[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75K7WZCNNRDE3P7N9TM9W2Q":3,"skill-same:01M75K7WZCNNRDE3P7N9TM9W2Q":56},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M75K7WZCNNRDE3P7N9TM9W2Q","trailmark",null,"Builds and queries multi-language source code graphs for security analysis. Includes pre-analysis passes for blast radius, taint propagation, privilege boundaries, and entry point enumeration. Use when analyzing call paths, mapping attack surface, finding complexity hotspots, enumerating entry points, tracing taint propagation, measuring blast radius, or building a code graph for audit prioritization. Supports 16 languages including Solidity, Cairo, Circom, Rust, Go, Python, C\u002FC++, TypeScript.","agisota\u002Fold-one","agisota","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F121413592?v=4","01M75B4BRNT67EC1NDRT8QZEP2","01M75B4BS7QR9VP580MSCPTS3X",3,"MIT","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Ftrailmark\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: trailmark\ndescription: \"Builds and queries multi-language source code graphs for security analysis. Includes pre-analysis passes for blast radius, taint propagation, privilege boundaries, and entry point enumeration. Use when analyzing call paths, mapping attack surface, finding complexity hotspots, enumerating entry points, tracing taint propagation, measuring blast radius, or building a code graph for audit prioritization. Supports 16 languages including Solidity, Cairo, Circom, Rust, Go, Python, C\u002FC++, TypeScript.\"\n---\n\n# Trailmark\n\nParses source code into a directed graph of functions, classes, calls, and\nsemantic metadata for security analysis. Supports 16 languages.\n\n## When to Use\n\n- Mapping call paths from user input to sensitive functions\n- Finding complexity hotspots for audit prioritization\n- Identifying attack surface and entrypoints\n- Understanding call relationships in unfamiliar codebases\n- Security review or audit preparation across polyglot projects\n- Adding LLM-inferred annotations (assumptions, preconditions) to code units\n- Pre-analysis before mutation testing (genotoxic skill) or diagramming\n\n## When NOT to Use\n\n- Single-file scripts where call graph adds no value (read the file directly)\n- Architecture diagrams not derived from code (use the `diagramming-code` skill or draw by hand)\n- Mutation testing triage (use the genotoxic skill, which calls trailmark internally)\n- Runtime behavior analysis (trailmark is static, not dynamic)\n\n## Rationalizations to Reject\n\n| Rationalization | Why It's Wrong | Required Action |\n|-----------------|----------------|-----------------|\n| \"I'll just read the source files manually\" | Manual reading misses call paths, blast radius, and taint data | Install trailmark and use the API |\n| \"Pre-analysis isn't needed for a quick query\" | Blast radius, taint, and privilege data are only available after `preanalysis()` | Always run `engine.preanalysis()` before handing off to other skills |\n| \"The graph is too large, I'll sample\" | Sampling misses cross-module attack paths | Build the full graph; use subgraph queries to focus |\n| \"Uncertain edges don't matter\" | Dynamic dispatch is where type confusion bugs hide | Account for `uncertain` edges in security claims |\n| \"Single-language analysis is enough\" | Polyglot repos have FFI boundaries where bugs cluster | Use the correct `--language` flag per component |\n| \"Complexity hotspots are the only thing worth checking\" | Low-complexity functions on tainted paths are high-value targets | Combine complexity with taint and blast radius data |\n\n---\n\n## Installation\n\n**MANDATORY:** If `uv run trailmark` fails (command not found, import error,\nModuleNotFoundError), install trailmark before doing anything else:\n\n```bash\nuv pip install trailmark\n```\n\n**DO NOT** fall back to \"manual verification\", \"manual analysis\", or reading\nsource files by hand as a substitute for running trailmark. The tool must be\ninstalled and used programmatically. If installation fails, report the error\nto the user instead of silently switching to manual code reading.\n\n## Quick Start\n\n```bash\n# Python (default)\nuv run trailmark analyze --summary {targetDir}\n\n# Other languages\nuv run trailmark analyze --language rust {targetDir}\nuv run trailmark analyze --language javascript {targetDir}\nuv run trailmark analyze --language go --summary {targetDir}\n\n# Complexity hotspots\nuv run trailmark analyze --complexity 10 {targetDir}\n```\n\n### Programmatic API\n\n```python\nfrom trailmark.query.api import QueryEngine\n\n# Specify language (defaults to \"python\")\nengine = QueryEngine.from_directory(\"{targetDir}\", language=\"rust\")\n\nengine.callers_of(\"function_name\")\nengine.callees_of(\"function_name\")\nengine.paths_between(\"entry_func\", \"db_query\")\nengine.complexity_hotspots(threshold=10)\nengine.attack_surface()\nengine.summary()\nengine.to_json()\n\n# Run pre-analysis (blast radius, entrypoints, privilege\n# boundaries, taint propagation)\nresult = engine.preanalysis()\n\n# Query subgraphs created by pre-analysis\nengine.subgraph_names()\nengine.subgraph(\"tainted\")\nengine.subgraph(\"high_blast_radius\")\nengine.subgraph(\"privilege_boundary\")\nengine.subgraph(\"entrypoint_reachable\")\n\n# Add LLM-inferred annotations\nfrom trailmark.models import AnnotationKind\n\nengine.annotate(\"function_name\", AnnotationKind.ASSUMPTION,\n                \"input is URL-encoded\", source=\"llm\")\n\n# Query annotations (including pre-analysis results)\nengine.annotations_of(\"function_name\")\nengine.annotations_of(\"function_name\",\n                       kind=AnnotationKind.BLAST_RADIUS)\nengine.annotations_of(\"function_name\",\n                       kind=AnnotationKind.TAINT_PROPAGATION)\n```\n\n## Pre-Analysis Passes\n\n**Always run `engine.preanalysis()` before handing off to genotoxic or\n`diagramming-code` skills.** Pre-analysis enriches the graph with four passes:\n\n1. **Blast radius estimation** — counts downstream and upstream nodes per\n   function, identifies critical high-complexity descendants\n2. **Entry point enumeration** — maps entrypoints by trust level, computes\n   reachable node sets\n3. **Privilege boundary detection** — finds call edges where trust levels\n   change (untrusted -> trusted)\n4. **Taint propagation** — marks all nodes reachable from untrusted\n   entrypoints\n\nResults are stored as annotations and named subgraphs on the graph.\n\nFor detailed documentation, see\n[references\u002Fpreanalysis-passes.md](references\u002Fpreanalysis-passes.md).\n\n## Supported Languages\n\n| Language | `--language` value | Extensions |\n| --- | --- | --- |\n| Python | `python` | `.py` |\n| JavaScript | `javascript` | `.js`, `.jsx` |\n| TypeScript | `typescript` | `.ts`, `.tsx` |\n| PHP | `php` | `.php` |\n| Ruby | `ruby` | `.rb` |\n| C | `c` | `.c`, `.h` |\n| C++ | `cpp` | `.cpp`, `.hpp`, `.cc`, `.hh`, `.cxx`, `.hxx` |\n| C# | `c_sharp` | `.cs` |\n| Java | `java` | `.java` |\n| Go | `go` | `.go` |\n| Rust | `rust` | `.rs` |\n| Solidity | `solidity` | `.sol` |\n| Cairo | `cairo` | `.cairo` |\n| Haskell | `haskell` | `.hs` |\n| Circom | `circom` | `.circom` |\n| Erlang | `erlang` | `.erl` |\n\n## Graph Model\n\n**Node kinds:** `function`, `method`, `class`, `module`, `struct`,\n`interface`, `trait`, `enum`, `namespace`, `contract`, `library`\n\n**Edge kinds:** `calls`, `inherits`, `implements`, `contains`, `imports`\n\n**Edge confidence:** `certain` (direct call, `self.method()`), `inferred`\n(attribute access on non-self object), `uncertain` (dynamic dispatch)\n\n### Per Code Unit\n- Parameters with types, return types, exception types\n- Cyclomatic complexity and branch metadata\n- Docstrings\n- Annotations: `assumption`, `precondition`, `postcondition`, `invariant`,\n  `blast_radius`, `privilege_boundary`, `taint_propagation`\n\n### Per Edge\n- Source\u002Ftarget node IDs, edge kind, confidence level\n\n### Project Level\n- Dependencies (imported packages)\n- Entrypoints with trust levels and asset values\n- Named subgraphs (populated by pre-analysis)\n\n## Key Concepts\n\n**Declared contract vs. effective input domain:** Trailmark separates what a\nfunction *declares* it accepts from what can *actually reach* it via call\npaths. Mismatches are where vulnerabilities hide:\n- **Widening**: Unconstrained data reaches a function that assumes validation\n- **Safe by coincidence**: No validation, but only safe callers exist today\n\n**Edge confidence:** Dynamic dispatch produces `uncertain` edges. Account for\nconfidence when making security claims.\n\n**Subgraphs:** Named collections of node IDs produced by pre-analysis.\nQuery with `engine.subgraph(\"name\")`. Available after `engine.preanalysis()`.\n\n## Query Patterns\n\nSee [references\u002Fquery-patterns.md](references\u002Fquery-patterns.md) for common\nsecurity analysis patterns.\n\nSee [references\u002Fpreanalysis-passes.md](references\u002Fpreanalysis-passes.md) for\npre-analysis pass documentation.\n","# Trailmark\n\nParses source code into a directed graph of functions, classes, calls, and\nsemantic metadata for security analysis. Supports 16 languages.\n\n## When to Use\n\n- Mapping call paths from user input to sensitive functions\n- Finding complexity hotspots for audit prioritization\n- Identifying attack surface and entrypoints\n- Understanding call relationships in unfamiliar codebases\n- Security review or audit preparation across polyglot projects\n- Adding LLM-inferred annotations (assumptions, preconditions) to code units\n- Pre-analysis before mutation testing (genotoxic skill) or diagramming\n\n## When NOT to Use\n\n- Single-file scripts where call graph adds no value (read the file directly)\n- Architecture diagrams not derived from code (use the `diagramming-code` skill or draw by hand)\n- Mutation testing triage (use the genotoxic skill, which calls trailmark internally)\n- Runtime behavior analysis (trailmark is static, not dynamic)\n\n## Rationalizations to Reject\n\n| Rationalization | Why It's Wrong | Required Action |\n|-----------------|----------------|-----------------|\n| \"I'll just read the source files manually\" | Manual reading misses call paths, blast radius, and taint data | Install trailmark and use the API |\n| \"Pre-analysis isn't needed for a quick query\" | Blast radius, taint, and privilege data are only available after `preanalysis()` | Always run `engine.preanalysis()` before handing off to other skills |\n| \"The graph is too large, I'll sample\" | Sampling misses cross-module attack paths | Build the full graph; use subgraph queries to focus |\n| \"Uncertain edges don't matter\" | Dynamic dispatch is where type confusion bugs hide | Account for `uncertain` edges in security claims |\n| \"Single-language analysis is enough\" | Polyglot repos have FFI boundaries where bugs cluster | Use the correct `--language` flag per component |\n| \"Complexity hotspots are the only thing worth checking\" | Low-complexity functions on tainted paths are high-value targets | Combine complexity with taint and blast radius data |\n\n---\n\n## Installation\n\n**MANDATORY:** If `uv run trailmark` fails (command not found, import error,\nModuleNotFoundError), install trailmark before doing anything else:\n\n```bash\nuv pip install trailmark\n```\n\n**DO NOT** fall back to \"manual verification\", \"manual analysis\", or reading\nsource files by hand as a substitute for running trailmark. The tool must be\ninstalled and used programmatically. If installation fails, report the error\nto the user instead of silently switching to manual code reading.\n\n## Quick Start\n\n```bash\n# Python (default)\nuv run trailmark analyze --summary {targetDir}\n\n# Other languages\nuv run trailmark analyze --language rust {targetDir}\nuv run trailmark analyze --language javascript {targetDir}\nuv run trailmark analyze --language go --summary {targetDir}\n\n# Complexity hotspots\nuv run trailmark analyze --complexity 10 {targetDir}\n```\n\n### Programmatic API\n\n```python\nfrom trailmark.query.api import QueryEngine\n\n# Specify language (defaults to \"python\")\nengine = QueryEngine.from_directory(\"{targetDir}\", language=\"rust\")\n\nengine.callers_of(\"function_name\")\nengine.callees_of(\"function_name\")\nengine.paths_between(\"entry_func\", \"db_query\")\nengine.complexity_hotspots(threshold=10)\nengine.attack_surface()\nengine.summary()\nengine.to_json()\n\n# Run pre-analysis (blast radius, entrypoints, privilege\n# boundaries, taint propagation)\nresult = engine.preanalysis()\n\n# Query subgraphs created by pre-analysis\nengine.subgraph_names()\nengine.subgraph(\"tainted\")\nengine.subgraph(\"high_blast_radius\")\nengine.subgraph(\"privilege_boundary\")\nengine.subgraph(\"entrypoint_reachable\")\n\n# Add LLM-inferred annotations\nfrom trailmark.models import AnnotationKind\n\nengine.annotate(\"function_name\", AnnotationKind.ASSUMPTION,\n                \"input is URL-encoded\", source=\"llm\")\n\n# Query annotations (including pre-analysis results)\nengine.annotations_of(\"function_name\")\nengine.annotations_of(\"function_name\",\n                       kind=AnnotationKind.BLAST_RADIUS)\nengine.annotations_of(\"function_name\",\n                       kind=AnnotationKind.TAINT_PROPAGATION)\n```\n\n## Pre-Analysis Passes\n\n**Always run `engine.preanalysis()` before handing off to genotoxic or\n`diagramming-code` skills.** Pre-analysis enriches the graph with four passes:\n\n1. **Blast radius estimation** — counts downstream and upstream nodes per\n   function, identifies critical high-complexity descendants\n2. **Entry point enumeration** — maps entrypoints by trust level, computes\n   reachable node sets\n3. **Privilege boundary detection** — finds call edges where trust levels\n   change (untrusted -> trusted)\n4. **Taint propagation** — marks all nodes reachable from untrusted\n   entrypoints\n\nResults are stored as annotations and named subgraphs on the graph.\n\nFor detailed documentation, see\n[references\u002Fpreanalysis-passes.md](references\u002Fpreanalysis-passes.md).\n\n## Supported Languages\n\n| Language | `--language` value | Extensions |\n| --- | --- | --- |\n| Python | `python` | `.py` |\n| JavaScript | `javascript` | `.js`, `.jsx` |\n| TypeScript | `typescript` | `.ts`, `.tsx` |\n| PHP | `php` | `.php` |\n| Ruby | `ruby` | `.rb` |\n| C | `c` | `.c`, `.h` |\n| C++ | `cpp` | `.cpp`, `.hpp`, `.cc`, `.hh`, `.cxx`, `.hxx` |\n| C# | `c_sharp` | `.cs` |\n| Java | `java` | `.java` |\n| Go | `go` | `.go` |\n| Rust | `rust` | `.rs` |\n| Solidity | `solidity` | `.sol` |\n| Cairo | `cairo` | `.cairo` |\n| Haskell | `haskell` | `.hs` |\n| Circom | `circom` | `.circom` |\n| Erlang | `erlang` | `.erl` |\n\n## Graph Model\n\n**Node kinds:** `function`, `method`, `class`, `module`, `struct`,\n`interface`, `trait`, `enum`, `namespace`, `contract`, `library`\n\n**Edge kinds:** `calls`, `inherits`, `implements`, `contains`, `imports`\n\n**Edge confidence:** `certain` (direct call, `self.method()`), `inferred`\n(attribute access on non-self object), `uncertain` (dynamic dispatch)\n\n### Per Code Unit\n- Parameters with types, return types, exception types\n- Cyclomatic complexity and branch metadata\n- Docstrings\n- Annotations: `assumption`, `precondition`, `postcondition`, `invariant`,\n  `blast_radius`, `privilege_boundary`, `taint_propagation`\n\n### Per Edge\n- Source\u002Ftarget node IDs, edge kind, confidence level\n\n### Project Level\n- Dependencies (imported packages)\n- Entrypoints with trust levels and asset values\n- Named subgraphs (populated by pre-analysis)\n\n## Key Concepts\n\n**Declared contract vs. effective input domain:** Trailmark separates what a\nfunction *declares* it accepts from what can *actually reach* it via call\npaths. Mismatches are where vulnerabilities hide:\n- **Widening**: Unconstrained data reaches a function that assumes validation\n- **Safe by coincidence**: No validation, but only safe callers exist today\n\n**Edge confidence:** Dynamic dispatch produces `uncertain` edges. Account for\nconfidence when making security claims.\n\n**Subgraphs:** Named collections of node IDs produced by pre-analysis.\nQuery with `engine.subgraph(\"name\")`. Available after `engine.preanalysis()`.\n\n## Query Patterns\n\nSee [references\u002Fquery-patterns.md](references\u002Fquery-patterns.md) for common\nsecurity analysis patterns.\n\nSee [references\u002Fpreanalysis-passes.md](references\u002Fpreanalysis-passes.md) for\npre-analysis pass documentation.\n",{"name":5,"description":7},"main","f37de8f681f0c0ca0e0ebab6e5fddf764ca7553d","skills\u002Ftrailmark",1,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one","https:\u002F\u002Fagisota.github.io\u002Fold-one\u002F","https:\u002F\u002Fgithub.com\u002Fagisota","pzd.world","2026-07-04 22:32:06",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add agisota\u002Fold-one --skill trailmark",{"tool":38,"command":39},"bunx","bunx skills add agisota\u002Fold-one --skill trailmark",{"tool":41,"command":42},"pnpm","pnpm dlx skills add agisota\u002Fold-one --skill trailmark","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Ftrailmark\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fpreanalysis-passes.md","REFERENCE","参考文档",4677,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Ftrailmark\u002Freferences\u002Fpreanalysis-passes.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fquery-patterns.md",3951,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Ftrailmark\u002Freferences\u002Fquery-patterns.md",[57,64,71,80,87,94],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":18},"01M75KRGZWQWE9JDBS6RX42NWV","zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-out\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M75KRCZHKE0ZYAQFFYHS0YNP","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":76,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M75KR94KYQ30DTE1P9WNDAE0","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M75KR3H13YJ9QHMD49818FA1","yara-rule-authoring","Guides authoring of high-quality YARA-X detection rules for malware identification. Use when writing, reviewing, or optimizing YARA rules. Covers naming conventions, string selection, performance optimization, migration from legacy YARA, and false positive reduction. Triggers on: YARA, YARA-X, malware detection, threat hunting, IOC, signature, crx module, dex module.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyara-rule-authoring\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M75KQMPY8A4Y8XTDD2DT0M9T","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":18},"01M75KQHNZ0ANZNJGZY6M8MDAK","x-api","X\u002FTwitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fx-api\u002FSKILL.md",[],[]]