voice-baseline
Measure your own writing corpus for the words and sentence shapes you over-use, so an agent writing in your voice stops amplifying your tics into a style. Produces a counted baseline file and checks any new draft against it
Install / Use
npx skills add huytieu/COG-second-brain --skill voice-baselineInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Content & MediaSupported Platforms
Our assessment of voice-baseline
voice-baseline scores 83/100 on our quality scale, 923rd of 1,155 Content & Media skills we index.
Its SKILL.md is 3.7 KB long, split into 5 sections with 1 code example: a solid amount of guidance for an agent.
With 1,216 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so voice-baseline is actively maintained.
- Our last check on 2026-11-07 found the source still online.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-04. Automated pattern scan on 2026-10-04. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
voice-baseline compared with similar skills
All 4 of these similar skills score higher than voice-baseline; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| voice-baseline (this skill)by huytieu | 83 | 1.2k | 59d ago | SKILL.md |
| LocalAIby mudler | 100 | 50.4k | today | MCP Server |
| siyuanby siyuan-note | 100 | 47.3k | today | MCP Server |
| x402by browser-use | 100 | 121.0k | 3d ago | SKILL.md |
| algorithmic-artby anthropics | 100 | 177.9k | 55d ago | SKILL.md |
Frequently asked questions
- How do I install voice-baseline?
- Run
npx skills add huytieu/COG-second-brain --skill voice-baseline. The install tabs above show the steps for each supported agent. - Which AI agents does voice-baseline work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is voice-baseline safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is voice-baseline still maintained?
- The repository was last updated about 2 months ago, so voice-baseline is actively maintained.
Skill content
View source on GitHubname: voice-baseline description: Measure your own writing corpus for the words and sentence shapes you over-use, so an agent writing in your voice stops amplifying your tics into a style. Produces a counted baseline file and checks any new draft against it. Use when an agent's drafts start sounding like a caricature of you, before publishing anything written in your voice, or every ten new pieces to re-measure.
voice-baseline
An agent writing in your voice does not only sample the median of the internet. It samples the median of you, from the pieces and rules and memory files in its context, and it regresses toward your most frequent choices because those are the highest probability tokens in your corpus. A word that was a choice at one use comes back at five. Then the fifth use teaches the next draft, and the tic becomes the style.
Generic ban lists cannot catch this, because the words are yours and they are not on anyone's list. Measure instead.
Run it
python3 scripts/census.py PATH/TO/YOUR/WRITING --out voice-baseline.md
python3 scripts/census.py PATH/TO/YOUR/WRITING --check DRAFT.md
The census walks a directory of your own finished pieces and reports word counts with
a per-file rate, sentence-shape counts, sentence openers, and heading first words.
--check compares one draft against those rates and prints only what sits above them.
Exit code 1 when something is above baseline, so it fits a pre-publish script.
Keep the output file next to your rules so the agent reads it before it writes.
What it measures
Words. A watchlist of praise and emphasis words, counted with word boundaries and
reported per file. Read the per-file rate: a word used twice per file is a habit, and
the same word at eight in one draft is the draft's problem. Edit WATCH in the
script to add your own suspects; the point is that the list ends up specific to you.
Paragraph-ending verdict sentences. "The fix was one line." A concrete noun, a past-tense verb, a short predicate, parked at the end of a paragraph so it lands like a ruling. One per piece at most, and only when it carries a fact the paragraph has not already delivered.
Kicker closers. "That is the point." "That is all a title is for." A closing line that restates the piece as an aphorism. The cap is zero.
Endings. How many pieces close on a question to the reader. Most of them means the question has become a formula.
Sentence openers and heading first words. These are where a personal tic hides best, because each instance reads fine. If a third of your headings begin with the same word, you have a template. In one real 27-file archive the census found 53 headings starting with "The", the exact shape people name as an AI tell, learned from the author's own archive.
How to read the result
The census counts; it does not judge. For each flagged word or shape, decide whether it is your voice or your mode:
- Voice. The word carries meaning the sentence needs, or the rhythm is yours and deliberate. Keep it, and note the exception so the next check does not re-raise it.
- Mode. The word is praise, emphasis, or padding, and removing it changes nothing for the reader. Cut it, or replace it with the behaviour it was gesturing at.
Fix the shapes by cap rather than by ban: one verdict sentence, zero kickers, no default question ending, one narrative heading pattern per piece.
Re-measure
Run the census again after roughly ten new pieces. A tic you fixed should fall. A new one will have appeared, usually the word you reached for while avoiding the last one, which is the same substitution the model makes when a single word is banned.
Pair with slop-gate for the universal tells and no-ai-slop for the structural ones
a regular expression cannot see.
Related Skills
LocalAI
50.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
siyuan
47.3kAn open-source, privacy-first, self-hosted knowledge workspace where humans and AI agents work together 开源、隐私优先、自托管的知识工作空间,让人与智能体在此协作
x402
121.0kSet up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
