调一次。每次都生成"当天"的报告(以系统当前日期为准,从 CLAUDE.md 注入或 date 命令获取)。
不是通用新闻聚合器。是给一个正在做 AI 产品的 PM 看的精炼简报 — 信号优先,噪音少。
输出语境
报告是写给单一用户(你自己)看的私人备忘,不是发布物。可以:
- 直接用真实产品名/项目名(
[Project-A]这种占位是 sample 公开版才用) - 在
🎯 今天具体动作字段里 reference 用户具体文件路径或 repo - 在观察段里 reference 用户在做什么
仅当用户表示要分享报告(推 GitHub / 发同事)时, 用 sed 批量脱敏成占位符。
工作流
按顺序执行下列步骤。每步给用户一行进度更新(如"抓取 ProductHunt..."),保持简短。
Step 1: 确认日期与输出路径
- 日期: 优先用 CLAUDE.md 注入的
currentDate,fallback 到date +%Y-%m-%d(bash,跨平台)。Windows-only 环境也可用 PowerShellGet-Date -Format yyyy-MM-dd。若两者差超过 12 小时(跨午夜调用), 显式问用户用哪个日期。 - 输出:
D:\hrdai\daily-input\YYYY-MM-DD.md - 覆盖策略: 文件已存在直接覆盖, 不要问用户、不要 diff (用户每天调一次, 同日重跑就是想要新版本)。Step 8 汇报时若覆盖了同日旧版, 一句话提示"(覆盖了 N 分钟前的同日报告)"。
记录 START_TS=$(date +%s),Step 8 计算抓取耗时。
Step 2: 抓取三源(WebFetch 优先,多 URL 重试)
默认用 WebFetch,不要用 /browse。 实测 (2026-05-06):
- ProductHunt 首页被 Cloudflare 挡 403,headless browser 进不去。WebFetch 走 leaderboard URL 可绕过。
- GitHub Trending 用 browse 抓回的 text 99% 是导航菜单噪音。WebFetch 输出干净 10 倍。
- HN 两种都行,WebFetch 更快。
并行抓三源(同一回合发三个 WebFetch 调用):
- ProductHunt 当日 leaderboard
- URL:
https://www.producthunt.com/leaderboard/daily/YYYY/M/D(注意月份不补零, e.g./2026/5/6) - prompt 要求: 每个产品返回名称、tagline、upvotes、tags、PH 链接、产品官网链接(从详情页抓), top 20。
- URL:
- GitHub Trending (daily)
- URL:
https://github.com/trending?since=daily - prompt 要求: 每个 repo 返回 owner/repo、完整 GitHub URL、描述、语言、总 stars、当日 stars。明确要求"不要包含导航菜单或语言选择器" — 否则 WebFetch 也可能塞导航。Top 25。
- URL:
- Hacker News 首页
- URL:
https://news.ycombinator.com/ - prompt 要求: 标题、分数、评论数、外链 URL、域名、HN 讨论页 URL。Top 30。
- URL:
Fallback (按顺序试,/browse 已确认无效不再用):
| 源 | 主路径 | Fallback 1 | Fallback 2 |
|---|---|---|---|
| PH | /leaderboard/daily/Y/M/D |
homepage / |
前一日 leaderboard (慢一天数据 > 没数据) |
| GH | /trending?since=daily |
/trending (无 since) |
/trending?since=weekly (退一档) |
| HN | / |
/news?p=1 |
/newest |
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 · 342 lines · 207 tokens per session scan A 7f8ab2557efe
pm-daily-brief is a skill published in the GitHub repository A-cat-with-carrots/pm-daily-brief-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 207 tokens to every session and 5,871 once invoked, about $0.0010 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
ai-pm-atom-lesson
A tool for teaching one small AI product-management concept through a standalone interactive web page. The page includes definitions, sources, an example project, questions, and an interactive demonstration.
social-post
A workflow for planning, writing, publishing, and evaluating social-media posts in the user's established voice. It covers Facebook, Instagram, YouTube, Threads, and X, including selected comment operations.
comfyui
Drive a local ComfyUI install for image, video, and audio generation via its HTTP API. Use WHENEVER generating, rendering, or editing images/video/audio/hero assets with ComfyUI, Z-Image, Ideogram, FLUX, LTX, Wan, or when building, parameterizing, or running ComfyUI workflows. Covers the API client, workflow JSON…
minimax-h3
Use when writing or debugging prompts for MiniMax H3 (Hailuo 3) video-with-audio generation, running the open weights locally in ComfyUI, choosing a quant or an acceleration LoRA for the VRAM you have, wiring reference-to-video with images, video or audio, or when a generated clip produces gibberish speech, drifts off…
hue
Meta-skill that generates new design language skills. Works on Claude Code and Codex. Use when the user says 'create a design skill', 'generate design language', 'new design system skill', 'design skill inspired by X', 'design skill from this screenshot', '/hue', or 'use hue'. Also triggers for 'remix my design skill'…
daily-briefing
Search for today's latest AI news and create/update a comprehensive briefing in Notion, with optional Obsidian vault publishing for graph visualization.