add humanizer voice presets#95
Conversation
![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 introduces a "Voice preset" feature to the humanizer skill, allowing the agent to use named voice styles defined in markdown files. It adds the "ПОЛНЫЙ ХУАВЕЙ" voice preset (huawei.md) with its specific style rules and sample posts, and updates the skill documentation (SKILL.md) to describe how to invoke and use these presets. The reviewer feedback points out that the paths to the voice presets (e.g., voices/) in the documentation should be updated to be relative to the repository root (e.g., plugins/dotagents/skills/humanizer/voices/ and skills/humanizer/voices/) so that the agent can correctly locate and load the preset files during execution.
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.
|
|
||
| - **Rewrite**: improve an existing draft while preserving meaning. | ||
| - **Voice match**: analyze 1-3 samples, then rewrite using that rhythm, directness, and vocabulary level. | ||
| - **Voice preset**: use a named voice from `voices/`. Invoke with `--voice <name>` or "in the style of <name>". Load the voice file, follow its style rules, use its samples as few-shot examples. Available presets are markdown files in `voices/`. |
There was a problem hiding this comment.
The path voices/ is relative to the skill directory, but the agent typically executes from the repository root. Specifying the full repository-relative path plugins/dotagents/skills/humanizer/voices/ ensures the agent can correctly locate the preset files.
| - **Voice preset**: use a named voice from `voices/`. Invoke with `--voice <name>` or "in the style of <name>". Load the voice file, follow its style rules, use its samples as few-shot examples. Available presets are markdown files in `voices/`. | |
| - **Voice preset**: use a named voice from `plugins/dotagents/skills/humanizer/voices/`. Invoke with `--voice <name>` or "in the style of <name>". Load the voice file, follow its style rules, use its samples as few-shot examples. Available presets are markdown files in `plugins/dotagents/skills/humanizer/voices/`. |
| Named voice presets live in `voices/` as markdown files. Each file contains style rules and sample posts. | ||
|
|
||
| When a preset is requested (`--voice huawei`, "write this in huawei style", etc.): | ||
| 1. Read `voices/<name>.md`. |
There was a problem hiding this comment.
Update the directory and file paths to be relative to the repository root (plugins/dotagents/skills/humanizer/voices/) so that the agent can successfully find and read the preset files during execution.
| Named voice presets live in `voices/` as markdown files. Each file contains style rules and sample posts. | |
| When a preset is requested (`--voice huawei`, "write this in huawei style", etc.): | |
| 1. Read `voices/<name>.md`. | |
| Named voice presets live in `plugins/dotagents/skills/humanizer/voices/` as markdown files. Each file contains style rules and sample posts. | |
| When a preset is requested (`--voice huawei`, "write this in huawei style", etc.): | |
| 1. Read `plugins/dotagents/skills/humanizer/voices/<name>.md`. |
|
|
||
| - **Rewrite**: improve an existing draft while preserving meaning. | ||
| - **Voice match**: analyze 1-3 samples, then rewrite using that rhythm, directness, and vocabulary level. | ||
| - **Voice preset**: use a named voice from `voices/`. Invoke with `--voice <name>` or "in the style of <name>". Load the voice file, follow its style rules, use its samples as few-shot examples. Available presets are markdown files in `voices/`. |
There was a problem hiding this comment.
The path voices/ is relative to the skill directory, but the agent typically executes from the repository root. Specifying the full repository-relative path skills/humanizer/voices/ ensures the agent can correctly locate the preset files.
| - **Voice preset**: use a named voice from `voices/`. Invoke with `--voice <name>` or "in the style of <name>". Load the voice file, follow its style rules, use its samples as few-shot examples. Available presets are markdown files in `voices/`. | |
| - **Voice preset**: use a named voice from `skills/humanizer/voices/`. Invoke with `--voice <name>` or "in the style of <name>". Load the voice file, follow its style rules, use its samples as few-shot examples. Available presets are markdown files in `skills/humanizer/voices/`. |
| Named voice presets live in `voices/` as markdown files. Each file contains style rules and sample posts. | ||
|
|
||
| When a preset is requested (`--voice huawei`, "write this in huawei style", etc.): | ||
| 1. Read `voices/<name>.md`. |
There was a problem hiding this comment.
Update the directory and file paths to be relative to the repository root (skills/humanizer/voices/) so that the agent can successfully find and read the preset files during execution.
| Named voice presets live in `voices/` as markdown files. Each file contains style rules and sample posts. | |
| When a preset is requested (`--voice huawei`, "write this in huawei style", etc.): | |
| 1. Read `voices/<name>.md`. | |
| Named voice presets live in `skills/humanizer/voices/` as markdown files. Each file contains style rules and sample posts. | |
| When a preset is requested (`--voice huawei`, "write this in huawei style", etc.): | |
| 1. Read `skills/humanizer/voices/<name>.md`. |
1 participant
Summary
--voice <name>or "in the style of ")huawei-- ПОЛНЫЙ ХУАВЕЙ channel style (ALL CAPS Russian corporate shitposting with heavy emoji)voices/as markdown with style rules + few-shot sample posts