voiceprint / rules
Cursor rule1 starsChanged 37 days agoMITView on GitHub
Run a draft through one unified prose-authenticity pass: check it, fix the AI tells once, report the residual. Use when the user wants the combined diagnose-fix-report intent in one step ("clean up and verify this," "make this authentic and tell me how it scored," "voiceprint this"). Not for a pure rewrite (standalone humanizer) or a pure score (standalone authenticity-check). Apply even when they do not say "voiceprint.
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,157 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- voiceprintSkill
The file
We split this voiceprint.mdc into the rules it gives an agent
5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 9
When this rule is engaged, act as the voiceprint skill defined in this repository.
- Distinctive: line 19
Run three steps in order, once each:
- Very specific: line 34
After / What changed / Residual / What remains is a human's call.
- Very specific: line 35
Keep Before verbatim and put hygiene counts and preservation reasons inside What changed, never in a seventh section.
- Very specific: line 50
Never edit anything under vendor/.
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
---
description: Run a draft through one unified prose-authenticity pass: check it, fix the AI tells once, report the residual. Use when the user wants the combined diagnose-fix-report intent in one step ("clean up and verify this," "make this authentic and tell me how it scored," "voiceprint this"). Not for a pure rewrite (standalone humanizer) or a pure score (standalone authenticity-check). Apply even when they do not say "voiceprint."
globs:
alwaysApply: false
---
# voiceprint (Cursor rule)
When this rule is engaged, act as the `voiceprint` skill defined in this
repository. Read `SKILL.md` at the repo root and follow it exactly. voiceprint
is a thin orchestrator: it composes two vendored prose skills in a fixed
order, exactly once, with one deterministic Unicode hygiene operation inside
the transformation stage.
For a one-sided request (rewrite-only or score-only), do not run a half pass:
serve just that half from the matching vendored copy (`vendor/humanizer/` or
`vendor/authenticity-check/`), or from the standalone skill if it is installed.
Run three steps in order, once each:
1. Diagnose: read `vendor/authenticity-check/SKILL.md` and follow it on the
immutable original. This is the before read. Carry no target score out of
it.
2. Clean and rewrite: run `python3 scripts/text_hygiene.py clean --stats` once,
then pass its cleaned working copy to one invocation of
`vendor/humanizer/SKILL.md` (voice discovery, density pre-check,
text-hygiene preflight, multi-pass workflow, meaning check). Pass pasted
text through standard input or a secure temporary file; never interpolate
it into a shell command or heredoc. This is the after text.
3. Re-diagnose: read `vendor/authenticity-check/SKILL.md` again and run it on
the after text as a fresh, cold diagnosis, for residual reporting only.
Produce the exact output contract: Before / Authenticity read (before) /
After / What changed / Residual / What remains is a human's call.
Keep `Before` verbatim and put hygiene counts and preservation reasons inside
`What changed`, never in a seventh section. On a hygiene processing error,
stop before humanizer and say the original was not changed.
Hard rule: one pass, never a loop. The re-check never drives further
rewriting, not when the residual score is low, not when spans remain. One
diagnose, one rewrite, one re-diagnose, then stop. A tool that rewrites text
to raise its own score is a detector-gaming loop, which both vendored skills
refuse. Report the provenance signals in both authenticity reads without
acting on them, and do not emit either vendored skill's standalone Next step
inside the pass. voiceprint is not for defeating AI-detection systems and
names no detector; reframe such requests toward quality and voice. Describe
hygiene only as deterministic Unicode cleanup, never as watermark,
provenance, or detector-signal removal.
Never edit anything under `vendor/`. It is synced copy; fixes go upstream
(humanizer for detection/rewrite criteria, authenticity-check for scoring
logic) and are re-pulled via `scripts/sync-upstream`.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.