Skip to content

Add AI-iness density pre-check to gate pass strength (closes #93)#115

Open
adelaidasofia wants to merge 1 commit intoblader:mainfrom
adelaidasofia:feat/density-precheck
Open

Add AI-iness density pre-check to gate pass strength (closes #93)#115
adelaidasofia wants to merge 1 commit intoblader:mainfrom
adelaidasofia:feat/density-precheck

Conversation

@adelaidasofia
Copy link
Copy Markdown

Summary

Per #93. Adds a pre-flight density check that counts Tier 1 dead-giveaway tells per 100 words and picks pass strength (light / mixed / full) before applying patterns.

This stops the skill from over-correcting human-first text (personal journals, rough drafts, meeting notes), where all-or-nothing rule application strips the exact quirks that made the writing sound like a person.

What changed

SKILL.md only. Strictly additive, no new tools, no infrastructure.

  1. New section ## Pre-flight: AI-iness Density Check inserted before ## Process. Defines Tier 1 as the seven dead-giveaway rules already in SKILL.md (1, 4, 7, 20, 21, 22, 25), the density thresholds, and the pre-flight announcement format the user sees.
  2. ## Process updated: step 2 runs the pre-flight check; the rest of the steps renumber accordingly.

41 added, 8 modified (renumbering only).

Density thresholds

Tier 1 hits / 100 words Mode Behavior
0 light Skip the rewrite. Apply only specific Tier 1 hits if any fire.
1-2 mixed (default) Tier 1 in full, other rules where they clearly fire. Preserves voice quirks.
3+ full All 29 rules. Text is AI-first and needs comprehensive rewriting.

Why these seven rules

Rules 1, 4, 7, 20, 21, 22, 25 are the patterns that almost never appear in authentic human writing (broader-trends framing, promotional language, AI vocabulary, "Certainly!" / "Of course!" openers, knowledge-cutoff disclaimers, sycophantic tone, generic positive conclusions). Restricting the density score to these keeps the signal clean. Lower-tier rules can fire as false positives on human writing, so counting them would inflate the score and trigger over-correction.

Verified

Running in production on a fork (adelaidasofia/humanizer) for several months on personal journal and rough-draft content. Eliminates the "humanizer made my writing worse" failure mode on human-first text. AI-generated text still routes to full mode and gets the comprehensive rewrite.

Notes

This is intentionally scoped to the issue. Other improvements in the fork (Spanish-language rule library, voice fingerprinting, ROI-ranked tiers for all 29 rules) are separate concerns and can ship as later PRs if you want them.

Counts Tier 1 dead-giveaway tells per 100 words and picks light/mixed/full
mode before applying patterns. Stops the skill from over-correcting
human-first text (personal journals, rough drafts, meeting notes) where
all-or-nothing rule application was stripping out the quirks that made
the writing sound like a person.

Tier 1 = the seven dead-giveaway rules already in SKILL.md (1, 4, 7, 20,
21, 22, 25). Density score is Tier 1 hits per 100 words:

  - 0 tells:  light mode, skip the rewrite (apply only specific Tier 1 hits)
  - 1-2:      mixed mode (default), Tier 1 in full + others where they clearly fire
  - 3+:       full mode, all 29 rules

Strictly additive to SKILL.md. No new tools, no infra changes.

Closes blader#93
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant