[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BZ353TS5P9Q9MYPR65SCFM":3,"skill-same:01M6BZ353TS5P9Q9MYPR65SCFM":81},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":51,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6BZ353TS5P9Q9MYPR65SCFM","tree-sitter-language-pack",null,"Parse and extract code intelligence from 371 programming languages using tree-sitter grammars. Use when writing code that parses source, extracts structure\u002Fimports\u002Fexports\u002Fsymbols\u002Fdocstrings\u002Fcomments, detects a language, runs syntax diagnostics, or produces syntax-aware chunks for LLMs — in Rust, Python, Node.js\u002FTypeScript, or the ts-pack CLI. Covers installation, the CLI surface, the SDK surface, and parser-cache management.","xberg-io\u002Ftree-sitter-language-pack","xberg-io","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F241328462?v=4","01M6BYYMACFMK5WNT338Y71K58","Xberg.io","01M6BYYMEGM63ZCEYZJRTVS9JT",485,"MIT","https:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack\u002Fblob\u002Fmain\u002Fplugin\u002F.pi\u002Fskills\u002Ftree-sitter-language-pack\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"language pack","tree sitter","tree sitter language pack","pack","language","tree","when","parse","imports","chunks","structure","io","typescript","parser","node","cli","llms","code","writing","rust","2026-11-10 10:12:30",false,"---\ndescription: Parse and extract code intelligence from 371 programming languages using tree-sitter grammars. Use when writing code that parses source, extracts structure\u002Fimports\u002Fexports\u002Fsymbols\u002Fdocstrings\u002Fcomments, detects a language, runs syntax diagnostics, or produces syntax-aware chunks for LLMs — in Rust, Python, Node.js\u002FTypeScript, or the ts-pack CLI. Covers installation, the CLI surface, the SDK surface, and parser-cache management.\nlicense: MIT\nmetadata:\n    author: xberg-io\n    version: \"0.1.0\"\n    repository: https:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack\nname: tree-sitter-language-pack\n---\n\n\u003C!--\nAI-RULEZ :: GENERATED FILE — DO NOT EDIT\nContent-Hash: blake3:7860f629c0c291cb2e4f9cb034035fadbc4de3b90bace596a2d2348c12b5ec00\nSource-Hash: blake3:b8687cf31ac8c66a5ecc15c4f11520ff201d8db14467b7528d5120124e9753a4\nSchema-Version: v1\n-->\n\n# Tree-Sitter Language Pack\n\ntree-sitter-language-pack is a polyglot code parsing and analysis library\nwith a high-performance Rust core and polyglot bindings for 15 languages —\nPython, Node.js\u002FTypeScript, Ruby, Go, Java, C#, PHP, Elixir, Dart,\nKotlin (Android), Swift, Zig, and WebAssembly, plus a C ABI and JNI. It\ncompiles 371 tree-sitter grammars into efficient parsers and exposes code\nintelligence on top of them.\n\n## Capabilities\n\n- **Parse 371 languages** into concrete syntax trees (s-expression or JSON).\n- **Extract structure** — functions, classes, methods, modules with line\n  and byte spans, child nesting, and visibility.\n- **Extract imports and exports** — statements, sources, exported kinds.\n- **Extract symbols** — all identifiers, for search and indexing.\n- **Extract docstrings and comments** — attached to definitions or standalone.\n- **Language detection** — from a file path, an extension, or content.\n- **Syntax diagnostics** — error nodes and syntax errors with positions.\n- **Syntax-aware chunking** — split source on syntactic boundaries for LLM\n  context windows, not on arbitrary byte offsets.\n- **Custom tree-sitter queries** — run your own query patterns over a tree\n  (SDK only).\n- **Parser cache management** — download, list, inspect, and clean the\n  on-demand parser cache for offline\u002FCI use.\n- **Distribution** — 15 language bindings (including WebAssembly, a C ABI,\n  and JNI) plus the `ts-pack` CLI.\n\nUse this skill when writing code that parses source in any supported\nlanguage, extracts code metadata, chunks code for an LLM, detects a\nlanguage, or validates syntax.\n\n## When to use\n\nReach for tree-sitter-language-pack when you need a real syntax tree or\nstructured code metadata — building a code index, feeding code to an LLM\nin semantically coherent chunks, linting for syntax errors across many\nlanguages, or detecting a file's language. For plain text extraction from\ndocuments (PDF, Office, HTML), use Xberg instead.\n\n## CLI vs SDK\n\n- **CLI (`ts-pack`)** — quick one-shot parsing and extraction over files,\n  parser-cache management, and shell\u002FCI pipelines. `parse` and `process`\n  print to stdout (`process` always emits JSON). Auto-detects the language\n  from the file extension.\n- **SDK** — embed parsing in an application, run custom tree-sitter\n  queries, detect a language from raw content (not just a path), or hold\n  parsers across many calls. Use the Rust core or the Python\u002FNode bindings.\n- **MCP server (`ts-pack mcp`)** — exposes `parse`\u002F`process`\u002F`detect_language`\n  (plus language and cache tools) as agent tools, so an MCP client can parse\n  and analyze code directly with no shell-out.\n  This plugin auto-registers it; see the **tree-sitter-language-pack-using-the-mcp-server** skill.\n\nPrefer the CLI for ad-hoc work in an agent session; prefer the SDK when the\nresult feeds back into a larger program; prefer the MCP server when the agent\nshould call parsing directly as a tool.\n\n## Installation\n\n### CLI\n\n```bash\nbrew install xberg-io\u002Ftap\u002Fts-pack\n# or run without a persistent install (the CLI proxy package self-installs the binary):\nnpx @xberg-io\u002Fts-pack-cli --help\n# or download a prebuilt binary from the latest GitHub release:\n#   https:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack\u002Freleases\u002Flatest\n# or install from crates.io:\ncargo install ts-pack-cli\n# binary is installed as `ts-pack`\n```\n\n### Python\n\n```bash\npip install tree-sitter-language-pack\n# or: uv add tree-sitter-language-pack\n```\n\n### Node.js \u002F TypeScript\n\n```bash\nnpm install @xberg-io\u002Ftree-sitter-language-pack\n# or: pnpm add @xberg-io\u002Ftree-sitter-language-pack\n```\n\n### Rust\n\n```toml\n# Cargo.toml\n[dependencies]\ntree-sitter-language-pack = { version = \"1\", features = [\"download\"] }\n```\n\nOther bindings: Ruby (`gem install tree_sitter_language_pack`), Go, Java,\nC#, PHP, Elixir, Dart, Kotlin (Android), Swift, Zig, and WebAssembly\n(`npm install @xberg-io\u002Ftree-sitter-language-pack-wasm`). See\n\u003Chttps:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack>.\n\n## CLI surface\n\n`ts-pack` has these subcommands:\n\n| Command | Purpose |\n| ------- | ------- |\n| `parse \u003Cfile>` | Parse a file into a syntax tree (`--format sexp|json`). |\n| `process \u003Cfile>` | Run the code-intelligence pipeline, emit JSON. |\n| `detect`* | No standalone command — `parse`\u002F`process` auto-detect from the extension. Use the SDK for content detection. |\n| `list` | List available languages (`--downloaded`, `--manifest`, `--filter`). |\n| `info \u003Clanguage>` | Show whether a language is known and cached. |\n| `download [langs...]` | Download parser libraries (`--all`, `--groups`, `--fresh`). |\n| `clean` | Remove all cached parser libraries (`--force`). |\n| `cache-dir` | Print the effective cache directory. |\n| `init` | Write a `language-pack.toml` config (`--languages`, `--cache-dir`). |\n| `completions \u003Cshell>` | Generate shell completions. |\n| `mcp` | Start the MCP server (`--transport stdio`). |\n\n\\* Language detection is implicit in `parse`\u002F`process`. There is no\n`detect` or `validate` subcommand; diagnostics come from\n`process --diagnostics`.\n\n### Parse\n\n```bash\nts-pack parse src\u002Fmain.rs                 # s-expression tree (auto-detect)\nts-pack parse src\u002Fmain.rs --format json   # { language, sexp, has_errors }\nts-pack parse - --language python         # read from stdin, explicit language\n```\n\n### Process (code intelligence)\n\n```bash\n# Defaults to structure + imports + exports when no feature flags are given:\nts-pack process src\u002Fapp.ts\n\n# Pick features explicitly:\nts-pack process src\u002Fapp.ts --structure --imports --symbols --docstrings\n\n# Everything:\nts-pack process src\u002Fapp.ts --all\n\n# Syntax-aware chunks (bytes) for an LLM:\nts-pack process src\u002Fapp.ts --chunk-size 2000\n\n# Syntax diagnostics:\nts-pack process src\u002Fapp.ts --diagnostics\n```\n\n`process` always prints JSON. Top-level keys: `language`, `metrics`,\n`structure`, `imports`, `exports`, `comments`, `docstrings`, `symbols`,\n`diagnostics`, and `chunks` (when `--chunk-size` is set).\n\n### SDK quick start\n\n```python\nfrom tree_sitter_language_pack import process, ProcessConfig, detect_language_from_path\n\nconfig = ProcessConfig(\"python\", symbols=True, docstrings=True)  # structure\u002Fimports\u002Fexports default to True\nresult = process(source_code, config)\nfor item in result.structure:                 # ProcessResult is an object, not a dict\n    print(item.kind, item.name, item.span.start_line)\n\n# Path-based detection (use detect_language_from_content for raw text;\n# see the detecting-languages skill):\nlang = detect_language_from_path(\"src\u002Fapp.py\")\n```\n\n```typescript\nimport { process, detectLanguageFromPath } from \"@xberg-io\u002Ftree-sitter-language-pack\";\n\nconst lang = detectLanguageFromPath(\"src\u002Fapp.ts\");\nconst result = process(source, { language: lang ?? \"typescript\", structure: true, imports: true });\n```\n\n## Parser cache\n\nParsers download on demand the first time a language is used and are cached\nlocally. For offline or CI runs, prefetch:\n\n```bash\nts-pack download python rust typescript   # specific languages\nts-pack download --all                    # everything\nts-pack download --groups all             # by group (see manifest_groups())\nts-pack list --downloaded                 # what is cached\nts-pack cache-dir                         # where the cache lives\nts-pack clean --force                     # wipe the cache\n```\n\nSee the `tree-sitter-language-pack-managing-parsers` skill for the full cache workflow.\n\n## Related skills\n\n- `tree-sitter-language-pack-parsing-source` — parse a file into a syntax tree \u002F s-expression.\n- `tree-sitter-language-pack-extracting-code-structure` — `process` with structure\u002Fimports\u002Fexports\u002F\n  symbols\u002Fdocstrings.\n- `tree-sitter-language-pack-chunking-for-llms` — `--chunk-size` syntax-aware splitting.\n- `tree-sitter-language-pack-detecting-languages` — detect by path, extension, or content.\n- `tree-sitter-language-pack-managing-parsers` — download\u002Fclean\u002Flist\u002Finfo parser-cache management.\n- `tree-sitter-language-pack-using-the-mcp-server` — call `parse`\u002F`process`\u002F`detect_language` over MCP\n  instead of the CLI.\n\nFull documentation: \u003Chttps:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack>\n","\u003C!--\nAI-RULEZ :: GENERATED FILE — DO NOT EDIT\nContent-Hash: blake3:7860f629c0c291cb2e4f9cb034035fadbc4de3b90bace596a2d2348c12b5ec00\nSource-Hash: blake3:b8687cf31ac8c66a5ecc15c4f11520ff201d8db14467b7528d5120124e9753a4\nSchema-Version: v1\n-->\n\n# Tree-Sitter Language Pack\n\ntree-sitter-language-pack is a polyglot code parsing and analysis library\nwith a high-performance Rust core and polyglot bindings for 15 languages —\nPython, Node.js\u002FTypeScript, Ruby, Go, Java, C#, PHP, Elixir, Dart,\nKotlin (Android), Swift, Zig, and WebAssembly, plus a C ABI and JNI. It\ncompiles 371 tree-sitter grammars into efficient parsers and exposes code\nintelligence on top of them.\n\n## Capabilities\n\n- **Parse 371 languages** into concrete syntax trees (s-expression or JSON).\n- **Extract structure** — functions, classes, methods, modules with line\n  and byte spans, child nesting, and visibility.\n- **Extract imports and exports** — statements, sources, exported kinds.\n- **Extract symbols** — all identifiers, for search and indexing.\n- **Extract docstrings and comments** — attached to definitions or standalone.\n- **Language detection** — from a file path, an extension, or content.\n- **Syntax diagnostics** — error nodes and syntax errors with positions.\n- **Syntax-aware chunking** — split source on syntactic boundaries for LLM\n  context windows, not on arbitrary byte offsets.\n- **Custom tree-sitter queries** — run your own query patterns over a tree\n  (SDK only).\n- **Parser cache management** — download, list, inspect, and clean the\n  on-demand parser cache for offline\u002FCI use.\n- **Distribution** — 15 language bindings (including WebAssembly, a C ABI,\n  and JNI) plus the `ts-pack` CLI.\n\nUse this skill when writing code that parses source in any supported\nlanguage, extracts code metadata, chunks code for an LLM, detects a\nlanguage, or validates syntax.\n\n## When to use\n\nReach for tree-sitter-language-pack when you need a real syntax tree or\nstructured code metadata — building a code index, feeding code to an LLM\nin semantically coherent chunks, linting for syntax errors across many\nlanguages, or detecting a file's language. For plain text extraction from\ndocuments (PDF, Office, HTML), use Xberg instead.\n\n## CLI vs SDK\n\n- **CLI (`ts-pack`)** — quick one-shot parsing and extraction over files,\n  parser-cache management, and shell\u002FCI pipelines. `parse` and `process`\n  print to stdout (`process` always emits JSON). Auto-detects the language\n  from the file extension.\n- **SDK** — embed parsing in an application, run custom tree-sitter\n  queries, detect a language from raw content (not just a path), or hold\n  parsers across many calls. Use the Rust core or the Python\u002FNode bindings.\n- **MCP server (`ts-pack mcp`)** — exposes `parse`\u002F`process`\u002F`detect_language`\n  (plus language and cache tools) as agent tools, so an MCP client can parse\n  and analyze code directly with no shell-out.\n  This plugin auto-registers it; see the **tree-sitter-language-pack-using-the-mcp-server** skill.\n\nPrefer the CLI for ad-hoc work in an agent session; prefer the SDK when the\nresult feeds back into a larger program; prefer the MCP server when the agent\nshould call parsing directly as a tool.\n\n## Installation\n\n### CLI\n\n```bash\nbrew install xberg-io\u002Ftap\u002Fts-pack\n# or run without a persistent install (the CLI proxy package self-installs the binary):\nnpx @xberg-io\u002Fts-pack-cli --help\n# or download a prebuilt binary from the latest GitHub release:\n#   https:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack\u002Freleases\u002Flatest\n# or install from crates.io:\ncargo install ts-pack-cli\n# binary is installed as `ts-pack`\n```\n\n### Python\n\n```bash\npip install tree-sitter-language-pack\n# or: uv add tree-sitter-language-pack\n```\n\n### Node.js \u002F TypeScript\n\n```bash\nnpm install @xberg-io\u002Ftree-sitter-language-pack\n# or: pnpm add @xberg-io\u002Ftree-sitter-language-pack\n```\n\n### Rust\n\n```toml\n# Cargo.toml\n[dependencies]\ntree-sitter-language-pack = { version = \"1\", features = [\"download\"] }\n```\n\nOther bindings: Ruby (`gem install tree_sitter_language_pack`), Go, Java,\nC#, PHP, Elixir, Dart, Kotlin (Android), Swift, Zig, and WebAssembly\n(`npm install @xberg-io\u002Ftree-sitter-language-pack-wasm`). See\n\u003Chttps:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack>.\n\n## CLI surface\n\n`ts-pack` has these subcommands:\n\n| Command | Purpose |\n| ------- | ------- |\n| `parse \u003Cfile>` | Parse a file into a syntax tree (`--format sexp|json`). |\n| `process \u003Cfile>` | Run the code-intelligence pipeline, emit JSON. |\n| `detect`* | No standalone command — `parse`\u002F`process` auto-detect from the extension. Use the SDK for content detection. |\n| `list` | List available languages (`--downloaded`, `--manifest`, `--filter`). |\n| `info \u003Clanguage>` | Show whether a language is known and cached. |\n| `download [langs...]` | Download parser libraries (`--all`, `--groups`, `--fresh`). |\n| `clean` | Remove all cached parser libraries (`--force`). |\n| `cache-dir` | Print the effective cache directory. |\n| `init` | Write a `language-pack.toml` config (`--languages`, `--cache-dir`). |\n| `completions \u003Cshell>` | Generate shell completions. |\n| `mcp` | Start the MCP server (`--transport stdio`). |\n\n\\* Language detection is implicit in `parse`\u002F`process`. There is no\n`detect` or `validate` subcommand; diagnostics come from\n`process --diagnostics`.\n\n### Parse\n\n```bash\nts-pack parse src\u002Fmain.rs                 # s-expression tree (auto-detect)\nts-pack parse src\u002Fmain.rs --format json   # { language, sexp, has_errors }\nts-pack parse - --language python         # read from stdin, explicit language\n```\n\n### Process (code intelligence)\n\n```bash\n# Defaults to structure + imports + exports when no feature flags are given:\nts-pack process src\u002Fapp.ts\n\n# Pick features explicitly:\nts-pack process src\u002Fapp.ts --structure --imports --symbols --docstrings\n\n# Everything:\nts-pack process src\u002Fapp.ts --all\n\n# Syntax-aware chunks (bytes) for an LLM:\nts-pack process src\u002Fapp.ts --chunk-size 2000\n\n# Syntax diagnostics:\nts-pack process src\u002Fapp.ts --diagnostics\n```\n\n`process` always prints JSON. Top-level keys: `language`, `metrics`,\n`structure`, `imports`, `exports`, `comments`, `docstrings`, `symbols`,\n`diagnostics`, and `chunks` (when `--chunk-size` is set).\n\n### SDK quick start\n\n```python\nfrom tree_sitter_language_pack import process, ProcessConfig, detect_language_from_path\n\nconfig = ProcessConfig(\"python\", symbols=True, docstrings=True)  # structure\u002Fimports\u002Fexports default to True\nresult = process(source_code, config)\nfor item in result.structure:                 # ProcessResult is an object, not a dict\n    print(item.kind, item.name, item.span.start_line)\n\n# Path-based detection (use detect_language_from_content for raw text;\n# see the detecting-languages skill):\nlang = detect_language_from_path(\"src\u002Fapp.py\")\n```\n\n```typescript\nimport { process, detectLanguageFromPath } from \"@xberg-io\u002Ftree-sitter-language-pack\";\n\nconst lang = detectLanguageFromPath(\"src\u002Fapp.ts\");\nconst result = process(source, { language: lang ?? \"typescript\", structure: true, imports: true });\n```\n\n## Parser cache\n\nParsers download on demand the first time a language is used and are cached\nlocally. For offline or CI runs, prefetch:\n\n```bash\nts-pack download python rust typescript   # specific languages\nts-pack download --all                    # everything\nts-pack download --groups all             # by group (see manifest_groups())\nts-pack list --downloaded                 # what is cached\nts-pack cache-dir                         # where the cache lives\nts-pack clean --force                     # wipe the cache\n```\n\nSee the `tree-sitter-language-pack-managing-parsers` skill for the full cache workflow.\n\n## Related skills\n\n- `tree-sitter-language-pack-parsing-source` — parse a file into a syntax tree \u002F s-expression.\n- `tree-sitter-language-pack-extracting-code-structure` — `process` with structure\u002Fimports\u002Fexports\u002F\n  symbols\u002Fdocstrings.\n- `tree-sitter-language-pack-chunking-for-llms` — `--chunk-size` syntax-aware splitting.\n- `tree-sitter-language-pack-detecting-languages` — detect by path, extension, or content.\n- `tree-sitter-language-pack-managing-parsers` — download\u002Fclean\u002Flist\u002Finfo parser-cache management.\n- `tree-sitter-language-pack-using-the-mcp-server` — call `parse`\u002F`process`\u002F`detect_language` over MCP\n  instead of the CLI.\n\nFull documentation: \u003Chttps:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack>\n",{"name":5,"license":15,"metadata":49,"description":7},{"author":9,"version":50,"repository":51},"0.1.0","https:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack","main","6403d3051157d3808dcdca49aeb0c211742d1d61","plugin\u002F.pi\u002Fskills\u002Ftree-sitter-language-pack",71,"https:\u002F\u002Fdocs.tree-sitter-language-pack.xberg.io","https:\u002F\u002Fgithub.com\u002Fxberg-io","https:\u002F\u002Fxberg.io","Open-source content intelligence with a Rust core: documents, web, LLMs and code, with native bindings for every major language.","2026-11-07 18:08:38",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add xberg-io\u002Ftree-sitter-language-pack --skill tree-sitter-language-pack",{"tool":67,"command":68},"bunx","bunx skills add xberg-io\u002Ftree-sitter-language-pack --skill tree-sitter-language-pack",{"tool":70,"command":71},"pnpm","pnpm dlx skills add xberg-io\u002Ftree-sitter-language-pack --skill tree-sitter-language-pack","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack\u002Fblob\u002Fmain\u002Fplugin\u002F.pi\u002Fskills\u002Ftree-sitter-language-pack\u002FSKILL.md",true,[75],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"index.md","REFERENCE","参考文档",729,"https:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack\u002Fblob\u002Fmain\u002Fplugin\u002F.pi\u002Fskills\u002Ftree-sitter-language-pack\u002Findex.md",[82,88,113,130,148,163],{"skillNo":83,"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":84,"categories":85,"keywords":87,"publishedAt":44},"01M6BZ48YBWAZH9X1XZ6QVA5TD","https:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack\u002Fblob\u002Fmain\u002Fskills\u002Ftree-sitter-language-pack\u002FSKILL.md",[86],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[26,24,25,29,28,27,43,42,41,40,39,38,37,36,35,34,33,32,31,30],{"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":102,"publishedAt":44},"01M6BZ461Q0A0TZJG56G6J5QF0","tree-sitter-language-pack-using-the-mcp-server","Use when parsing source, extracting code structure, or detecting a language through the tree-sitter-language-pack MCP server's tools, rather than shelling out to the ts-pack CLI. Covers the tool surface, the auto-installing launcher, and when MCP beats the CLI or SDK.","https:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack\u002Fblob\u002Fmain\u002Fskills\u002Ftree-sitter-language-pack-using-the-mcp-server\u002FSKILL.md",[94,99],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":100,"categoryName":101,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000023","Skill与智能体开发",[103,104,26,105,106,24,25,29,28,27,41,39,107,108,109,110,34,111,112,30],"tree sitter language pack using the mcp server","MCP","mcp server","server","detecting","extracting","launcher","auto","source","Tools",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":44},"01M6BZ437CE3DZQ22GYHMNMMVK","tree-sitter-language-pack-parsing-source","Use when the user wants a tree-sitter syntax tree for a source file — an s-expression dump or JSON tree. Covers `ts-pack parse`, language auto-detection vs `--language`, stdin input, and reading `has_errors`.","https:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack\u002Fblob\u002Fmain\u002Fskills\u002Ftree-sitter-language-pack-parsing-source\u002FSKILL.md",[],[120,121,26,24,25,29,111,28,27,122,123,124,125,126,127,110,128,129,31,30],"parsing","tree sitter language pack parsing source","file","json","syntax","for","errors","expression","use","reading",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":44},"01M6BZ40QMB2C6QF2N09MM15GF","tree-sitter-language-pack-managing-parsers","Use when the user needs to manage the tree-sitter parser cache — prefetch parsers for offline or CI runs, list what is downloaded, inspect a language, find the cache directory, or clean it. Covers `ts-pack download`, `list`, `info`, `cache-dir`, `clean`, and `init`.","https:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack\u002Fblob\u002Fmain\u002Fskills\u002Ftree-sitter-language-pack-managing-parsers\u002FSKILL.md",[],[137,138,26,24,25,29,28,27,139,140,141,142,143,125,144,145,146,128,147,30],"parsers","tree sitter language pack managing parsers","ci","init","prefetch","cache","find","inspect","manage","clean","info",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":155,"publishedAt":44},"01M6BZ3Y1E46H4CPXVJD6SB03D","tree-sitter-language-pack-extracting-code-structure","Use when the user wants structured code metadata from a source file — functions, classes, imports, exports, symbols, docstrings, comments, or syntax diagnostics. Covers `ts-pack process` feature flags, the JSON result shape, and the default feature set.","https:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack\u002Fblob\u002Fmain\u002Fskills\u002Ftree-sitter-language-pack-extracting-code-structure\u002FSKILL.md",[154],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[156,26,41,24,25,108,34,29,28,27,157,158,159,124,160,161,111,32,162,30],"tree sitter language pack extracting code structure","extracting code structure","code structure","SET","default","flags","result",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":44},"01M6BZ3VAJEY26GESPCWQ2JSXA","tree-sitter-language-pack-detecting-languages","Use when the user wants to know which programming language a file or snippet is. Covers implicit detection in `ts-pack parse`\u002F`process`, confirming support with `ts-pack list`\u002F`info`, and the SDK detection functions for path, extension, and raw content.","https:\u002F\u002Fgithub.com\u002Fxberg-io\u002Ftree-sitter-language-pack\u002Fblob\u002Fmain\u002Fskills\u002Ftree-sitter-language-pack-detecting-languages\u002FSKILL.md",[],[170,26,24,25,29,107,28,27,171,122,172,173,174,125,128,175,176,147,31,30],"tree sitter language pack detecting languages","programming language","programming","support","which","functions","with"]