xberg-io
- 112 skills
- 0 followers
- 9.6k repo stars
- yesterday last updated
- ▌ Liter LLM Streaming Responses · xberg-io bundleUse when streaming tokens incrementally from an LLM via liter-llm over SSE or async iterators. Covers chat_stream, delta handling, and null-content chunks.
- ▌ Liter LLM Using The MCP Server · xberg-io bundleUse 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.
- ▌ Liter LLM Embeddings And Search · xberg-io bundleUse 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.
- ▌ Liter LLM 3 · xberg-io bundleUniversal LLM API client for 174 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.
- ▌ Liter LLM Calling Llms · xberg-io bundleUse 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.
- ▌ Liter LLM Tool Calling · xberg-io bundleUse 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.
- ▌ Liter LLM Running The Proxy · xberg-io bundleUse 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.
- ▌ Extracting Tables 5 · xberg-ioUse 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.
- ▌ Using The MCP Server 5 · xberg-ioUse 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.
- ▌
- ▌ Crawlberg 3 · xberg-ioCrawl, 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.
- ▌ Mapping Urls 3 · xberg-ioUse 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.
- ▌ Serving The API 3 · xberg-ioUse 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.
- ▌ Headless Fallback 3 · xberg-ioUse 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.
- ▌ Automating The Browser 3 · xberg-ioUse 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.
- ▌ Crate Structure 2 · xberg-ioMap of the html-to-markdown workspace — the seven `crates/` (core, cli, ffi, py, node, php, wasm) with the unsafe_code forbid/override rule, the out-of-workspace language packages under `packages/`, and the primary `convert()` API with its ConversionResult shape, feature flags, and dual parser. Load when navigating crates/packages, deciding where code belongs, or working with the core conversion API.
- ▌ Converting HTML 4 · xberg-ioUse when converting HTML to Markdown, Djot, or plain text. Covers output formats, heading and code-block styles, lists, escaping, wrapping, and HTML preprocessing.
- ▌ HTML To Markdown 4 · xberg-io bundleConvert 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.
- ▌ Extracting Metadata 4 · xberg-ioUse 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.
- ▌ Fetching And Converting Urls 2 · xberg-ioUse when fetching a live URL and converting it to Markdown. Covers --url, custom user agents, preprocessing for noisy pages, and the --json ConversionResult shape.
- ▌
- ▌
- ▌ Parsing Source 2 · xberg-ioUse 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`.
- ▌ Managing Parsers 4 · xberg-ioUse 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`.
- ▌ Chunking For Llms 2 · xberg-ioUse 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.
- ▌ Detecting Languages 4 · xberg-ioUse 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.
- ▌ Extracting Code Structure 4 · xberg-ioUse 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.
- ▌ Tree Sitter Language Pack 4 · xberg-ioParse 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.
- ▌ Xberg 2 · xberg-io bundleExtract text, tables, metadata, and images from 98+ 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.
- ▌ Chunking 2 · xberg-ioUse 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.
- ▌ Liter LLM 2 · xberg-ioUniversal 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.
- ▌ Batch Extraction 2 · xberg-ioUse 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.
- ▌ Picking A Format 2 · xberg-ioUse 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.
- ▌ Extracting Tables 3 · xberg-ioUse 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.
- ▌ Crawling A Site 3 · xberg-ioUse when the user wants to follow links across a domain and capture every reachable page as Markdown. Covers `crawlberg crawl` with depth, page caps, concurrency, rate limiting, domain scoping, robots, and output selection.
- ▌ Extracting Keywords 2 · xberg-ioUse 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.
- ▌ Extracting With Ocr 2 · xberg-ioUse 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.
- ▌ Running The Proxy 2 · xberg-ioUse 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.
- ▌ Streaming Responses 2 · xberg-ioUse when streaming tokens incrementally from an LLM via liter-llm over SSE or async iterators. Covers chat_stream, delta handling, and null-content chunks.
- ▌ Using The MCP Server 3 · xberg-ioUse 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.
- ▌ Converting HTML 3 · xberg-ioUse when converting HTML to Markdown, Djot, or plain text. Covers output formats, heading and code-block styles, lists, escaping, wrapping, and HTML preprocessing.
- ▌ HTML To Markdown 3 · xberg-io bundleConvert 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.
- ▌ Extracting Tables 4 · xberg-ioUse 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.
- ▌ Scraping HTML To Markdown 3 · xberg-ioUse when the user wants a single page rendered as clean Markdown plus structured metadata. Covers `crawlberg scrape URL`, JSON vs Markdown output, what metadata is returned, and how to handle JS-heavy pages.
- ▌ Extracting Metadata 3 · xberg-ioUse 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.
- ▌ Managing Parsers 3 · xberg-ioUse 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`.
- ▌ Detecting Languages 3 · xberg-ioUse 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.
- ▌ Using The MCP Server 4 · xberg-ioUse 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.
- ▌ Extracting Code Structure 3 · xberg-ioUse 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.
- ▌ Tree Sitter Language Pack 3 · xberg-ioParse 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.
- ▌ Managing Parsers 2 · xberg-ioUse 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`.
- ▌ Detecting Languages 2 · xberg-ioUse 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.
- ▌ Extracting Code Structure 2 · xberg-ioUse 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.
- ▌ Tree Sitter Language Pack 2 · xberg-ioParse 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.
- ▌ Liter LLM · xberg-ioUniversal 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.
- ▌ Running The Proxy · xberg-ioUse 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.
- ▌ Streaming Responses · xberg-ioUse when streaming tokens incrementally from an LLM via liter-llm over SSE or async iterators. Covers chat_stream, delta handling, and null-content chunks.
- ▌ Extracting Tables 2 · xberg-ioUse 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.
- ▌ Using The MCP Server 2 · xberg-ioUse 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.
- ▌ Converting HTML 2 · xberg-ioUse when converting HTML to Markdown, Djot, or plain text. Covers output formats, heading and code-block styles, lists, escaping, wrapping, and HTML preprocessing.
- ▌ HTML To Markdown 2 · xberg-io bundleConvert 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.
- ▌ Extracting Metadata 2 · xberg-ioUse 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.
- ▌ Crawlberg 2 · xberg-ioCrawl, 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.
- ▌ Mapping Urls 2 · xberg-ioUse 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.
- ▌ Crawling A Site 2 · xberg-ioUse when the user wants to follow links across a domain and capture every reachable page as Markdown. Covers `crawlberg crawl` with depth, page caps, concurrency, rate limiting, domain scoping, robots, and output selection.
- ▌ Serving The API 2 · xberg-ioUse 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.
- ▌ Headless Fallback 2 · xberg-ioUse 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.
- ▌ Automating The Browser 2 · xberg-ioUse 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.
- ▌ Scraping HTML To Markdown 2 · xberg-ioUse when the user wants a single page rendered as clean Markdown plus structured metadata. Covers `crawlberg scrape URL`, JSON vs Markdown output, what metadata is returned, and how to handle JS-heavy pages.
- ▌ Formula Maintenance · xberg-ioHomebrew tap formula maintenance for xberg-io CLIs — source-build vs binary-only formula types, the version-bump checklist (url/version/sha256/bottles/root_url), and building bottles with scripts/build-bottles.sh. Load when editing a .rb formula, cutting a release bump, or updating bottle hashes.
- ▌ Converting HTML · xberg-ioUse when converting HTML to Markdown, Djot, or plain text. Covers output formats, heading and code-block styles, lists, escaping, wrapping, and HTML preprocessing.
- ▌ HTML To Markdown · xberg-io bundleConvert 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.
- ▌ Extracting Metadata · xberg-ioUse 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.
- ▌ Fetching And Converting Urls · xberg-ioUse when fetching a live URL and converting it to Markdown. Covers --url, custom user agents, preprocessing for noisy pages, and the --json ConversionResult shape.
- ▌ Parsing Source · xberg-ioUse 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`.
- ▌ Managing Parsers · xberg-ioUse 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`.
- ▌ Chunking For Llms · xberg-ioUse 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.
- ▌ Detecting Languages · xberg-ioUse 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.
- ▌ Using The MCP Server · xberg-ioUse 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.
- ▌ Extracting Code Structure · xberg-ioUse 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.
- ▌ Tree Sitter Language Pack · xberg-ioParse 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.
- ▌
- ▌
- ▌
- ▌ Crawlberg · xberg-ioCrawl, 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.
- ▌ Dev Cycle · xberg-ioCrawlberg iteration loops codified as Taskfile tasks — alef install/generate/format/bump, core and binding builds, e2e generate/build/test cycles, cleanup tiers, and the mock-server / stale-.so / precompiled-NIF / generated-e2e gotchas. Load when running or debugging crawlberg build, alef regeneration, or e2e workflows, or when unsure which task to run.
- ▌ Mapping Urls · xberg-ioUse 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.
- ▌ Crawling A Site · xberg-ioUse when the user wants to follow links across a domain and capture every reachable page as Markdown. Covers `crawlberg crawl` with depth, page caps, concurrency, rate limiting, domain scoping, robots, and output selection.
- ▌ Serving The API · xberg-ioUse 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.
- ▌ Headless Fallback · xberg-ioUse 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.
- ▌ Automating The Browser · xberg-ioUse 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.
- ▌ Scraping HTML To Markdown · xberg-ioUse when the user wants a single page rendered as clean Markdown plus structured metadata. Covers `crawlberg scrape URL`, JSON vs Markdown output, what metadata is returned, and how to handle JS-heavy pages.
- ▌ Xberg · xberg-io bundleExtract 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.
- ▌ Alef Generated Bindings · xberg-ioAlef-managed generated bindings in packages/* and binding crates — the regeneration workflow (task alef:generate / alef:verify), the alef.toml section layout, the core-side edits that break a regen, and the FFI bridge's JSON marshalling requirement. Load before editing anything under packages/* or a binding crate, before adding a trait method or extractor, or when regenerating or verifying Alef output.
- ▌ Mime Detection Routing · xberg-ioMIME type detection and extractor routing in core/mime.rs — the FORMATS registry that EXT_TO_MIME and SUPPORTED_MIME_TYPES are derived from, the path-based and bytes-based detection functions, priority-based registry selection, wildcard MIME families, and the real procedure for adding a format. Load when adding a format, wiring an extractor to a MIME type, or debugging why a file routes to the wrong (or no) extractor.
- ▌
- ▌ Feature Flag Policy · xberg-ioCargo feature flags for crates/xberg — ORT-incompatible targets (WASM, Android x86_64 emulator), type-only and tract inference companion features, WASM/Android-safe variants, PDF backend, mutually-exclusive ORT variants, platform-conditional deps, aggregate feature sets, and build profiles. Load when adding, wiring, or debugging a Cargo feature, or when reasoning about what compiles on WASM/Android/Windows/macOS-intel targets.
- ▌ Polyrepo Boundaries · xberg-ioDecide which xberg-io repository owns a cross-repository fix or API, and coordinate compatible changes across Xberg, Alef, enterprise, crawler, LLM, and OCR repositories. Load when work spans sibling repos; do not use for a self-contained Xberg edit.
- ▌ Benchmark Workflow · xberg-ioRun, diagnose, or change Xberg extraction benchmarks, quality scoring, benchmark fixtures, artifact contracts, and independently sourced ground truth. Load for the Benchmarks workflow or benchmark-harness work, not ordinary unit tests.
- ▌ Release Versioning · xberg-ioHow xberg versions are synced and released — Cargo.toml is the single source of truth, `task version:sync` propagates it to alef-managed binding manifests AND the integrations under integrations/, which are versioned and published in lockstep with core (including -rc.N). Load before bumping a version, editing the version-sync task, or touching an integration's version/xberg dependency.