[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M736PDVCT2S02KPP59CCCWCZ":3,"skill-same:01M736PDVCT2S02KPP59CCCWCZ":59},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":6,"updatedAt":44,"install":45,"resources":58},"01M736PDVCT2S02KPP59CCCWCZ","assess-ip-landscape",null,"Map the intellectual property landscape for a technology domain or product area. Covers patent cluster analysis, white space identification, competitor IP portfolio assessment, freedom-to-operate preliminary screening, and strategic IP positioning recommendations. Use before starting R&D in a new technology area, when evaluating market entry against incumbents with strong patent portfolios, preparing for investment due diligence, informing a patent filing strategy, or assessing freedom-to-operate risk for a new product.","roohe\u002Fagentic-super-skills","roohe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99054084?v=4","01M734WCDFP6RZVT5CNM00QR26","01M734WCE4BD0T4NZS5PCV9V5F",10,"MIT","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fassess-ip-landscape\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: assess-ip-landscape\nlocale: caveman-lite\nsource_locale: en\nsource_commit: 82c77053\ntranslator: \"Julius Brussee homage — caveman\"\ntranslation_date: \"2026-04-19\"\ndescription: >\n  Map the intellectual property landscape for a technology domain or product\n  area. Covers patent cluster analysis, white space identification, competitor\n  IP portfolio assessment, freedom-to-operate preliminary screening, and\n  strategic IP positioning recommendations. Use before starting R&D in a new\n  technology area, when evaluating market entry against incumbents with strong\n  patent portfolios, preparing for investment due diligence, informing a patent\n  filing strategy, or assessing freedom-to-operate risk for a new product.\nlicense: MIT\nallowed-tools: Read Grep Glob WebFetch WebSearch\nmetadata:\n  author: Philipp Thoss\n  version: \"1.0\"\n  domain: intellectual-property\n  complexity: advanced\n  language: natural\n  tags: intellectual-property, patents, landscape, fto, trademark, ip-strategy, prior-art\n---\n\n# Assess IP Landscape\n\nMap the intellectual property landscape for a technology area — identify patent clusters, white spaces, key players, and freedom-to-operate risks. Produces a strategic assessment that informs R&D direction, licensing decisions, and IP filing strategy.\n\n## When to Use\n\n- Before starting R&D in a new technology area (what's already claimed?)\n- Evaluating a market entry where incumbents have strong patent portfolios\n- Preparing for investment due diligence (IP asset assessment)\n- Informing a patent filing strategy (where to file, what to claim)\n- Assessing freedom-to-operate risk for a new product or feature\n- Monitoring competitor IP activity for strategic positioning\n\n## Inputs\n\n- **Required**: Technology domain or product area to assess\n- **Required**: Geographic scope (US, EU, global)\n- **Optional**: Specific competitors to focus on\n- **Optional**: Own patent portfolio (for gap analysis and FTO)\n- **Optional**: Time horizon (last 5 years, last 10 years, all time)\n- **Optional**: Classification codes (IPC, CPC) if known\n\n## Procedure\n\n### Step 1: Define the Search Scope\n\nEstablish the boundaries of the landscape analysis.\n\n1. Define the technology domain precisely:\n   - Core technology area (e.g., \"transformer-based language models\" not \"AI\")\n   - Adjacent areas to include (e.g., \"attention mechanisms, tokenization, inference optimization\")\n   - Areas to explicitly exclude (e.g., \"computer vision transformers\" if focusing on NLP)\n2. Identify relevant classification codes:\n   - IPC (International Patent Classification) — broad, used worldwide\n   - CPC (Cooperative Patent Classification) — more specific, US\u002FEU standard\n   - Search WIPO's IPC publication or USPTO's CPC browser\n3. Define the geographic scope:\n   - US (USPTO), EU (EPO), WIPO (PCT), specific national offices\n   - Most analyses start with US + EU + PCT for broad coverage\n4. Set the time window:\n   - Recent activity: last 3-5 years (current competitive landscape)\n   - Full history: 10-20 years (mature technology areas)\n   - Watch for expired patents that open up design space\n5. Document the scope as the **Landscape Charter**\n\n**Got:** A clear, bounded scope that is specific enough to produce actionable results but broad enough to capture the relevant competitive landscape. Classification codes identified for systematic search.\n\n**If fail:** If the technology domain is too broad (thousands of results), narrow by adding technical specificity or focusing on a specific application area. If too narrow (few results), broaden to adjacent technologies. The right scope yields 100-1000 patent families.\n\n### Step 2: Harvest Patent Data\n\nCollect the patent data within the defined scope.\n\n1. Query patent databases using the Landscape Charter:\n   - **Free databases**: Google Patents, USPTO PatFT\u002FAppFT, Espacenet, WIPO Patentscope\n   - **Commercial databases**: Orbit, PatSnap, Derwent, Lens.org (freemium)\n   - Combine keyword search + classification codes for best coverage\n2. Build search queries systematically:\n\n```\nQuery Construction:\n+-------------------+------------------------------------------+\n| Component         | Example                                  |\n+-------------------+------------------------------------------+\n| Core keywords     | \"language model\" OR \"LLM\" OR \"GPT\"       |\n| Technical terms   | \"attention mechanism\" OR \"transformer\"    |\n| Classification    | CPC: G06F40\u002F*, G06N3\u002F08                  |\n| Date range        | filed:2019-2024                          |\n| Assignee filter   | (optional) specific companies            |\n+-------------------+------------------------------------------+\n```\n\n3. Download results in structured format (CSV, JSON) including:\n   - Patent\u002Fapplication number, title, abstract, filing date\n   - Assignee\u002Fapplicant, inventor(s)\n   - Classification codes, citation data\n   - Legal status (granted, pending, expired, abandoned)\n4. Deduplicate by patent family (group national filings of the same invention)\n5. Record the total patent family count and source databases\n\n**Got:** A structured dataset of patent families within scope, deduplicated and timestamped. The dataset is the foundation for all subsequent analysis.\n\n**If fail:** If database access is limited, Google Patents + Lens.org (free) provide good coverage. If the query returns too many results (>5000), add technical specificity. If too few (\u003C50), broaden keywords or add classification codes.\n\n### Step 3: Analyze the Landscape\n\nMap the patent clusters, key players, and trends.\n\n1. **Cluster analysis**: Group patents by sub-technology:\n   - Use classification codes or keyword clustering to identify 5-10 sub-areas\n   - Count patent families per cluster\n   - Identify which clusters are growing (recent filing surges) vs. mature (flat or declining)\n2. **Key player analysis**: Identify the top 10 assignees by:\n   - Total patent family count (portfolio breadth)\n   - Recent filing rate (last 3 years — current activity)\n   - Average citation count (patent quality proxy)\n   - Geographic filing breadth (US-only vs. global filings)\n3. **Trend analysis**: Chart filing trends over the time window:\n   - Overall filing volume by year\n   - Filing volume by cluster by year\n   - New entrants (assignees filing for the first time in the domain)\n4. **Citation network**: Identify the most-cited patents (foundational IP):\n   - High forward citations = heavily relied upon by subsequent filings\n   - These are likely blocking patents or essential prior art\n5. Produce the **Landscape Map**: clusters, players, trends, and key patents\n\n**Got:** A clear picture of who owns what, where the activity is concentrated, and how the landscape is evolving. Key blocking patents identified. White spaces (areas with few filings) visible.\n\n**If fail:** If the dataset is too small for meaningful clustering, combine clusters into broader groups. If one assignee dominates (>50% of filings), analyze their portfolio as a separate sub-landscape.\n\n### Step 4: Identify White Spaces and Risks\n\nExtract strategic insights from the landscape.\n\n1. **White space analysis** (opportunities):\n   - Technology areas within scope with few or no patent filings\n   - Expired patent families where the design space has reopened\n   - Active areas where only one player has filed (first-mover but no competition)\n   - White spaces adjacent to growing clusters (next frontier)\n2. **FTO risk screening** (threats) — adapted from `heal` triage matrix:\n   - **Critical**: Granted patents directly covering your planned product\u002Ffeature\n   - **High**: Pending applications likely to grant with relevant claims\n   - **Medium**: Granted patents in adjacent areas that could be broadly interpreted\n   - **Low**: Expired patents, narrow claims, or geographically irrelevant filings\n3. **Competitive positioning**:\n   - Where does your portfolio (if any) sit relative to competitors?\n   - Which competitors have blocking positions in your target areas?\n   - Which competitors might be interested in cross-licensing?\n4. Produce the **Strategic Assessment**: white spaces, FTO risks, positioning, and recommendations\n\n**Got:** Actionable strategic recommendations: where to file, what to avoid, who to watch, and what risks need detailed FTO analysis.\n\n**If fail:** If FTO risks are identified, this screening is preliminary — it does NOT replace a formal FTO opinion from a patent attorney. Flag critical risks for legal review. If white spaces seem too good (a valuable area with no filings), verify the search scope didn't accidentally exclude relevant filings.\n\n### Step 5: Document and Recommend\n\nPackage the landscape assessment for decision-makers.\n\n1. Write the **Landscape Report** with sections:\n   - Executive summary (1 page: key findings, top risks, main recommendations)\n   - Scope and methodology (search terms, databases, date range)\n   - Landscape overview (clusters, trends, key players with visualizations)\n   - White space analysis (opportunities ranked by strategic value)\n   - Risk assessment (FTO concerns ranked by severity)\n   - Recommendations (filing strategy, licensing targets, monitoring alerts)\n2. Include supporting data:\n   - Patent family list (structured, sortable)\n   - Cluster map (visual)\n   - Filing trend charts\n   - Key patent summaries (top 10-20 most relevant patents)\n3. Set up ongoing monitoring:\n   - Define alert queries for new filings in critical areas\n   - Set review cadence (quarterly for active areas, annually for stable ones)\n\n**Got:** A complete landscape report that enables strategic IP decisions. The report is evidence-based, clearly scoped, and actionable.\n\n**If fail:** If the report is too large, produce the executive summary first and offer detailed sections on request. The executive summary should always stand alone as a decision document.\n\n## Validation Checklist\n\n- [ ] Landscape Charter defines scope, classification, geography, and time window\n- [ ] Patent dataset harvested from multiple databases and deduplicated\n- [ ] Clusters identified with filing counts and trend direction\n- [ ] Top 10 key players profiled with portfolio metrics\n- [ ] White spaces identified and ranked by strategic value\n- [ ] FTO risks screened and classified by severity\n- [ ] Key blocking patents identified with citation analysis\n- [ ] Recommendations are specific and actionable\n- [ ] Limitations acknowledged (screening vs. formal FTO opinion)\n- [ ] Monitoring alerts defined for ongoing landscape tracking\n\n## Pitfalls\n\n- **Too broad a scope**: \"AI patents\" is not a landscape — it's an ocean. Be specific about the technology and application\n- **Single-database reliance**: No single patent database has complete coverage. Use at least two sources\n- **Ignoring patent families**: Counting individual filings instead of families inflates the numbers. One invention filed in 10 countries is one patent family, not ten\n- **Confusing applications with grants**: A pending application is not an enforceable right. Distinguish between granted patents and published applications\n- **White space misinterpretation**: An empty area might mean \"nobody tried\" or \"everybody tried and failed.\" Investigate before assuming opportunity\n- **Landscape as legal opinion**: This skill produces strategic intelligence, not legal advice. FTO risks flagged here need formal analysis by patent counsel\n\n## Related Skills\n\n- `search-prior-art` — Detailed prior art search for specific inventions or patent validity challenges\n- `screen-trademark` — Trademark conflict screening and distinctiveness analysis for the trademark side of IP landscapes\n- `file-trademark` — Trademark filing procedures for EUIPO, USPTO, and Madrid Protocol\n- `security-audit-codebase` — Risk assessment methodology parallels IP risk screening\n- `review-research` — Literature review skills apply to prior art analysis\n","# Assess IP Landscape\n\nMap the intellectual property landscape for a technology area — identify patent clusters, white spaces, key players, and freedom-to-operate risks. Produces a strategic assessment that informs R&D direction, licensing decisions, and IP filing strategy.\n\n## When to Use\n\n- Before starting R&D in a new technology area (what's already claimed?)\n- Evaluating a market entry where incumbents have strong patent portfolios\n- Preparing for investment due diligence (IP asset assessment)\n- Informing a patent filing strategy (where to file, what to claim)\n- Assessing freedom-to-operate risk for a new product or feature\n- Monitoring competitor IP activity for strategic positioning\n\n## Inputs\n\n- **Required**: Technology domain or product area to assess\n- **Required**: Geographic scope (US, EU, global)\n- **Optional**: Specific competitors to focus on\n- **Optional**: Own patent portfolio (for gap analysis and FTO)\n- **Optional**: Time horizon (last 5 years, last 10 years, all time)\n- **Optional**: Classification codes (IPC, CPC) if known\n\n## Procedure\n\n### Step 1: Define the Search Scope\n\nEstablish the boundaries of the landscape analysis.\n\n1. Define the technology domain precisely:\n   - Core technology area (e.g., \"transformer-based language models\" not \"AI\")\n   - Adjacent areas to include (e.g., \"attention mechanisms, tokenization, inference optimization\")\n   - Areas to explicitly exclude (e.g., \"computer vision transformers\" if focusing on NLP)\n2. Identify relevant classification codes:\n   - IPC (International Patent Classification) — broad, used worldwide\n   - CPC (Cooperative Patent Classification) — more specific, US\u002FEU standard\n   - Search WIPO's IPC publication or USPTO's CPC browser\n3. Define the geographic scope:\n   - US (USPTO), EU (EPO), WIPO (PCT), specific national offices\n   - Most analyses start with US + EU + PCT for broad coverage\n4. Set the time window:\n   - Recent activity: last 3-5 years (current competitive landscape)\n   - Full history: 10-20 years (mature technology areas)\n   - Watch for expired patents that open up design space\n5. Document the scope as the **Landscape Charter**\n\n**Got:** A clear, bounded scope that is specific enough to produce actionable results but broad enough to capture the relevant competitive landscape. Classification codes identified for systematic search.\n\n**If fail:** If the technology domain is too broad (thousands of results), narrow by adding technical specificity or focusing on a specific application area. If too narrow (few results), broaden to adjacent technologies. The right scope yields 100-1000 patent families.\n\n### Step 2: Harvest Patent Data\n\nCollect the patent data within the defined scope.\n\n1. Query patent databases using the Landscape Charter:\n   - **Free databases**: Google Patents, USPTO PatFT\u002FAppFT, Espacenet, WIPO Patentscope\n   - **Commercial databases**: Orbit, PatSnap, Derwent, Lens.org (freemium)\n   - Combine keyword search + classification codes for best coverage\n2. Build search queries systematically:\n\n```\nQuery Construction:\n+-------------------+------------------------------------------+\n| Component         | Example                                  |\n+-------------------+------------------------------------------+\n| Core keywords     | \"language model\" OR \"LLM\" OR \"GPT\"       |\n| Technical terms   | \"attention mechanism\" OR \"transformer\"    |\n| Classification    | CPC: G06F40\u002F*, G06N3\u002F08                  |\n| Date range        | filed:2019-2024                          |\n| Assignee filter   | (optional) specific companies            |\n+-------------------+------------------------------------------+\n```\n\n3. Download results in structured format (CSV, JSON) including:\n   - Patent\u002Fapplication number, title, abstract, filing date\n   - Assignee\u002Fapplicant, inventor(s)\n   - Classification codes, citation data\n   - Legal status (granted, pending, expired, abandoned)\n4. Deduplicate by patent family (group national filings of the same invention)\n5. Record the total patent family count and source databases\n\n**Got:** A structured dataset of patent families within scope, deduplicated and timestamped. The dataset is the foundation for all subsequent analysis.\n\n**If fail:** If database access is limited, Google Patents + Lens.org (free) provide good coverage. If the query returns too many results (>5000), add technical specificity. If too few (\u003C50), broaden keywords or add classification codes.\n\n### Step 3: Analyze the Landscape\n\nMap the patent clusters, key players, and trends.\n\n1. **Cluster analysis**: Group patents by sub-technology:\n   - Use classification codes or keyword clustering to identify 5-10 sub-areas\n   - Count patent families per cluster\n   - Identify which clusters are growing (recent filing surges) vs. mature (flat or declining)\n2. **Key player analysis**: Identify the top 10 assignees by:\n   - Total patent family count (portfolio breadth)\n   - Recent filing rate (last 3 years — current activity)\n   - Average citation count (patent quality proxy)\n   - Geographic filing breadth (US-only vs. global filings)\n3. **Trend analysis**: Chart filing trends over the time window:\n   - Overall filing volume by year\n   - Filing volume by cluster by year\n   - New entrants (assignees filing for the first time in the domain)\n4. **Citation network**: Identify the most-cited patents (foundational IP):\n   - High forward citations = heavily relied upon by subsequent filings\n   - These are likely blocking patents or essential prior art\n5. Produce the **Landscape Map**: clusters, players, trends, and key patents\n\n**Got:** A clear picture of who owns what, where the activity is concentrated, and how the landscape is evolving. Key blocking patents identified. White spaces (areas with few filings) visible.\n\n**If fail:** If the dataset is too small for meaningful clustering, combine clusters into broader groups. If one assignee dominates (>50% of filings), analyze their portfolio as a separate sub-landscape.\n\n### Step 4: Identify White Spaces and Risks\n\nExtract strategic insights from the landscape.\n\n1. **White space analysis** (opportunities):\n   - Technology areas within scope with few or no patent filings\n   - Expired patent families where the design space has reopened\n   - Active areas where only one player has filed (first-mover but no competition)\n   - White spaces adjacent to growing clusters (next frontier)\n2. **FTO risk screening** (threats) — adapted from `heal` triage matrix:\n   - **Critical**: Granted patents directly covering your planned product\u002Ffeature\n   - **High**: Pending applications likely to grant with relevant claims\n   - **Medium**: Granted patents in adjacent areas that could be broadly interpreted\n   - **Low**: Expired patents, narrow claims, or geographically irrelevant filings\n3. **Competitive positioning**:\n   - Where does your portfolio (if any) sit relative to competitors?\n   - Which competitors have blocking positions in your target areas?\n   - Which competitors might be interested in cross-licensing?\n4. Produce the **Strategic Assessment**: white spaces, FTO risks, positioning, and recommendations\n\n**Got:** Actionable strategic recommendations: where to file, what to avoid, who to watch, and what risks need detailed FTO analysis.\n\n**If fail:** If FTO risks are identified, this screening is preliminary — it does NOT replace a formal FTO opinion from a patent attorney. Flag critical risks for legal review. If white spaces seem too good (a valuable area with no filings), verify the search scope didn't accidentally exclude relevant filings.\n\n### Step 5: Document and Recommend\n\nPackage the landscape assessment for decision-makers.\n\n1. Write the **Landscape Report** with sections:\n   - Executive summary (1 page: key findings, top risks, main recommendations)\n   - Scope and methodology (search terms, databases, date range)\n   - Landscape overview (clusters, trends, key players with visualizations)\n   - White space analysis (opportunities ranked by strategic value)\n   - Risk assessment (FTO concerns ranked by severity)\n   - Recommendations (filing strategy, licensing targets, monitoring alerts)\n2. Include supporting data:\n   - Patent family list (structured, sortable)\n   - Cluster map (visual)\n   - Filing trend charts\n   - Key patent summaries (top 10-20 most relevant patents)\n3. Set up ongoing monitoring:\n   - Define alert queries for new filings in critical areas\n   - Set review cadence (quarterly for active areas, annually for stable ones)\n\n**Got:** A complete landscape report that enables strategic IP decisions. The report is evidence-based, clearly scoped, and actionable.\n\n**If fail:** If the report is too large, produce the executive summary first and offer detailed sections on request. The executive summary should always stand alone as a decision document.\n\n## Validation Checklist\n\n- [ ] Landscape Charter defines scope, classification, geography, and time window\n- [ ] Patent dataset harvested from multiple databases and deduplicated\n- [ ] Clusters identified with filing counts and trend direction\n- [ ] Top 10 key players profiled with portfolio metrics\n- [ ] White spaces identified and ranked by strategic value\n- [ ] FTO risks screened and classified by severity\n- [ ] Key blocking patents identified with citation analysis\n- [ ] Recommendations are specific and actionable\n- [ ] Limitations acknowledged (screening vs. formal FTO opinion)\n- [ ] Monitoring alerts defined for ongoing landscape tracking\n\n## Pitfalls\n\n- **Too broad a scope**: \"AI patents\" is not a landscape — it's an ocean. Be specific about the technology and application\n- **Single-database reliance**: No single patent database has complete coverage. Use at least two sources\n- **Ignoring patent families**: Counting individual filings instead of families inflates the numbers. One invention filed in 10 countries is one patent family, not ten\n- **Confusing applications with grants**: A pending application is not an enforceable right. Distinguish between granted patents and published applications\n- **White space misinterpretation**: An empty area might mean \"nobody tried\" or \"everybody tried and failed.\" Investigate before assuming opportunity\n- **Landscape as legal opinion**: This skill produces strategic intelligence, not legal advice. FTO risks flagged here need formal analysis by patent counsel\n\n## Related Skills\n\n- `search-prior-art` — Detailed prior art search for specific inventions or patent validity challenges\n- `screen-trademark` — Trademark conflict screening and distinctiveness analysis for the trademark side of IP landscapes\n- `file-trademark` — Trademark filing procedures for EUIPO, USPTO, and Madrid Protocol\n- `security-audit-codebase` — Risk assessment methodology parallels IP risk screening\n- `review-research` — Literature review skills apply to prior art analysis\n",{"name":5,"locale":23,"license":14,"metadata":24,"translator":31,"description":32,"allowed-tools":33,"source_commit":34,"source_locale":35,"translation_date":36},"caveman-lite",{"tags":25,"author":26,"domain":27,"version":28,"language":29,"complexity":30},"intellectual-property, patents, landscape, fto, trademark, ip-strategy, prior-art","Philipp Thoss","intellectual-property","1.0","natural","advanced","Julius Brussee homage — caveman","Map the intellectual property landscape for a technology domain or product area. Covers patent cluster analysis, white space identification, competitor IP portfolio assessment, freedom-to-operate preliminary screening, and strategic IP positioning recommendations. Use before starting R&D in a new technology area, when evaluating market entry against incumbents with strong patent portfolios, preparing for investment due diligence, informing a patent filing strategy, or assessing freedom-to-operate risk for a new product.\n","Read Grep Glob WebFetch WebSearch","82c77053","en","2026-04-19","master","f483e54f3ad5f202a77d45f2e57f8d970b71195f","skills_library\u002Fassess-ip-landscape",2,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills","https:\u002F\u002Fgithub.com\u002Froohe","yoou.link","2026-05-19 15:56:07",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add roohe\u002Fagentic-super-skills --skill assess-ip-landscape",{"tool":51,"command":52},"bunx","bunx skills add roohe\u002Fagentic-super-skills --skill assess-ip-landscape",{"tool":54,"command":55},"pnpm","pnpm dlx skills add roohe\u002Fagentic-super-skills --skill assess-ip-landscape","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fassess-ip-landscape\u002FSKILL.md",true,[],[60,67,74,81,88,95],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M73D865CZME2FCMKA4PQM348","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M73D7Z64J4ABWZJD7P44XBBF","youtube-downloader","Download and process YouTube content for research. Use when: downloading competitor videos for analysis; extracting audio for podcasts; getting transcripts for content repurposing; archiving webinars; research content curation","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyoutube-downloader\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M73D7K8778TGZV3GJFR3703D","yc-pitch-deck","Create a compelling startup pitch deck that follows the structure proven to raise billions from top investors. Master the YC and Sequoia formats that get founders funded. Use when: **Fundraising** to create investor pitch decks; **YC application** to structure your narrative; **Demo Day prep** to craft your 2-minute pitch; **Angel investors** to communicate your opportunity; **Partnership pitches** to structure compelling asks","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyc-pitch-deck\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M73D70KJSE0E8Z28YMNNRT04","x-twitter-scraper","Use when the user needs X (Twitter) data or confirmation-gated X actions through Xquik: tweet search, user lookup, follower extraction, media download, monitoring, webhooks, MCP, SDKs, posting, likes, DMs, and profile updates. Requires a Xquik API key. Never ask for X login material.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fx-twitter-scraper\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M73D6ED01GV077R7K4NZNFZJ","write-vignette","Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, and CRAN requirements for vignettes. Use when adding a Getting Started tutorial, documenting complex workflows spanning multiple functions, creating domain-specific guides, or when CRAN submission requires user-facing documentation beyond function help pages.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-vignette\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M73D69YJR0BK3NFHE0CYG3EF","write-validation-documentation","Write IQ\u002FOQ\u002FPQ validation documentation for computerized systems in regulated environments. Covers protocols, reports, test scripts, deviation handling, and approval workflows. Use when validating R or other software for regulated use, preparing for a regulatory audit, documenting qualification of computing environments, or creating and updating validation protocols and reports for new or re-qualified systems.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-validation-documentation\u002FSKILL.md",[],[]]