docs: sharpen Promptimprover portfolio proof#1
Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: f2df0944b8
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
|
|
||
| - `universal-refiner/package.json` defines the active package as `gemini-prompt-refiner` and describes it as cross-CLI prompt refinement using an MCP server. | ||
| - `universal-refiner/tests/` contains targeted Vitest coverage for detectors, history, lessons, memory, snippets, predictive refinement, timeline behavior, and server behavior. | ||
| - `build_and_install.ps1` installs the `universal-refiner` package globally as `prompt-refiner`, showing the intended operator entry point. |
There was a problem hiding this comment.
This proof point incorrectly states that the install script exposes prompt-refiner. The script runs npm install -g ., but universal-refiner/package.json defines only the gemini-prompt-refiner bin, so no prompt-refiner executable is installed. Anyone using this claimed operator entry point in an MCP configuration will get a command-not-found error unless the package bin or documentation is corrected.
Useful? React with 👍 / 👎.
2 participants
Summary
Why
These changes harden portfolio positioning and documentation clarity so Promptimprover presents its evidence and value more directly.