LobsterAI is an open-source desktop AI agent that operates files, commands, browsers, documents, spreadsheets, slides, messaging channels, and scheduled jobs in a user's working environment. It supports office work, research, and custom multi-agent workflows, while catalogue add-ons extend the agent with additional skills and workflows.
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 netease-youdao/LobsterAI --skill daily-trendinggit clone --depth 1 https://github.com/netease-youdao/LobsterAIWrote 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/netease-youdao/lobsterai/daily-trending)<a href="https://agentmods.dev/skills/netease-youdao/lobsterai/daily-trending"><img src="https://agentmods.dev/badge/skills/netease-youdao/lobsterai/daily-trending/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/netease-youdao/lobsterai/daily-trending"><img src="https://agentmods.dev/badge/skills/netease-youdao/lobsterai/daily-trending.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 | $0.00043 | $0.00617 |
| Opus 5 | $0.00022 | $0.00309 |
| Sonnet 5 | $0.00009 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
daily-trending 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 13d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- daily-trending — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daily Trending
Fetch today's trending topics by scraping data from various platforms via tophub.today.
Data Collection
Multi-Platform Trending Lists
Fetch trending lists from the following platforms on tophub.today:
- Zhihu Hot List:
/n/mproPpoq6O - Weibo Trending:
/n/KqndgxeLl9 - Baidu Real-time Hot Topics:
/n/Jb0vmloB1G - 36Kr 24-Hour Hot List:
/n/Q1Vd5Ko85R - Huxiu Hot Articles:
/n/5VaobgvAj1 - The Paper Hot List:
/n/wWmoO5Rd4E
Fetching Strategy
To avoid context overflow, fetch in batches with character limits!
Option A: Core Platforms First (Recommended)
Use web-search skill or web_fetch to fetch only 2-3 core platforms:
web_fetch("https://tophub.today/n/KqndgxeLl9") # Weibo
web_fetch("https://tophub.today/n/mproPpoq6O") # Zhihu
web_fetch("https://tophub.today/n/Jb0vmloB1G") # Baidu
Fetching Priority:
- Prioritize Weibo + Zhihu + Baidu (covers 90% of hot topics)
- Only fetch other platforms if suitable topics are not found in these 3
- Fetch one platform at a time, filter immediately, then decide whether to fetch the next
Filtering Criteria
From all platform trending lists, filter out truly important topics:
Include:
- Major Events: Significant policies, international relations, social events
- Hot Discussion Topics: Topics that spark widespread discussion
- Factual Content: Keep the events themselves without commentary
Exclude:
- Headlines with subjective commentary
- Pure entertainment gossip
- Obvious promotional content
- Emotional expressions
Output Requirements:
- Each news item must be complete with clear beginning and end
- Describe events like news headlines
- Avoid single words or incomplete fragments
Output Format
Output only the 5 most valuable items:
======
🔥 今日热搜（3月25日）
1. [完整新闻标题1]
2. [完整新闻标题2]
3. [完整新闻标题3]
4. [完整新闻标题4]
5. [完整新闻标题5]
======
Notes:
- Each news item should be complete with clear beginning and end
- No source attribution needed
- Facts only, exclude subjective commentary
- Output only the required content, no extra text
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.
- 13d ago First seen · 87 lines · 43 tokens per session scan A ba1d8c3269a2
daily-trending is a skill published in the GitHub repository netease-youdao/LobsterAI (6,012 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 617 once invoked, about $0.0002 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
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.writing-hive-skills
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.