Skip to content
CAI
Software that uses CAICheck a score

blader/humanizer

47.5

Weak · 18 September 2026

67

lines of production code

Python

primary language

1

measurement over time

CAI band scale
CAI lens gauges

What this system is

This system is a validation tool designed to enforce structural consistency and quality standards within the Humanizer package. It operates by verifying that key documentation files, such as SKILL.md and README.md, adhere to specific constraints regarding versioning, pattern sequencing, and file size. The primary purpose is to ensure that the package's metadata and documentation remain synchronized and well-structured.

Features

New package validation script for Humanizer

A new \scripts/validate-package.py\ script has been added to enforce consistency and structure in the Humanizer package. It verifies that SKILL.md, README.md, and plugin.json share a single version number, ensures SKILL.md contains sequentially numbered patterns without gaps, checks that the README accurately reflects these patterns, and enforces constraints such as keeping SKILL.md under 400 lines and using a single root SKILL.md file.

scripts · high confidence

Written by watchdog.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

Baseline

  • First survey — no prior run to compare against. CAI 47.

Lenses

  • Code Health 100
  • Architecture 69
  • Maturity 45
  • Readiness 29
  • Security 100

Changes since last survey

  • 75 commits — 59 feature/other, 16 fixes

By area

  • (root) — 52 commits
  • (repo) — 20 commits
  • scripts/validate-package.py — 2 commits
  • .github/workflows — 1 commit

Notable commits

  • fix: Add minor fix for excessive usage of "actually" in chatbot output, Fixes #72
  • fix: Cleanup pass: cut bloat and fix the aggressiveness contradiction (v2.6.0)
  • fix: Fix Agent Skills version metadata (v2.8.3)
  • fix: Fix Claude Desktop ZIP uploads (v2.11.1) (#226)
  • fix: Fix Claude Desktop plugin discovery (v2.10.2)
  • fix: Fix installation instructions
  • fix: Fix package validator UTF-8 reads (#214)
  • fix: Fix pattern #18 curly quotes example
  • fix: Fix pattern count in WARP.md: 24 → 25
  • fix: Merge pull request #121 from Longman006/fix/section-26-attributive-vs-predicate-hyphens
  • fix: Merge pull request #74 from marcoenricovd-lang/fix/warp-pattern-count
  • fix: Merge pull request #84 from mvanhorn/fix/78-content-preservation
  • fix: fix: add content preservation rule and strengthen em dash pattern
  • fix: fix: preserve ranking and simultaneity claims
  • fix: fix: reject top-level version in package validation
  • fix: fix: remove horizontal rule separators from SKILL.md (#35)
  • change: Accept cross-agent install updates
  • change: Add Detection Guidance: false positives, human-writing signs, LLM idiolects
  • change: Add Personality and Soul section
  • change: Add em/en dash cut, gap-filling tell, and diff-anchored pattern (v2.7.0)
  • …and 55 more

Written by watchdog.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

blader/humanizer was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 18 September 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit 9862685f575c65a8247f90369951df1b3416e3d6 — the exact code this score is about.
  • Scored under rubric-2026.09.15 — the same rubric and the same method as every other entry in this index.
  • Measured by watchdog.canine.dev using codehealth-analyzer preprod-5d04157a340d.