74 skills · sorted by relevance
Prepare Markdown for pandoc PDF conversion by replacing problematic Unicode symbols with ASCII alternatives. The skill covers reusable substitution scripts, broader character conversion, and alternative PDF engines for documents that need to retain Unicode.
Resolve Unicode character errors when converting Markdown to PDF with pandoc. Follow a workflow to replace troublesome symbols with ASCII equivalents, regenerate and check the PDF, or consider another PDF engine when preserving characters matters.
Create text diagrams with PlantUML for README files, emails, and terminal workflows. Convert diagram definitions into plain ASCII or Unicode box-drawing output to share interactions and relationships where image-based diagrams are unsuitable.
Turn ideas, notes, or technical material into LinkedIn posts ready to copy and paste. Organize hooks, short sections, closing prompts, and hashtags, using Unicode characters to give plain text the appearance of bold or italic styling.
Recover from file-writing errors involving emoji or special symbols by switching to shell-based writing. Guides character preservation or replacement, literal text handling, directory preparation, and checks of the saved content.
差分に追加されたソースコードへ混入した不可視・危険な Unicode 文字（タグ文字・異体字セレクター・ゼロ幅文字・双方向制御/マーク・変則空白）を検出する。GlassWorm 型サプライチェーン攻撃・ASCII smuggling・Trojan Source（CVE-2021-42574）でコードを不可視化する手口を、決定論的な静的解析（列挙した code point 集合に限定）として捕捉し、canary テストで誤検出の再発を防ぐ
The English summary is being prepared. Showing the original description.
Inspect and remove invisible characters from text and AI provenance metadata, information about content origin, from images and documents. It also supports prose rewriting and reports what changed, with limits on verifying watermark removal.
Recover from Pandoc PDF generation failures by checking installed PDF engines and retrying alternatives. The guide matches engines to Unicode text, simple Latin documents, or HTML-based layouts, and includes an automated fallback script.
Build Bengali search and AI features with guidance on consistent character encoding, word splitting, digit conversion, and safe text display. Includes patterns for cleaning training data, storing text, and handling Bengali alongside English.
Recover failed writes of large files or code containing special characters by placing content in a temporary Python script. Use raw strings or Base64 encoding, then check that the output file exists and has content.
Convert Markdown into Word, PDF, and HTML using a workflow suited to the document. Simple files use direct delegation, while documents with special characters use separate conversion steps, character replacement, and output checks.
Generate Word, PDF, and HTML documents from Markdown while diagnosing conversion failures. The workflow checks required tools, replaces problematic characters for PDF, tries alternative conversion engines, and verifies the resulting files.
Generate DOCX, PDF, and HTML from Markdown through separate, observable conversion steps. The workflow replaces problematic characters for PDF output, captures error messages, and switches PDF engines when needed to troubleshoot document generation failures.
Fix intermittent `{:no_translation, :unicode, :latin1}` crashes in Elixir escript daemons that use length-prefixed framed IPC on stdin/stdout. Use when: (1) daemon worker crashes only on some input files, usually ones with non-ASCII bytes (kanji, cyrillic, emoji); (2) error surfaces as `Protocol error` from daemon's error branch or as garbled frame-length bytes seen by the orchestrator/client side; (3) standalone one-shot mode works fine on the same input but multi-request daemon mode fails; (4) `IO.binread(:stdio, N)` returns `{:error, {:no_translation, :unicode, :latin1}}` despite the "bin" prefix suggesting it should be encoding-agnostic. Root cause is the escript default `:standard_io` encoding — it's `:unicode`, and `IO.binread` still routes through the io_server, which translates bytes to codepoints and errors when raw binary frames contain invalid UTF-8 sequences.
The English summary is being prepared. Showing the original description.
Build text tokenizers that split multilingual text into small units for AI models. Learn how to train SentencePiece on raw text, configure BPE or Unigram splitting methods, and convert text to token IDs and back.
Review articles, emails, documentation, and other reader-facing prose for invisible characters and formulaic writing. When measured signals are high, revise the wording while preserving facts, the writer’s voice, code, citations, and required disclosures.
Build text tokenizers, which split text into units for AI models, directly from raw multilingual text. Learn custom vocabularies with BPE or Unigram, convert text to pieces or numeric IDs, and decode the results.
Produce Word, PDF, and HTML documents when retrieval or conversion tools fail. The workflow switches to available knowledge with stated limitations, prepares characters for PDF conversion, tries alternative tools, and checks the resulting files.
Generate Word, PDF, and HTML documents from Markdown through visible conversion steps. Check available tools, handle special characters according to the output format, switch to alternative converters when needed, and verify the resulting files.
Generate DOCX, PDF, and HTML documents from Markdown, with alternative PDF tools to try when conversion fails. The workflow includes character replacement, separate conversion steps, and checks for missing, empty, or invalid output files.
Design terminal output for a CLI tool with chalk colors, Unicode glyphs, multiple verbosity levels (human, verbose, quiet, JSON), and consistent voice rules. Covers color palette selection, status indicator design, reporter function architecture, ceremony/narrative output variants, and cross-terminal compatibility. Use when building a new CLI reporter module, adding warm narrative output to an existing tool, standardizing output across multiple commands, or designing machine-readable JSON alongside human-readable text.
The English summary is being prepared. Showing the original description.
Tokenizador agnóstico de linguagem que trata texto como Unicode bruto. Suporta algoritmos BPE e Unigram. Rápido (50k sentenças/seg), leve (6MB de memória), vocabulário determinístico. Usado por T5, ALBERT, XLNet, mBART. Treina em texto bruto sem pré-tokenização. Use quando você precisar de suporte multilíngue, linguagens CJK ou tokenização reproduzível.
The English summary is being prepared. Showing the original description.
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
The English summary is being prepared. Showing the original description.
Format and draft compelling LinkedIn posts using Unicode bold/italic styling, visual separators, structured sections, and engagement-optimized patterns. USE FOR: draft LinkedIn post, format text for LinkedIn, create social media post, write thought leadership post, convert content to LinkedIn format, LinkedIn carousel text, Unicode bold italic formatting.
The English summary is being prepared. Showing the original description.