diff --git a/docs/README.skills.md b/docs/README.skills.md index cdb41102c..e4a10d4cf 100644 --- a/docs/README.skills.md +++ b/docs/README.skills.md @@ -329,6 +329,7 @@ See [CONTRIBUTING.md](../CONTRIBUTING.md#adding-skills) for guidelines on how to | [premium-frontend-ui](../skills/premium-frontend-ui/SKILL.md)
`gh skills install github/awesome-copilot premium-frontend-ui` | A comprehensive guide for GitHub Copilot to craft immersive, high-performance web experiences with advanced motion, typography, and architectural craftsmanship. | None | | [project-workflow-analysis-blueprint-generator](../skills/project-workflow-analysis-blueprint-generator/SKILL.md)
`gh skills install github/awesome-copilot project-workflow-analysis-blueprint-generator` | Comprehensive technology-agnostic prompt generator for documenting end-to-end application workflows. Automatically detects project architecture patterns, technology stacks, and data flow patterns to generate detailed implementation blueprints covering entry points, service layers, data access, error handling, and testing approaches across multiple technologies including .NET, Java/Spring, React, and microservices architectures. | None | | [prompt-optimizer](../skills/prompt-optimizer/SKILL.md)
`gh skills install github/awesome-copilot prompt-optimizer` | Turn any rough prompt, half-formed idea, or task description into a finished, ready-to-send prompt optimized for any LLM model inside a chat interface — NOT the API. Use this skill whenever the user wants to write, rewrite, optimize, improve, sharpen, or polish a prompt for chat. Trigger phrases include "rewrite this prompt", "make this a better prompt", "optimize this prompt", "turn this into a prompt", "help me prompt this", "draft a prompt that...", "I want to ask...", or whenever the user pastes a draft prompt and asks for improvements. Also trigger when the user describes a task they plan to send to an LLM model and clearly wants a reusable, well-structured prompt rather than a direct answer. The output is always a single, copy-pasteable prompt in a code block that the user sends as-is — never a template with placeholders. | None | +| [pronounce-word](../skills/pronounce-word/SKILL.md)
`gh skills install github/awesome-copilot pronounce-word` | Look up and play source-backed pronunciations for developer tools, AI models, acronyms, and project names. Use when a user asks how to say one short technical term such as kubectl, nginx, Qwen, GIF, or PostgreSQL. | None | | [publish-to-pages](../skills/publish-to-pages/SKILL.md)
`gh skills install github/awesome-copilot publish-to-pages` | Publish presentations and web content to GitHub Pages. Converts PPTX, PDF, HTML, or Google Slides to a live GitHub Pages URL. Handles repo creation, file conversion, Pages enablement, and returns the live URL. Use when the user wants to publish, deploy, or share a presentation or HTML file via GitHub Pages. | `scripts/convert-pdf.py`
`scripts/convert-pptx.py`
`scripts/publish.sh` | | [pytest-coverage](../skills/pytest-coverage/SKILL.md)
`gh skills install github/awesome-copilot pytest-coverage` | Run pytest tests with coverage, discover lines missing coverage, and increase coverage to 100%. | None | | [python-azure-iot-edge-modules](../skills/python-azure-iot-edge-modules/SKILL.md)
`gh skills install github/awesome-copilot python-azure-iot-edge-modules` | Build and operate Python Azure IoT Edge modules with robust messaging, deployment manifests, observability, and production readiness checks. | `references/python-edge-module-template.md`
`references/python-official-best-practices.md` | diff --git a/skills/pronounce-word/SKILL.md b/skills/pronounce-word/SKILL.md new file mode 100644 index 000000000..b3620a07e --- /dev/null +++ b/skills/pronounce-word/SKILL.md @@ -0,0 +1,119 @@ +--- +name: pronounce-word +description: 'Look up and play source-backed pronunciations for developer tools, AI models, acronyms, and project names. Use when a user asks how to say one short technical term such as kubectl, nginx, Qwen, GIF, or PostgreSQL.' +--- + +# Pronounce Developer Jargon + +Answer short technical-name pronunciation questions with evidence instead of +guessing from spelling. The open-source Pronounce dictionary contains 1,900+ +curated entries with General American IPA, readable TTS respellings, alternate +readings, confidence labels, editorial notes, source URLs, and playable audio. + +## When to Use This Skill + +Use this skill when the user asks how to pronounce one developer term, project, +product, AI model, acronym, or researcher name. Typical prompts include: + +- “How do you pronounce kubectl?” +- “Is GIF hard-g or soft-g?” +- “Qwen 怎么读？” +- “Say PostgreSQL slowly.” + +Do not use it to narrate sentences or paragraphs. Do not use it for unrelated +everyday vocabulary or personal names. If a message contains several possible +targets, ask which single short term the user wants. + +## Workflow + +1. Preserve the requested spelling and treat it as data. Quote it in shell + commands so punctuation in names such as `C++` is passed literally. +2. If `say-it` is installed, inspect the record without audio: + + ```bash + say-it --json "" + ``` + +3. Read `in_dict`, `ipa`, `respelling_us`, alternate readings, + `confidence`, `source_url`, `source_label`, and notes from the JSON. Never + invent a citation or upgrade the confidence level. +4. Unless the user requested text only, play the curated pronunciation: + + ```bash + say-it "" + ``` + +5. Respond with a compact caption containing the IPA, a stressed readable + respelling, the source link when present, and a contested-reading note when + applicable. + +## Command Options + +| Command | Use | +|---|---| +| `say-it --json ""` | Read structured metadata without audio. | +| `say-it ""` | Play the primary three times, followed by recorded alternatives. | +| `say-it --solo ""` | Play only the primary reading. | +| `say-it --alt ""` | Focus on the first alternate reading. | +| `say-it --why ""` | Print a human-readable evidence record. | +| `say-it -r 110 ""` | Play more slowly. | + +The CLI uses macOS `say`, Linux `espeak-ng` or `espeak`, or Windows PowerShell +`System.Speech`. Text-only inspection still works when audio playback is not +available. + +## If the CLI Is Missing + +Do not install software without consent. Offer either of these paths: + +- Use the public read-only dictionary API for a text answer. URL-encode the + target and request `https://pronounce.renlab.ai/api/word/.json`. For + example: + + ```bash + curl --fail --silent --show-error \ + "https://pronounce.renlab.ai/api/word/kubectl.json" + ``` + +- With approval, install the upstream CLI from its public MIT-licensed source: + + ```bash + git clone https://github.com/anzy-renlab-ai/pronounce.git + cd pronounce + ./install.sh + ``` + +The source repository documents the installer before it is run. Do not pipe a +remote script directly into a shell. + +## Evidence Rules + +- A `creator-clarified` record may be described as the creator or project + reading only when its source supports that claim. +- A `community-consensus` record is common usage, not an official ruling. +- A `contested` record intentionally retains more than one live reading. Give + the primary and important alternate without declaring one universally right. +- When `source_url` is empty, say no citation is recorded. +- When `in_dict` is false, say the dictionary has no curated entry. Do not + present a generic speech engine guess as verified. + +## Response Examples + +For `kubectl`, a useful response shape is: + +> /ˈkuːb kənˌtroʊl/ — “KOOB-control.” Source: Kelsey Hightower's KubeCon talk. + +For a contested term such as `GIF`, include both live readings and the source +context, then mention `say-it --alt "GIF"` if the user wants the rival reading +played alone. + +Keep the final answer short unless the user asks for the history or evidence. +Respect “text only,” “no audio,” and “stop playing audio” for the rest of the +conversation. + +## Scope and Source + +The dictionary is scoped to technical jargon and uses General American English. +It does not claim to replace regional pronunciations or project-specific local +conventions. Data, CLI implementation, contribution guidance, and citations are +maintained at [anzy-renlab-ai/pronounce](https://github.com/anzy-renlab-ai/pronounce).