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 article-writergit 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/article-writer)<a href="https://agentmods.dev/skills/netease-youdao/lobsterai/article-writer"><img src="https://agentmods.dev/badge/skills/netease-youdao/lobsterai/article-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/netease-youdao/lobsterai/article-writer"><img src="https://agentmods.dev/badge/skills/netease-youdao/lobsterai/article-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 | $0.00062 | $0.02105 |
| Opus 5 | $0.00031 | $0.01052 |
| Sonnet 5 | $0.00012 | $0.00421 |
| Haiku 4.5 | $0.00006 | $0.00211 |
Grade A, and why
article-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 11d 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:
- article-writer — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Style Article Creation
Use Cases
- User says "写一篇关于XX的文章"
- User says "帮我写一篇公众号文章"
- User selects a topic from the content calendar to start writing
- User specifies a writing style (e.g., "深度分析风格", "写个教程")
5 Writing Styles
| Style ID | Name | Characteristics | Word Count | Use Cases |
|---|---|---|---|---|
deep-analysis |
深度分析 | Rigorous structure, data-backed | 2000-4000 words | Trend analysis, in-depth reporting |
practical-guide |
实用指南 | Clear steps, highly actionable | 1500-3000 words | Tool tutorials, how-to guides |
story-driven |
故事驱动 | Conversational, emotional resonance | 1500-2500 words | Personal stories, case reviews |
opinion |
观点评论 | Sharp opening, pros/cons argumentation | 1000-2000 words | Hot takes, controversial topics |
news-brief |
新闻简报 | Inverted pyramid, fact-focused | 500-1000 words | Breaking news, information roundups |
Workflow
Step 1: Read the Brief
Obtain topic information from:
- Entries with status
plannedincontent_calendar.json - Topic description directly provided by the user
Extract key information:
- Topic direction / title
- Target audience
- Writing style (if not specified, recommend based on topic content)
- Reference material URLs
Step 2: Determine Writing Style
If user hasn't specified, recommend based on topic:
| Topic Characteristics | Recommended Style |
|---|---|
| Involves data, trends, underlying causes | deep-analysis |
| "How to", "tutorial", "steps" | practical-guide |
| Involves people, experiences, insights | story-driven |
| Involves controversy, hot topic commentary | opinion |
| Breaking events, quick information | news-brief |
Confirm the style choice with the user.
Step 3: Material Collection
Use content-planner's search script to collect reference materials:
node "$SKILLS_ROOT/content-planner/scripts/wechat_search.js" "topic keywords" -n 10
Also use web-search skill for additional materials.
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.
- 11d ago First seen · 235 lines · 62 tokens per session scan A 0f0113951d9e
article-writer is a skill published in the GitHub repository netease-youdao/LobsterAI (6,007 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 2,105 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 2026-08-30.
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.