Add Pronounce — developer-jargon pronunciation MCP server + skill#223
Add Pronounce — developer-jargon pronunciation MCP server + skill#223anzy-renlab-ai wants to merge 1 commit into
Conversation
Tools & Integrations. MCP server (lookup/search) + pronounce-word skill backed by a 1,721-entry community pronunciation dictionary with IPA, audio, and cited sources. Requested via anzy-renlab-ai/pronounce#41. HOL Plugin Scanner: passing in CI on the plugin repo's main branch (min_score 80, fail_on high, SARIF uploaded), no critical/high findings. Required files present: .codex-plugin/plugin.json, SECURITY.md, LICENSE, README.md.
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request adds the 'Pronounce' plugin to the marketplace, registering it in the marketplace configurations, README, and adding its local plugin files. Feedback highlights that the mirrored plugin directory is missing the 'skills/' folder and its associated files despite the description claiming to ship the 'pronounce-word' skill. Additionally, running the MCP server via 'uvx' with a direct Git URL in '.mcp.json' may cause startup latency and network dependency; publishing to PyPI or bundling the server files locally is recommended.
Important
The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.
| { | ||
| "name": "pronounce", | ||
| "version": "2.12.0", | ||
| "description": "Pronounce developer jargon out loud — 1721+ sourced entries (kubectl, GIF, JSON, JWT, …). Ships the pronounce-word skill and the pronounce MCP server.", |
There was a problem hiding this comment.
The plugin description and manifest state that this plugin ships the 'pronounce-word' skill. However, the mirrored plugin bundle under 'plugins/anzy-renlab-ai/pronounce/' is missing the 'skills/' directory and its corresponding skill files (such as 'SKILL.md'). Please add the missing skill files to the mirrored directory so that the skill is correctly installed and available to users.
| "command": "uvx", | ||
| "args": [ | ||
| "--from", | ||
| "git+https://github.com/anzy-renlab-ai/pronounce.git#subdirectory=mcp-server", | ||
| "pronounce-mcp" | ||
| ] |
There was a problem hiding this comment.
Using 'uvx' with a direct 'git+https' URL to run the MCP server can introduce significant startup latency and makes the plugin's startup dependent on network connectivity and GitHub's availability. Consider publishing the 'pronounce-mcp' package to PyPI so it can be run directly via 'uvx pronounce-mcp' (which uses cached/versioned releases), or bundling the server files locally within the plugin directory.
2 participants
Add Pronounce (Tools & Integrations)
Pronounce is a community-maintained pronunciation dictionary for developer jargon — 1,721 sourced entries (kubectl, nginx, YAML, GIF, JSON, JWT, …), each with IPA, a plain-English respelling, audio, and a cited source.
The plugin ships:
lookup(word)/search(query)returning IPA, respelling,audio_url, source, and confidence;Requested by a community member in anzy-renlab-ai/pronounce#41.
Scanner (mandatory)
mainbranch: https://github.com/anzy-renlab-ai/pronounce/actions/runs/27814499520min_score: 80,fail_on_severity: high, SARIF uploaded — job passed (no critical/high findings).Checklist
.codex-plugin/plugin.json(valid manifest)SECURITY.md,LICENSE(MIT),README.mdactions/checkoutplugins/anzy-renlab-ai/pronounce/plugins.jsonand.agents/plugins/marketplace.json