[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BK3ARYA5SCAYW2R3B3DGDJ":3,"skill-same:01M7BK3ARYA5SCAYW2R3B3DGDJ":73},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7BK3ARYA5SCAYW2R3B3DGDJ","gtars",null,"High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fgtars\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: gtars\ndescription: High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.\n---\n\n# Gtars: Genomic Tools and Algorithms in Rust\n\n## Overview\n\nGtars is a high-performance Rust toolkit for manipulating, analyzing, and processing genomic interval data. It provides specialized tools for overlap detection, coverage analysis, tokenization for machine learning, and reference sequence management.\n\nUse this skill when working with:\n- Genomic interval files (BED format)\n- Overlap detection between genomic regions\n- Coverage track generation (WIG, BigWig)\n- Genomic ML preprocessing and tokenization\n- Fragment analysis in single-cell genomics\n- Reference sequence retrieval and validation\n\n## Installation\n\n### Python Installation\n\nInstall gtars Python bindings:\n\n```bash\nuv uv pip install gtars\n```\n\n### CLI Installation\n\nInstall command-line tools (requires Rust\u002FCargo):\n\n```bash\n# Install with all features\ncargo install gtars-cli --features \"uniwig overlaprs igd bbcache scoring fragsplit\"\n\n# Or install specific features only\ncargo install gtars-cli --features \"uniwig overlaprs\"\n```\n\n### Rust Library\n\nAdd to Cargo.toml for Rust projects:\n\n```toml\n[dependencies]\ngtars = { version = \"0.1\", features = [\"tokenizers\", \"overlaprs\"] }\n```\n\n## Core Capabilities\n\nGtars is organized into specialized modules, each focused on specific genomic analysis tasks:\n\n### 1. Overlap Detection and IGD Indexing\n\nEfficiently detect overlaps between genomic intervals using the Integrated Genome Database (IGD) data structure.\n\n**When to use:**\n- Finding overlapping regulatory elements\n- Variant annotation\n- Comparing ChIP-seq peaks\n- Identifying shared genomic features\n\n**Quick example:**\n```python\nimport gtars\n\n# Build IGD index and query overlaps\nigd = gtars.igd.build_index(\"regions.bed\")\noverlaps = igd.query(\"chr1\", 1000, 2000)\n```\n\nSee `references\u002Foverlap.md` for comprehensive overlap detection documentation.\n\n### 2. Coverage Track Generation\n\nGenerate coverage tracks from sequencing data with the uniwig module.\n\n**When to use:**\n- ATAC-seq accessibility profiles\n- ChIP-seq coverage visualization\n- RNA-seq read coverage\n- Differential coverage analysis\n\n**Quick example:**\n```bash\n# Generate BigWig coverage track\ngtars uniwig generate --input fragments.bed --output coverage.bw --format bigwig\n```\n\nSee `references\u002Fcoverage.md` for detailed coverage analysis workflows.\n\n### 3. Genomic Tokenization\n\nConvert genomic regions into discrete tokens for machine learning applications, particularly for deep learning models on genomic data.\n\n**When to use:**\n- Preprocessing for genomic ML models\n- Integration with geniml library\n- Creating position encodings\n- Training transformer models on genomic sequences\n\n**Quick example:**\n```python\nfrom gtars.tokenizers import TreeTokenizer\n\ntokenizer = TreeTokenizer.from_bed_file(\"training_regions.bed\")\ntoken = tokenizer.tokenize(\"chr1\", 1000, 2000)\n```\n\nSee `references\u002Ftokenizers.md` for tokenization documentation.\n\n### 4. Reference Sequence Management\n\nHandle reference genome sequences and compute digests following the GA4GH refget protocol.\n\n**When to use:**\n- Validating reference genome integrity\n- Extracting specific genomic sequences\n- Computing sequence digests\n- Cross-reference comparisons\n\n**Quick example:**\n```python\n# Load reference and extract sequences\nstore = gtars.RefgetStore.from_fasta(\"hg38.fa\")\nsequence = store.get_subsequence(\"chr1\", 1000, 2000)\n```\n\nSee `references\u002Frefget.md` for reference sequence operations.\n\n### 5. Fragment Processing\n\nSplit and analyze fragment files, particularly useful for single-cell genomics data.\n\n**When to use:**\n- Processing single-cell ATAC-seq data\n- Splitting fragments by cell barcodes\n- Cluster-based fragment analysis\n- Fragment quality control\n\n**Quick example:**\n```bash\n# Split fragments by clusters\ngtars fragsplit cluster-split --input fragments.tsv --clusters clusters.txt --output-dir .\u002Fby_cluster\u002F\n```\n\nSee `references\u002Fcli.md` for fragment processing commands.\n\n### 6. Fragment Scoring\n\nScore fragment overlaps against reference datasets.\n\n**When to use:**\n- Evaluating fragment enrichment\n- Comparing experimental data to references\n- Quality metrics computation\n- Batch scoring across samples\n\n**Quick example:**\n```bash\n# Score fragments against reference\ngtars scoring score --fragments fragments.bed --reference reference.bed --output scores.txt\n```\n\n## Common Workflows\n\n### Workflow 1: Peak Overlap Analysis\n\nIdentify overlapping genomic features:\n\n```python\nimport gtars\n\n# Load two region sets\npeaks = gtars.RegionSet.from_bed(\"chip_peaks.bed\")\npromoters = gtars.RegionSet.from_bed(\"promoters.bed\")\n\n# Find overlaps\noverlapping_peaks = peaks.filter_overlapping(promoters)\n\n# Export results\noverlapping_peaks.to_bed(\"peaks_in_promoters.bed\")\n```\n\n### Workflow 2: Coverage Track Pipeline\n\nGenerate coverage tracks for visualization:\n\n```bash\n# Step 1: Generate coverage\ngtars uniwig generate --input atac_fragments.bed --output coverage.wig --resolution 10\n\n# Step 2: Convert to BigWig for genome browsers\ngtars uniwig generate --input atac_fragments.bed --output coverage.bw --format bigwig\n```\n\n### Workflow 3: ML Preprocessing\n\nPrepare genomic data for machine learning:\n\n```python\nfrom gtars.tokenizers import TreeTokenizer\nimport gtars\n\n# Step 1: Load training regions\nregions = gtars.RegionSet.from_bed(\"training_peaks.bed\")\n\n# Step 2: Create tokenizer\ntokenizer = TreeTokenizer.from_bed_file(\"training_peaks.bed\")\n\n# Step 3: Tokenize regions\ntokens = [tokenizer.tokenize(r.chromosome, r.start, r.end) for r in regions]\n\n# Step 4: Use tokens in ML pipeline\n# (integrate with geniml or custom models)\n```\n\n## Python vs CLI Usage\n\n**Use Python API when:**\n- Integrating with analysis pipelines\n- Need programmatic control\n- Working with NumPy\u002FPandas\n- Building custom workflows\n\n**Use CLI when:**\n- Quick one-off analyses\n- Shell scripting\n- Batch processing files\n- Prototyping workflows\n\n## Reference Documentation\n\nComprehensive module documentation:\n\n- **`references\u002Fpython-api.md`** - Complete Python API reference with RegionSet operations, NumPy integration, and data export\n- **`references\u002Foverlap.md`** - IGD indexing, overlap detection, and set operations\n- **`references\u002Fcoverage.md`** - Coverage track generation with uniwig\n- **`references\u002Ftokenizers.md`** - Genomic tokenization for ML applications\n- **`references\u002Frefget.md`** - Reference sequence management and digests\n- **`references\u002Fcli.md`** - Command-line interface complete reference\n\n## Integration with geniml\n\nGtars serves as the foundation for the geniml Python package, providing core genomic interval operations for machine learning workflows. When working on geniml-related tasks, use gtars for data preprocessing and tokenization.\n\n## Performance Characteristics\n\n- **Native Rust performance**: Fast execution with low memory overhead\n- **Parallel processing**: Multi-threaded operations for large datasets\n- **Memory efficiency**: Streaming and memory-mapped file support\n- **Zero-copy operations**: NumPy integration with minimal data copying\n\n## Data Formats\n\nGtars works with standard genomic formats:\n\n- **BED**: Genomic intervals (3-column or extended)\n- **WIG\u002FBigWig**: Coverage tracks\n- **FASTA**: Reference sequences\n- **Fragment TSV**: Single-cell fragment files with barcodes\n\n## Error Handling and Debugging\n\nEnable verbose logging for troubleshooting:\n\n```python\nimport gtars\n\n# Enable debug logging\ngtars.set_log_level(\"DEBUG\")\n```\n\n```bash\n# CLI verbose mode\ngtars --verbose \u003Ccommand>\n```\n","# Gtars: Genomic Tools and Algorithms in Rust\n\n## Overview\n\nGtars is a high-performance Rust toolkit for manipulating, analyzing, and processing genomic interval data. It provides specialized tools for overlap detection, coverage analysis, tokenization for machine learning, and reference sequence management.\n\nUse this skill when working with:\n- Genomic interval files (BED format)\n- Overlap detection between genomic regions\n- Coverage track generation (WIG, BigWig)\n- Genomic ML preprocessing and tokenization\n- Fragment analysis in single-cell genomics\n- Reference sequence retrieval and validation\n\n## Installation\n\n### Python Installation\n\nInstall gtars Python bindings:\n\n```bash\nuv uv pip install gtars\n```\n\n### CLI Installation\n\nInstall command-line tools (requires Rust\u002FCargo):\n\n```bash\n# Install with all features\ncargo install gtars-cli --features \"uniwig overlaprs igd bbcache scoring fragsplit\"\n\n# Or install specific features only\ncargo install gtars-cli --features \"uniwig overlaprs\"\n```\n\n### Rust Library\n\nAdd to Cargo.toml for Rust projects:\n\n```toml\n[dependencies]\ngtars = { version = \"0.1\", features = [\"tokenizers\", \"overlaprs\"] }\n```\n\n## Core Capabilities\n\nGtars is organized into specialized modules, each focused on specific genomic analysis tasks:\n\n### 1. Overlap Detection and IGD Indexing\n\nEfficiently detect overlaps between genomic intervals using the Integrated Genome Database (IGD) data structure.\n\n**When to use:**\n- Finding overlapping regulatory elements\n- Variant annotation\n- Comparing ChIP-seq peaks\n- Identifying shared genomic features\n\n**Quick example:**\n```python\nimport gtars\n\n# Build IGD index and query overlaps\nigd = gtars.igd.build_index(\"regions.bed\")\noverlaps = igd.query(\"chr1\", 1000, 2000)\n```\n\nSee `references\u002Foverlap.md` for comprehensive overlap detection documentation.\n\n### 2. Coverage Track Generation\n\nGenerate coverage tracks from sequencing data with the uniwig module.\n\n**When to use:**\n- ATAC-seq accessibility profiles\n- ChIP-seq coverage visualization\n- RNA-seq read coverage\n- Differential coverage analysis\n\n**Quick example:**\n```bash\n# Generate BigWig coverage track\ngtars uniwig generate --input fragments.bed --output coverage.bw --format bigwig\n```\n\nSee `references\u002Fcoverage.md` for detailed coverage analysis workflows.\n\n### 3. Genomic Tokenization\n\nConvert genomic regions into discrete tokens for machine learning applications, particularly for deep learning models on genomic data.\n\n**When to use:**\n- Preprocessing for genomic ML models\n- Integration with geniml library\n- Creating position encodings\n- Training transformer models on genomic sequences\n\n**Quick example:**\n```python\nfrom gtars.tokenizers import TreeTokenizer\n\ntokenizer = TreeTokenizer.from_bed_file(\"training_regions.bed\")\ntoken = tokenizer.tokenize(\"chr1\", 1000, 2000)\n```\n\nSee `references\u002Ftokenizers.md` for tokenization documentation.\n\n### 4. Reference Sequence Management\n\nHandle reference genome sequences and compute digests following the GA4GH refget protocol.\n\n**When to use:**\n- Validating reference genome integrity\n- Extracting specific genomic sequences\n- Computing sequence digests\n- Cross-reference comparisons\n\n**Quick example:**\n```python\n# Load reference and extract sequences\nstore = gtars.RefgetStore.from_fasta(\"hg38.fa\")\nsequence = store.get_subsequence(\"chr1\", 1000, 2000)\n```\n\nSee `references\u002Frefget.md` for reference sequence operations.\n\n### 5. Fragment Processing\n\nSplit and analyze fragment files, particularly useful for single-cell genomics data.\n\n**When to use:**\n- Processing single-cell ATAC-seq data\n- Splitting fragments by cell barcodes\n- Cluster-based fragment analysis\n- Fragment quality control\n\n**Quick example:**\n```bash\n# Split fragments by clusters\ngtars fragsplit cluster-split --input fragments.tsv --clusters clusters.txt --output-dir .\u002Fby_cluster\u002F\n```\n\nSee `references\u002Fcli.md` for fragment processing commands.\n\n### 6. Fragment Scoring\n\nScore fragment overlaps against reference datasets.\n\n**When to use:**\n- Evaluating fragment enrichment\n- Comparing experimental data to references\n- Quality metrics computation\n- Batch scoring across samples\n\n**Quick example:**\n```bash\n# Score fragments against reference\ngtars scoring score --fragments fragments.bed --reference reference.bed --output scores.txt\n```\n\n## Common Workflows\n\n### Workflow 1: Peak Overlap Analysis\n\nIdentify overlapping genomic features:\n\n```python\nimport gtars\n\n# Load two region sets\npeaks = gtars.RegionSet.from_bed(\"chip_peaks.bed\")\npromoters = gtars.RegionSet.from_bed(\"promoters.bed\")\n\n# Find overlaps\noverlapping_peaks = peaks.filter_overlapping(promoters)\n\n# Export results\noverlapping_peaks.to_bed(\"peaks_in_promoters.bed\")\n```\n\n### Workflow 2: Coverage Track Pipeline\n\nGenerate coverage tracks for visualization:\n\n```bash\n# Step 1: Generate coverage\ngtars uniwig generate --input atac_fragments.bed --output coverage.wig --resolution 10\n\n# Step 2: Convert to BigWig for genome browsers\ngtars uniwig generate --input atac_fragments.bed --output coverage.bw --format bigwig\n```\n\n### Workflow 3: ML Preprocessing\n\nPrepare genomic data for machine learning:\n\n```python\nfrom gtars.tokenizers import TreeTokenizer\nimport gtars\n\n# Step 1: Load training regions\nregions = gtars.RegionSet.from_bed(\"training_peaks.bed\")\n\n# Step 2: Create tokenizer\ntokenizer = TreeTokenizer.from_bed_file(\"training_peaks.bed\")\n\n# Step 3: Tokenize regions\ntokens = [tokenizer.tokenize(r.chromosome, r.start, r.end) for r in regions]\n\n# Step 4: Use tokens in ML pipeline\n# (integrate with geniml or custom models)\n```\n\n## Python vs CLI Usage\n\n**Use Python API when:**\n- Integrating with analysis pipelines\n- Need programmatic control\n- Working with NumPy\u002FPandas\n- Building custom workflows\n\n**Use CLI when:**\n- Quick one-off analyses\n- Shell scripting\n- Batch processing files\n- Prototyping workflows\n\n## Reference Documentation\n\nComprehensive module documentation:\n\n- **`references\u002Fpython-api.md`** - Complete Python API reference with RegionSet operations, NumPy integration, and data export\n- **`references\u002Foverlap.md`** - IGD indexing, overlap detection, and set operations\n- **`references\u002Fcoverage.md`** - Coverage track generation with uniwig\n- **`references\u002Ftokenizers.md`** - Genomic tokenization for ML applications\n- **`references\u002Frefget.md`** - Reference sequence management and digests\n- **`references\u002Fcli.md`** - Command-line interface complete reference\n\n## Integration with geniml\n\nGtars serves as the foundation for the geniml Python package, providing core genomic interval operations for machine learning workflows. When working on geniml-related tasks, use gtars for data preprocessing and tokenization.\n\n## Performance Characteristics\n\n- **Native Rust performance**: Fast execution with low memory overhead\n- **Parallel processing**: Multi-threaded operations for large datasets\n- **Memory efficiency**: Streaming and memory-mapped file support\n- **Zero-copy operations**: NumPy integration with minimal data copying\n\n## Data Formats\n\nGtars works with standard genomic formats:\n\n- **BED**: Genomic intervals (3-column or extended)\n- **WIG\u002FBigWig**: Coverage tracks\n- **FASTA**: Reference sequences\n- **Fragment TSV**: Single-cell fragment files with barcodes\n\n## Error Handling and Debugging\n\nEnable verbose logging for troubleshooting:\n\n```python\nimport gtars\n\n# Enable debug logging\ngtars.set_log_level(\"DEBUG\")\n```\n\n```bash\n# CLI verbose mode\ngtars --verbose \u003Ccommand>\n```\n",{"name":5,"description":7},"main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fgtars",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill gtars",{"tool":39,"command":40},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill gtars",{"tool":42,"command":43},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill gtars","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fgtars\u002FSKILL.md",true,[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcli.md","REFERENCE","参考文档",5060,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fgtars\u002Freferences\u002Fcli.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fcoverage.md",3995,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fgtars\u002Freferences\u002Fcoverage.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Foverlap.md",3679,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fgtars\u002Freferences\u002Foverlap.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fpython-api.md",4222,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fgtars\u002Freferences\u002Fpython-api.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Frefget.md",3165,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fgtars\u002Freferences\u002Frefget.md",{"path":70,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Ftokenizers.md",2444,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fgtars\u002Freferences\u002Ftokenizers.md",[74,81,88,95,102,109],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]