all publishers

kreuzberg-dev

@kreuzberg-dev source repo

164 published skills · page 1 of 2

  1. ▌
    API 4 · kreuzberg-dev
    Use html-to-markdown-rs api reference documentation.
    887 repo stars
  2. ▌
    CLI 4 · kreuzberg-dev
    Use html-to-markdown-rs cli reference documentation.
    887 repo stars
  3. ▌
    MCP 4 · kreuzberg-dev
    Use html-to-markdown-rs mcp reference documentation.
    887 repo stars
  4. ▌
    Using The MCP Server 11 · kreuzberg-dev
    Use when converting HTML to Markdown or extracting metadata and tables through the html-to-markdown MCP server's tools, rather than shelling out to the CLI. Covers the tool surface, the auto-installing launcher, and when MCP beats the CLI or SDK.
    887 repo stars
  5. ▌
    Release Workflow 2 · kreuzberg-dev
    How to cut a release of the xberg-io/actions repo — clean-tree + poly/tests preconditions, CHANGELOG rollover, commit and push to main, then the two-tag scheme this repo uses (create a NEW immutable `vX.Y.Z` annotated tag AND force-move the floating major `v1` tag to the same commit so every consumer pinning `@v1` picks up the release). Load when cutting/releasing a new version of the actions repo, or when the floating `v1` tag needs to be advanced.
    887 repo stars
  6. ▌
    Liter LLM 4 · kreuzberg-dev
    Universal LLM API client for 165 providers with native bindings for 14 languages. Use when writing code that calls LLM APIs via liter-llm in Python, TypeScript, Rust, Go, Java, C#, Ruby, PHP, Elixir, WASM, or C, when running the OpenAI-compatible proxy, or when calling LLMs through the MCP server. Covers chat, streaming, tool calling, embeddings, image generation, speech, transcription, moderation, web search, OCR, reranking, provider routing, middleware, and configuration.
    887 repo stars
  7. ▌
    Calling Llms 5 · kreuzberg-dev
    Use when sending chat completions through liter-llm and routing to a specific provider via the `provider/model` prefix. Covers the chat call shape, provider routing, model_hint, message roles, and error categories.
    887 repo stars
  8. ▌
    Tool Calling 5 · kreuzberg-dev
    Use when defining functions/tools for an LLM to call through liter-llm, or requesting structured JSON outputs. Covers tool schemas, tool_calls handling, and response formats.
    887 repo stars
  9. ▌
    Running The Proxy 4 · kreuzberg-dev
    Use when running the `liter-llm api` OpenAI-compatible gateway — virtual keys, per-key rate limits, budgets, cost tracking, and model routing. Covers the TOML config and the 22 REST endpoints.
    887 repo stars
  10. ▌
    Streaming Responses 4 · kreuzberg-dev
    Use when streaming tokens incrementally from an LLM via liter-llm over SSE or async iterators. Covers chat_stream, delta handling, and null-content chunks.
    887 repo stars
  11. ▌
    Embeddings And Search 5 · kreuzberg-dev
    Use when generating embeddings, calling the 12 web-search providers, or running OCR over documents with the 4 OCR providers through liter-llm. Covers embed, search, and ocr methods plus reranking.
    887 repo stars
  12. ▌
    Converting HTML 4 · kreuzberg-dev
    Use when converting HTML to Markdown, Djot, or plain text. Covers output formats, heading and code-block styles, lists, escaping, wrapping, and HTML preprocessing.
    887 repo stars
  13. ▌
    HTML To Markdown 4 · kreuzberg-dev bundle
    Convert HTML to Markdown, Djot, or plain text with structured extraction. Use when writing code that calls html-to-markdown APIs in Rust, Python, TypeScript, Go, Ruby, PHP, Java, C#, Elixir, R, C, or WASM. Covers installation, conversion, configuration, metadata extraction, tables, document structure, inline images, URL fetching, and CLI usage.
    887 repo stars
  14. ▌
    Extracting Tables 5 · kreuzberg-dev
    Use when extracting tabular data from HTML. Covers GFM Markdown tables, the structured tables array (grid cells plus pre-rendered markdown), and HTML line breaks in table cells.
    887 repo stars
  15. ▌
    Extracting Metadata 4 · kreuzberg-dev
    Use when extracting metadata from HTML — title, description, language, Open Graph, JSON-LD / Microdata / RDFa, headers, links, and images. Covers the --json output shape and the --extract-metadata flag.
    887 repo stars
  16. ▌
    Fetching And Converting Urls 5 · kreuzberg-dev
    Use when fetching a live URL and converting it to Markdown. Covers --url, custom user agents, preprocessing for noisy pages, and the --json ConversionResult shape.
    887 repo stars
  17. ▌
    API 3 · kreuzberg-dev
    Use tree-sitter-language-pack api reference documentation.
    887 repo stars
  18. ▌
    CLI 3 · kreuzberg-dev
    Use tree-sitter-language-pack cli reference documentation.
    887 repo stars
  19. ▌
    MCP 3 · kreuzberg-dev
    Use tree-sitter-language-pack mcp reference documentation.
    887 repo stars
  20. ▌
    Parsing Source 5 · kreuzberg-dev
    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`.
    887 repo stars
  21. ▌
    Managing Parsers 4 · kreuzberg-dev
    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`.
    887 repo stars
  22. ▌
    Chunking For Llms 5 · kreuzberg-dev
    Use when the user wants to split source code into chunks for an LLM context window without breaking syntax mid-construct. Covers `ts-pack process --chunk-size`, why syntax-aware splits beat fixed-byte splits, picking a size, and the chunk JSON shape.
    887 repo stars
  23. ▌
    Detecting Languages 4 · kreuzberg-dev
    Use when the user wants to know which programming language a file or snippet is. Covers implicit detection in `ts-pack parse`/`process`, confirming support with `ts-pack list`/`info`, and the SDK detection functions for path, extension, and raw content.
    887 repo stars
  24. ▌
    Using The MCP Server 9 · kreuzberg-dev
    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.
    887 repo stars
  25. ▌
    Extracting Code Structure 4 · kreuzberg-dev
    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.
    887 repo stars
  26. ▌
    Tree Sitter Language Pack 4 · kreuzberg-dev
    Parse and extract code intelligence from 371 programming languages using tree-sitter grammars. Use when writing code that parses source, extracts structure/imports/exports/symbols/docstrings/comments, detects a language, runs syntax diagnostics, or produces syntax-aware chunks for LLMs — in Rust, Python, Node.js/TypeScript, or the ts-pack CLI. Covers installation, the CLI surface, the SDK surface, and parser-cache management.
    887 repo stars
  27. ▌
    Using The MCP Server 10 · kreuzberg-dev
    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.
    887 repo stars
  28. ▌
    API 2 · kreuzberg-dev
    Use liter-llm api reference documentation.
    887 repo stars
  29. ▌
    CLI 2 · kreuzberg-dev
    Use liter-llm cli reference documentation.
    887 repo stars
  30. ▌
    MCP 2 · kreuzberg-dev
    Use liter-llm mcp reference documentation.
    887 repo stars
  31. ▌
    Parsing Source 3 · kreuzberg-dev
    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`.
    887 repo stars
  32. ▌
    Extracting Metadata 3 · kreuzberg-dev
    Use when extracting metadata from HTML — title, description, language, Open Graph, JSON-LD / Microdata / RDFa, headers, links, and images. Covers the --json output shape and the --extract-metadata flag.
    887 repo stars
  33. ▌
    Using The MCP Server 7 · kreuzberg-dev
    Use when converting HTML to Markdown or extracting metadata and tables through the html-to-markdown MCP server's tools, rather than shelling out to the CLI. Covers the tool surface, the auto-installing launcher, and when MCP beats the CLI or SDK.
    887 repo stars
  34. ▌
    Chunking For Llms 3 · kreuzberg-dev
    Use when the user wants to split source code into chunks for an LLM context window without breaking syntax mid-construct. Covers `ts-pack process --chunk-size`, why syntax-aware splits beat fixed-byte splits, picking a size, and the chunk JSON shape.
    887 repo stars
  35. ▌
    Fetching And Converting Urls 3 · kreuzberg-dev
    Use when fetching a live URL and converting it to Markdown. Covers --url, custom user agents, preprocessing for noisy pages, and the --json ConversionResult shape.
    887 repo stars
  36. ▌
    Parsing Source 4 · kreuzberg-dev
    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`.
    887 repo stars
  37. ▌
    Managing Parsers 3 · kreuzberg-dev
    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`.
    887 repo stars
  38. ▌
    Chunking For Llms 4 · kreuzberg-dev
    Use when the user wants to split source code into chunks for an LLM context window without breaking syntax mid-construct. Covers `ts-pack process --chunk-size`, why syntax-aware splits beat fixed-byte splits, picking a size, and the chunk JSON shape.
    887 repo stars
  39. ▌
    Fetching And Converting Urls 4 · kreuzberg-dev
    Use when fetching a live URL and converting it to Markdown. Covers --url, custom user agents, preprocessing for noisy pages, and the --json ConversionResult shape.
    887 repo stars
  40. ▌
    Detecting Languages 3 · kreuzberg-dev
    Use when the user wants to know which programming language a file or snippet is. Covers implicit detection in `ts-pack parse`/`process`, confirming support with `ts-pack list`/`info`, and the SDK detection functions for path, extension, and raw content.
    887 repo stars
  41. ▌
    Using The MCP Server 8 · kreuzberg-dev
    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.
    887 repo stars
  42. ▌
    Extracting Code Structure 3 · kreuzberg-dev
    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.
    887 repo stars
  43. ▌
    Tree Sitter Language Pack 3 · kreuzberg-dev
    Parse and extract code intelligence from 306 programming languages using tree-sitter grammars. Use when writing code that parses source, extracts structure/imports/exports/symbols/docstrings/comments, detects a language, runs syntax diagnostics, or produces syntax-aware chunks for LLMs — in Rust, Python, Node.js/TypeScript, or the ts-pack CLI. Covers installation, the CLI surface, the SDK surface, and parser-cache management.
    887 repo stars
  44. ▌
    Xberg 3 · kreuzberg-dev bundle
    Extract text, tables, metadata, and images from 91+ document formats (PDF, Office, images, HTML, email, archives, academic) using Xberg. Use when writing code that calls Xberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output format), batch processing, error handling, and plugins.
    887 repo stars
  45. ▌
    Crawlberg 2 · kreuzberg-dev
    Crawl, scrape, and convert websites to Markdown using the local crawlberg CLI and its MCP server. Use when the user wants to fetch a page, follow links across a domain, enumerate URLs, or drive a real browser. Covers installation, the subcommands (scrape, crawl, map, interact, batch-scrape, batch-crawl, download, citations, version, mcp, serve), output formats (JSON + Markdown), browser fallback, and when to prefer the MCP server over shelling out.
    887 repo stars
  46. ▌
    Chunking 2 · kreuzberg-dev
    Use when splitting extracted text into chunks for LLM context windows or RAG ingestion. Covers chunk size, overlap, markdown/yaml/semantic chunkers, tokenizer-based sizing, and the standalone `chunk` command.
    887 repo stars
  47. ▌
    Mapping Urls 2 · kreuzberg-dev
    Use when the user wants the list of URLs on a site rather than the page content — sitemap analysis, link planning, or seeding another tool. Covers `crawlberg map URL` with `--limit`, `--search`, robots, output, and how it differs from a full crawl.
    887 repo stars
  48. ▌
    Calling Llms 3 · kreuzberg-dev
    Use when sending chat completions through liter-llm and routing to a specific provider via the `provider/model` prefix. Covers the chat call shape, provider routing, model_hint, message roles, and error categories.
    887 repo stars
  49. ▌
    Tool Calling 3 · kreuzberg-dev
    Use when defining functions/tools for an LLM to call through liter-llm, or requesting structured JSON outputs. Covers tool schemas, tool_calls handling, and response formats.
    887 repo stars
  50. ▌
    Liter LLM 3 · kreuzberg-dev
    Universal LLM API client for 143 providers with native bindings for 14 languages. Use when writing code that calls LLM APIs via liter-llm in Python, TypeScript, Rust, Go, Java, C#, Ruby, PHP, Elixir, WASM, or C, when running the OpenAI-compatible proxy, or when calling LLMs through the MCP server. Covers chat, streaming, tool calling, embeddings, image generation, speech, transcription, moderation, web search, OCR, reranking, provider routing, middleware, and configuration.
    887 repo stars
  51. ▌
    Serving The API 2 · kreuzberg-dev
    Use when the user wants a long-running HTTP service for scrape/crawl/map instead of one-shot CLI calls or the MCP server — for example wiring crawlberg into other apps over REST. Covers `crawlberg serve`, the Firecrawl-v1-compatible endpoints, `--host`/`--port`, and when to prefer it.
    887 repo stars
  52. ▌
    Headless Fallback 2 · kreuzberg-dev
    Use when a static fetch returns nothing useful and the page needs a real browser. Covers `--browser-mode auto|always|never`, external CDP via `--browser-endpoint`, symptoms of JS-only pages and WAF blocks, and the performance cost.
    887 repo stars
  53. ▌
    Calling Llms 4 · kreuzberg-dev
    Use when sending chat completions through liter-llm and routing to a specific provider via the `provider/model` prefix. Covers the chat call shape, provider routing, model_hint, message roles, and error categories.
    887 repo stars
  54. ▌
    Tool Calling 4 · kreuzberg-dev
    Use when defining functions/tools for an LLM to call through liter-llm, or requesting structured JSON outputs. Covers tool schemas, tool_calls handling, and response formats.
    887 repo stars
  55. ▌
    Batch Extraction 2 · kreuzberg-dev
    Use when extracting from many files at once with shared config, bounded parallelism, per-file overrides, and error recovery. Covers the `batch` command, `--file-configs`, `--max-concurrent`, and output layout.
    887 repo stars
  56. ▌
    Picking A Format 2 · kreuzberg-dev
    Use when choosing an output format for extracted documents — text, markdown, djot, html, or JSON. Maps consumer (LLM, parser, archive) to the right `--format` / `--content-format` pair.
    887 repo stars
  57. ▌
    Extracting Tables 3 · kreuzberg-dev
    Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits.
    887 repo stars
  58. ▌
    Extracting Keywords 2 · kreuzberg-dev
    Use when extracting keywords (YAKE/RAKE) from documents — and, secondarily, when detecting document language or generating embeddings for RAG and search. Covers the keyword config (and its feature gating), `--detect-language`, and the standalone `embed` command with real flags.
    887 repo stars
  59. ▌
    Extracting With Ocr 2 · kreuzberg-dev
    Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning.
    887 repo stars
  60. ▌
    Embeddings And Search 3 · kreuzberg-dev
    Use when generating embeddings, calling the 12 web-search providers, or running OCR over documents with the 4 OCR providers through liter-llm. Covers embed, search, and ocr methods plus reranking.
    887 repo stars
  61. ▌
    Automating The Browser 2 · kreuzberg-dev
    Use when extracting a page needs scripted interaction first — click, type, press a key, scroll, wait, screenshot, or run JS before capturing the DOM. Covers `crawlberg interact URL --actions` with the real action schema, result shape, limits, and external-CDP options.
    887 repo stars
  62. ▌
    Running The Proxy 3 · kreuzberg-dev
    Use when running the `liter-llm api` OpenAI-compatible gateway — virtual keys, per-key rate limits, budgets, cost tracking, and model routing. Covers the TOML config and the 22 REST endpoints.
    887 repo stars
  63. ▌
    Streaming Responses 3 · kreuzberg-dev
    Use when streaming tokens incrementally from an LLM via liter-llm over SSE or async iterators. Covers chat_stream, delta handling, and null-content chunks.
    887 repo stars
  64. ▌
    Using The MCP Server 5 · kreuzberg-dev
    Use when calling LLM APIs through the liter-llm MCP server's 22 tools, and to decide when MCP beats the CLI or SDK. Covers the tool surface, the auto-installing launcher, and authentication.
    887 repo stars
  65. ▌
    Embeddings And Search 4 · kreuzberg-dev
    Use when generating embeddings, calling the 12 web-search providers, or running OCR over documents with the 4 OCR providers through liter-llm. Covers embed, search, and ocr methods plus reranking.
    887 repo stars
  66. ▌
    Using The MCP Server 6 · kreuzberg-dev
    Use when converting HTML to Markdown or extracting metadata and tables through the html-to-markdown MCP server's tools, rather than shelling out to the CLI. Covers the tool surface, the auto-installing launcher, and when MCP beats the CLI or SDK.
    887 repo stars
  67. ▌
    Converting HTML 3 · kreuzberg-dev
    Use when converting HTML to Markdown, Djot, or plain text. Covers output formats, heading and code-block styles, lists, escaping, wrapping, and HTML preprocessing.
    887 repo stars
  68. ▌
    HTML To Markdown 3 · kreuzberg-dev bundle
    Convert HTML to Markdown, Djot, or plain text with structured extraction. Use when writing code that calls html-to-markdown APIs in Rust, Python, TypeScript, Go, Ruby, PHP, Java, C#, Elixir, R, C, or WASM. Covers installation, conversion, configuration, metadata extraction, tables, document structure, inline images, URL fetching, and CLI usage.
    887 repo stars
  69. ▌
    Extracting Tables 4 · kreuzberg-dev
    Use when extracting tabular data from HTML. Covers GFM Markdown tables, the structured tables array (grid cells plus pre-rendered markdown), and HTML line breaks in table cells.
    887 repo stars
  70. ▌
    Using The MCP Server 3 · kreuzberg-dev
    Use when converting HTML to Markdown or extracting metadata and tables through the html-to-markdown MCP server's tools, rather than shelling out to the CLI. Covers the tool surface, the auto-installing launcher, and when MCP beats the CLI or SDK.
    887 repo stars
  71. ▌
    Using The MCP Server 4 · kreuzberg-dev
    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.
    887 repo stars
  72. ▌
    Xberg 2 · kreuzberg-dev bundle
    Extract text, tables, metadata, and images from 107 document formats (PDF, Office, images, HTML, email, archives, academic) using Xberg. Use when writing code that calls Xberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output format), batch processing, error handling, and plugins.
    887 repo stars
  73. ▌
    Converting HTML 2 · kreuzberg-dev
    Use when converting HTML to Markdown, Djot, or plain text. Covers output formats, heading and code-block styles, lists, escaping, wrapping, and HTML preprocessing.
    887 repo stars
  74. ▌
    HTML To Markdown 2 · kreuzberg-dev bundle
    Convert HTML to Markdown, Djot, or plain text with structured extraction. Use when writing code that calls html-to-markdown APIs in Rust, Python, TypeScript, Go, Ruby, PHP, Java, C#, Elixir, R, C, or WASM. Covers installation, conversion, configuration, metadata extraction, tables, document structure, inline images, URL fetching, and CLI usage.
    887 repo stars
  75. ▌
    Extracting Tables 2 · kreuzberg-dev
    Use when extracting tabular data from HTML. Covers GFM Markdown tables, the structured tables array (grid cells plus pre-rendered markdown), and HTML line breaks in table cells.
    887 repo stars
  76. ▌
    Extracting Metadata 2 · kreuzberg-dev
    Use when extracting metadata from HTML — title, description, language, Open Graph, JSON-LD / Microdata / RDFa, headers, links, and images. Covers the --json output shape and the --extract-metadata flag.
    887 repo stars
  77. ▌
    Fetching And Converting Urls 2 · kreuzberg-dev
    Use when fetching a live URL and converting it to Markdown. Covers --url, custom user agents, preprocessing for noisy pages, and the --json ConversionResult shape.
    887 repo stars
  78. ▌
    Liter LLM 2 · kreuzberg-dev
    Universal LLM API client for 165 providers with native bindings for 14 languages. Use when writing code that calls LLM APIs via liter-llm in Python, TypeScript, Rust, Go, Java, C#, Ruby, PHP, Elixir, WASM, or C, when running the OpenAI-compatible proxy, or when calling LLMs through the MCP server. Covers chat, streaming, tool calling, embeddings, image generation, speech, transcription, moderation, web search, OCR, reranking, provider routing, middleware, and configuration.
    887 repo stars
  79. ▌
    Calling Llms 2 · kreuzberg-dev
    Use when sending chat completions through liter-llm and routing to a specific provider via the `provider/model` prefix. Covers the chat call shape, provider routing, model_hint, message roles, and error categories.
    887 repo stars
  80. ▌
    Tool Calling 2 · kreuzberg-dev
    Use when defining functions/tools for an LLM to call through liter-llm, or requesting structured JSON outputs. Covers tool schemas, tool_calls handling, and response formats.
    887 repo stars
  81. ▌
    Running The Proxy 2 · kreuzberg-dev
    Use when running the `liter-llm api` OpenAI-compatible gateway — virtual keys, per-key rate limits, budgets, cost tracking, and model routing. Covers the TOML config and the 22 REST endpoints.
    887 repo stars
  82. ▌
    Streaming Responses 2 · kreuzberg-dev
    Use when streaming tokens incrementally from an LLM via liter-llm over SSE or async iterators. Covers chat_stream, delta handling, and null-content chunks.
    887 repo stars
  83. ▌
    Using The MCP Server 2 · kreuzberg-dev
    Use when calling LLM APIs through the liter-llm MCP server's 22 tools, and to decide when MCP beats the CLI or SDK. Covers the tool surface, the auto-installing launcher, and authentication.
    887 repo stars
  84. ▌
    Embeddings And Search 2 · kreuzberg-dev
    Use when generating embeddings, calling the 12 web-search providers, or running OCR over documents with the 4 OCR providers through liter-llm. Covers embed, search, and ocr methods plus reranking.
    887 repo stars
  85. ▌
    Parsing Source 2 · kreuzberg-dev
    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`.
    887 repo stars
  86. ▌
    Managing Parsers 2 · kreuzberg-dev
    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`.
    887 repo stars
  87. ▌
    Chunking For Llms 2 · kreuzberg-dev
    Use when the user wants to split source code into chunks for an LLM context window without breaking syntax mid-construct. Covers `ts-pack process --chunk-size`, why syntax-aware splits beat fixed-byte splits, picking a size, and the chunk JSON shape.
    887 repo stars
  88. ▌
    Detecting Languages 2 · kreuzberg-dev
    Use when the user wants to know which programming language a file or snippet is. Covers implicit detection in `ts-pack parse`/`process`, confirming support with `ts-pack list`/`info`, and the SDK detection functions for path, extension, and raw content.
    887 repo stars
  89. ▌
    Extracting Code Structure 2 · kreuzberg-dev
    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.
    887 repo stars
  90. ▌
    Tree Sitter Language Pack 2 · kreuzberg-dev
    Parse and extract code intelligence from 371 programming languages using tree-sitter grammars. Use when writing code that parses source, extracts structure/imports/exports/symbols/docstrings/comments, detects a language, runs syntax diagnostics, or produces syntax-aware chunks for LLMs — in Rust, Python, Node.js/TypeScript, or the ts-pack CLI. Covers installation, the CLI surface, the SDK surface, and parser-cache management.
    887 repo stars
  91. ▌
    Testing Conventions · kreuzberg-dev
    How to test scripts in xberg-io/actions — which framework each language uses (Bats for shell, pytest for Python, Pester for PowerShell), where suites live, how to isolate a test from the host machine so it cannot pass locally and fail on a runner, and how to prove a test actually discriminates. Load when adding or changing any script under an action, when writing or fixing tests, or when a suite passes locally but fails in CI.
    887 repo stars
  92. ▌
    Alef · kreuzberg-dev
    Use Alef correctly for Rust-to-polyglot binding generation. Trigger when configuring alef.toml, generating bindings, READMEs, API/CLI/MCP docs, llms.txt, agent skills, e2e suites, or debugging stale/missing generated output in Alef-powered repositories. Covers the safe command sequence, config ownership, generated-output rules, snippet validation, downstream smoke testing, and Alef development workflow.
    887 repo stars
  93. ▌
    Regen Audit · kreuzberg-dev
    Treat running `alef generate`/`alef all`/`alef verify` in a consumer repo as an audit, not a build step. Use this skill whenever you run a regen, read its log or diff, or investigate "the fix didn't work" after regenerating a consumer repo's bindings.
    887 repo stars
  94. ▌
    Binding Audit · kreuzberg-dev
    Audit bindings for coverage gaps — verify every public Rust item is exposed across all generated language bindings. Use this skill any time you need to check that a function/type is present in every target language, audit intentional exclusions, or investigate missing bindings in one or more languages. Covers the full audit flow: config review, attribute scan, item enumeration, cross-binding diff, gap reporting, and triage (alef vs Alef-owned workflow/action vs consumer config).
    887 repo stars
  95. ▌
    Jinja Codegen · kreuzberg-dev
    Mechanics of alef's Minijinja template system: which template_env module to call, how to register a template, inline-template rules, and engine settings. Use this skill when adding or changing generated-code templates in any backend, codegen, or e2e generator module.
    887 repo stars
  96. ▌
    Release Procedure · kreuzberg-dev
    Cut, tag, and publish an alef release end-to-end. Use this skill any time the user asks for a release, a version bump, a hotfix tag, or a CHANGELOG roll-up in this repo. Covers the full pipeline: changelog, version sync via Taskfile, Cargo.toml verification, poly lint pass, atomic commit (no AI signatures, no --no-verify when avoidable), git tag, and `gh release create` (not just a tag).
    887 repo stars
  97. ▌
    Two Generators Disagree · kreuzberg-dev
    Alef's dominant defect shape: two components read the same config or IR and act on it differently. Use this skill when a generated package fails to build, a generated suite fails wholesale, or a lowering looks wrong in one backend but not others.
    887 repo stars
  98. ▌
    Kreuzberg · kreuzberg-dev bundle
    Extract text, tables, metadata, and images from 91+ document formats (PDF, Office, images, HTML, email, archives, academic) using Kreuzberg. Use when writing code that calls Kreuzberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output format), batch processing, error handling, and plugins.
    887 repo stars
  99. ▌
    API Server MCP · kreuzberg-dev
    api server mcp
    887 repo stars
  100. ▌
    Wasm Constraints · kreuzberg-dev
    wasm constraints
    887 repo stars