Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub ยท Developer Tools
Embodied Ai News
Aggregates publicly available Embodied AI and Robotics news from curated sources (robotics media, arXiv, company blogs). Delivers structured briefings on hum...
skill openclawclawhub Free
Aggregates publicly available Embodied AI and Robotics news from curated sources (robotics media, arXiv, company blogs). Delivers structured briefings on hum...
โฌ 0 downloads โ
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md, references/news_sources.md, references/output_templates.md, references/search_queries.md, references/taxonomy.md, references/workflow.md
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.3
Provenance
- Publisher
- HeXavi8
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Embodied AI News Briefing
Aggregates the latest Embodied AI & Robotics news from curated sources and delivers concise summaries with direct links. Covers the full stack: algorithms, hardware, simulation, deployment, funding, policy, and the China ecosystem.
When to Use This Skill
Activate this skill when the user: Asks for embodied AI news, robot news, or humanoid robot updates Requests a daily/weekly/monthly robotics briefing Mentions wanting to know what's happening in embodied AI / robotics Asks about specific companies: Tesla Optimus, Figure, Unitree, AGIBOT, Boston Dynamics, etc. Asks about specific technologies: VLA models, diffusion policy, sim-to-real, dexterous manipulation Wants a summary of recent robotics research papers Asks about robotics funding, deployments, or supply chain Asks about simulation platforms, benchmarks, or datasets Asks about robotics policy, safety standards, or export controls Requests a monthly trend report or competitive analysis Says: "็ปๆไปๅคฉ็ๅ ท่บซๆบ่ฝ่ต่ฎฏ" (Give me today's embodied AI news) Says: "ๆบๅจไบบ่กไธๆไปไนๆฐๅจๆ" (What's new in the robot industry) Says: "ๆ่ฟๆไปไนไบบๅฝขๆบๅจไบบ็ๆถๆฏ" (Any recent humanoid robot news) Says: "่ฟไธชๆ็ๅ ท่บซๆบ่ฝ่ถๅฟๆฅๅ" (This month's embodied AI trend report) Says: "embodied AI updates", "robot learning news", "humanoid robot news"
Trigger Keywords
English: embodied AI, humanoid robot, robot news, robotics update, robot learning, VLA model, diffusion policy, dexterous manipulation, sim-to-real, robot deployment, robotics funding, Figure AI, Tesla Optimus, Unitree, AGIBOT, Boston Dynamics, 1X, Physical Intelligence, Skild AI, robot hand, quadruped robot, Isaac Sim, world model robot, robot benchmark, robot safety, robot regulation, monthly robot report Chinese: ๅ ท่บซๆบ่ฝ, ไบบๅฝขๆบๅจไบบ, ๆบๅจไบบ่ต่ฎฏ, ็ตๅทงๆไฝ, ไปฟ็ๅฐ็ๅฎ, ๆบๅจไบบ้จ็ฝฒ, ๅฎๆ , ๆบๅ , ไผๅฟ ้, ้ถๆฒณ้็จ, ๅ ๅฉๅถ, ๆบๅจไบบ่่ต, ็ตๅทงๆ, ๅ่ถณๆบๅจไบบ, ๆบๅจไบบๅคงๆจกๅ, ๆบๅจไบบๆๆฅ, ๆบๅจไบบๅฎๅ จ, ๆบๅจไบบๆฟ็ญ
Reference Files
This skill relies on 5 companion reference files. Always consult them during execution: ๐ references/ โโโ ๐ฐ news_sources.md โ WHERE to find information (tiered source list) โโโ ๐ search_queries.md โ HOW to search (query templates & recipes) โโโ ๐ output_templates.md โ WHAT format to output (6+ template variants) โโโ ๐ taxonomy.md โ SHARED LANGUAGE (categories, keywords, company list) โโโ ๐งญ workflow.md โ WHEN and in what ORDER to execute (SOP for daily/weekly/monthly) FileWhen to Consultnews_sources.mdPhase 1 โ choosing which sites to fetch; selecting tier-appropriate sourcessearch_queries.mdPhase 1 โ building search queries; selecting recipe by briefing typetaxonomy.mdPhase 3 โ classifying stories; Phase 1 โ looking up company aliases & tech termsoutput_templates.mdPhase 5 โ rendering final output; selecting template by user requestworkflow.mdAll Phases โ orchestrating the end-to-end workflow; time budgeting; monthly maintenance
File Interconnection Map
โโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโ โ search_queries โโโโโโถ โ news_sources โโโโโโถโ Classify & โโโโโโถโ output_templates โ โ (discover) โ โ (browse & verify) โ โ Prioritize โ โ (generate) โ โโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโ โฒ โฒ โ โ โโโโโโโ taxonomy.md โโโโโโ (shared vocabulary)
Phase 0: Determine Briefing Type & Time Scope
Before any tool calls, ask the user (if not already clear): Briefing Type: Daily / Weekly / Monthly / Custom Topic? Time Scope: Last 24 hours / Last 7 days / Last 30 days / Custom date range? Output Format: Standard / Brief / Thread / Markdown Report / Presentation / Custom? Focus Area (optional): All categories / Specific category (e.g., only hardware, only China ecosystem)? Default if user doesn't specify: Type: Daily Scope: Last 24 hours Format: Standard Focus: All categories Map to workflow.md: Daily โ workflow.md Section "Daily Workflow" Weekly โ workflow.md Section "Weekly Workflow" Monthly โ workflow.md Section "Monthly Workflow"
Phase 1: Information Gathering
Consult workflow.md for the appropriate recipe, then execute the corresponding steps from search_queries.md and news_sources.md. Step 1.1: Execute Search Queries Tool: WebSearch (or equivalent web search tool) Source: search_queries.md โ Select the appropriate recipe: Daily Briefing โ Recipe A (5 queries) Weekly Roundup โ Recipe B (8 queries) Monthly Deep Dive โ Recipe C (12 queries) Custom Topic โ Recipe D + user-specified filters Parameters: return_format: markdown with_images_summary: false timeout: 20 seconds per source Fetch only from publicly accessible sources listed in news_sources.md Output: A list of 20โ50 URLs with headlines and snippets. Step 1.2: Fetch Tier 1 Sources Directly Tool: mcp__web_reader__webReader Source: news_sources.md โ Tier 1 section Directly fetch the homepage or RSS feed of: The Robot Report IEEE Spectrum โ Robotics TechCrunch โ Robotics Robotics Business Review (Add others based on briefing type) Parameters: url: [homepage URL from news_sources.md] return_format: markdown with_images_summary: false Process only URLs from verified sources in news_sources.md Output: Recent headlines (last 24h / 7d / 30d based on scope). Step 1.3: Fetch arXiv Papers Tool: mcp__arxiv__readURL (if available) or WebSearch with arXiv-specific queries Source: search_queries.md โ Section "6. Academic Research (arXiv)" Execute 2โ3 arXiv queries: cat:cs.RO AND ("embodied AI" OR "robot learning" OR "VLA") submittedDate:[today - 7d TO today] Output: 5โ10 recent papers with abstracts. Step 1.4: Fetch Company Blogs & Official Announcements Tool: mcp__web_reader__webReader Source: news_sources.md โ Tier 2 (Company Blogs) + Tier 4 (China Ecosystem) Fetch from: Figure AI Blog Physical Intelligence Blog Tesla AI Blog Unitree Blog (Chinese + English) AGIBOT WeChat Official Account (if accessible) (Add others based on focus area) Fetch constraints: Only process URLs from search results and sources listed in news_sources.md Skip content requiring authentication Timeout: 15 seconds per URL Output: Recent announcements (last 7d / 30d based on scope).
Phase 2: Content Extraction & Deduplication
For each fetched URL: Extract: Headline Publication date Source name Summary (first 2โ3 paragraphs or abstract) Key entities: companies, models, hardware platforms (use taxonomy.md for reference) Deduplicate: If multiple sources cover the same story, keep the one with the most detail Merge information if they provide complementary details Discard: Stories older than the time scope Irrelevant content (use search_queries.md Section 1.4 "Noise Exclusion Filter") Duplicate announcements Output: A deduplicated list of 15โ30 stories with extracted metadata.
Phase 3: Classification & Prioritization
Consult taxonomy.md to classify each story. Step 3.1: Assign Primary Category Use taxonomy.md โ Section "1. News Category Taxonomy" Assign each story to exactly one primary category: ๐ฅ Major Announcements ๐ง Foundation Models & Algorithms ๐ฆพ Hardware & Platforms ๐ Simulation & Infrastructure ๐ญ Deployments & Commercial ๐ฐ Funding, M&A & Business ๐ Policy, Safety & Ethics ๐จ๐ณ China Ecosystem Rules (from taxonomy.md โ "Category Assignment Rules"): Major Announcements: Only for top-impact stories (new paradigm, >$500M funding, first-ever deployment milestone) China Ecosystem: Use when the story's primary significance is about the Chinese market/ecosystem Cross-cutting stories: Assign primary + up to 2 secondary tags Step 3.2: Assign Priority Level Use taxonomy.md โ Section "3. Priority Scoring System" Calculate priority score (0โ100) based on: Impact (0โ40 points): Paradigm shift / Major milestone / Incremental improvement Timeliness (0โ20 points): Breaking news / Recent (1โ3 days) / Older Source Authority (0โ20 points): Tier 1 / Tier 2 / Tier 3 Relevance (0โ20 points): Core embodied AI / Adjacent / Tangential Priority Levels: P0 (90โ100): Must-read, above-the-fold P1 (70โ89): Important, include in main body P2 (50โ69): Notable, include if space allows P3 (<50): Optional, move to "Other News" section or omit Step 3.3: Sort Stories Within each category, sort by: Priority score (descending) Publication date (most recent first)
Phase 4: Content Synthesis
For each story, generate: One-sentence summary: Capture the core news in <20 words Key points (2โ4 bullet points): Extract the most important details Metadata fields (based on category): For Foundation Models: Model Type, Embodiment, Open Source, Impact For Hardware: Hardware Type, Company, Specs, Impact For Deployments: Deployment Scale, Industry Vertical, Performance Metrics, Impact For Funding: Amount, Lead Investor, Valuation, Use of Funds (See output_templates.md for full metadata schema per category) Impact statement: Why this matters for the embodied AI field (1โ2 sentences) Tone & Style: Objective: Present facts without hype or editorial opinion Concise: Favor clarity over completeness Technical: Use domain-specific terminology from taxonomy.md Neutral: Treat all companies, countries, and technologies equally
Phase 5: Output Generation
Consult output_templates.md to select the appropriate template. Step 5.1: Select Template Based on user request (from Phase 0): User RequestTemplate to Use"Daily briefing"Standard Format"Quick summary"Brief Format"Twitter thread"Thread Format"Markdown report"Markdown Report Format"Presentation slides"Presentation Format"Custom"Adapt from Standard Format Step 5.2: Render Output Fill in the selected template with: Header: Date, source count, time scope Category sections: Ordered by priority (๐ฅ Major Announcements first) Story blocks: Headline, summary, key points, metadata, source link Footer: Methodology note, source attribution Quality checks: All links are valid and correctly formatted All metadata fields are filled (use "N/A" if not applicable) No duplicate stories Stories are sorted by priority within each category Total output length is appropriate for briefing type: Daily: 1,500โ2,500 words Weekly: 3,000โ5,000 words Monthly: 5,000โ10,000 words Step 5.3: Add Contextual Notes (Optional) If the user requested analysis or trends, append: Trend Spotlight: 2โ3 emerging patterns observed this period Company Momentum: Which companies/labs are most active Technology Shifts: Notable changes in technical approaches Geographic Insights: Regional differences (e.g., US vs China ecosystem) Use taxonomy.md โ Section "5. Trend Analysis Framework" for guidance.
Phase 6: Delivery & Follow-up
Deliver the briefing in the selected format Offer follow-up options: "Would you like me to deep-dive into any specific story?" "Should I track these companies/topics for your next briefing?" "Would you like a comparison with last week/month's trends?"
Custom Topic Deep-Dive
If user asks about a specific topic (e.g., "What's new with dexterous hands?"): Consult taxonomy.md โ Section "2. Technology & Product Taxonomy" โ Find relevant subcategories Build custom queries using search_queries.md โ Recipe D (Custom Topic) Fetch from all tiers in news_sources.md that cover this topic Output using the "Deep-Dive Format" from output_templates.md
Company-Specific Briefing
If user asks about a specific company (e.g., "What's Figure AI been up to?"): Consult taxonomy.md โ Section "4. Company & Organization Directory" โ Find company profile Build queries targeting: Company blog News mentions arXiv papers by company researchers Funding announcements Output using the "Company Spotlight Format" from output_templates.md
China Ecosystem Focus
If user asks specifically about China (e.g., "ไธญๅฝไบบๅฝขๆบๅจไบบๆไปไน่ฟๅฑ?"): Prioritize news_sources.md โ Tier 4 (China Ecosystem) Use search_queries.md โ Section "8. China Ecosystem" Consult taxonomy.md โ Section "4.3 China Ecosystem Companies" Output in Chinese or bilingual format (ask user preference)
Operating Scope
This skill operates in read-only mode: Fetches content from public sources listed in reference files Synthesizes and presents information to the user Does not modify, post, or interact with external systems Does not perform actions on behalf of the user unless explicitly requested (e.g., "add this to my calendar")
Information Freshness
Daily briefing: Prioritize stories from the last 24 hours Weekly briefing: Include stories from the last 7 days, but highlight the most recent Monthly briefing: Cover the full 30 days, but organize by week or theme
Source Diversity
Aim for a balanced mix: 40% from Tier 1 (core industry media) 30% from Tier 2 (company blogs & official sources) 20% from Tier 3 (academic & research) 10% from Tier 4 (China ecosystem, if relevant)
Quality over Quantity
Better to have 15 high-quality, well-summarized stories than 50 shallow headlines If a story lacks detail or verification, mark it as "Unconfirmed" or omit it
Handling Uncertainty
If a story's details are unclear, state: "Details are limited; awaiting official confirmation" If sources conflict, present both versions: "Source A reports X, while Source B reports Y" Never fabricate details to fill gaps
Language Handling
If user asks in Chinese, output in Chinese (but keep company/model names in English) If user asks in English, output in English For bilingual users, offer: "Would you like this in English, Chinese, or bilingual?"
If a source is unreachable:
Skip it and note in the footer: "Note: [Source Name] was unavailable at the time of this briefing"
If search returns no results:
Broaden the query or try alternative keywords from taxonomy.md If still no results, inform the user: "No recent news found for [topic] in the specified time range"
If classification is ambiguous:
Default to the most specific applicable category Add a secondary tag if the story spans multiple domains
If output exceeds length limits:
Prioritize P0 and P1 stories Move P2 and P3 stories to a "Quick Hits" section with one-line summaries Offer to generate a separate deep-dive on omitted topics
Monthly (consult workflow.md โ "Monthly Workflow"):
Review taxonomy.md for new companies, models, or terminology Update news_sources.md if new authoritative sources emerge Refine search_queries.md based on what queries yielded the best results
Quarterly:
Audit the priority scoring system โ are P0 stories truly the most impactful? Review output templates โ do they match user preferences?
Example 1: Daily Briefing
User: "Give me today's embodied AI news" Agent: Determines: Daily briefing, last 24h, Standard format, All categories Executes Recipe A from search_queries.md (5 queries) Fetches Tier 1 sources from news_sources.md Classifies using taxonomy.md Outputs using Standard Format from output_templates.md
Example 2: Weekly Roundup
User: "What happened in robotics this week?" Agent: Determines: Weekly briefing, last 7 days, Standard format, All categories Executes Recipe B from search_queries.md (8 queries) Fetches Tier 1 + Tier 2 sources Prioritizes P0 and P1 stories Outputs using Standard Format with "Trend Spotlight" section
Example 3: Custom Topic
User: "What's new with VLA models?" Agent: Determines: Custom topic, last 7 days, Deep-Dive format Consults taxonomy.md โ "Vision-Language-Action (VLA) Models" Builds custom queries from search_queries.md Section 2.1 Fetches from Tier 1 + Tier 3 (arXiv) Outputs using Deep-Dive Format
Example 4: Company Spotlight
User: "What's Unitree been up to?" Agent: Determines: Company-specific, last 30 days, Company Spotlight format Consults taxonomy.md โ Company profile for Unitree Fetches Unitree blog + news mentions + arXiv papers Outputs using Company Spotlight Format from output_templates.md
Example 5: China Ecosystem
User: "ไธญๅฝไบบๅฝขๆบๅจไบบๆไปไน่ฟๅฑ?" Agent: Determines: China focus, last 7 days, Standard format, Chinese output Prioritizes news_sources.md Tier 4 sources Uses search_queries.md Section 8 (China Ecosystem) Outputs in Chinese using Standard Format
Summary
This skill orchestrates a multi-phase workflow: Determine briefing type & scope Gather information from curated sources using structured queries Classify stories using a shared taxonomy Prioritize based on impact, timeliness, and relevance Synthesize concise summaries with metadata Output in the user's preferred format Key success factors: Always consult the 5 reference files at the appropriate workflow stage Maintain objectivity and source attribution Prioritize quality and relevance over quantity Adapt to user preferences (language, format, focus area)
Category context
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
6 Docs
- SKILL.md
- references/news_sources.md
- references/output_templates.md
- references/search_queries.md
- references/taxonomy.md
- references/workflow.md