hyv-strict-check

SkillDev tools

Run the local strict AI-pattern and calibrated voice-match gate.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the hyv-strict-check skill

What this skill tells your AI

The instructions your AI receives, as published by shashank-sn/holdyourvoice in skills/hyv-strict-check/SKILL.md and read by ahel’s review.

Run the calibrated strict local quality gate without changing the draft, profile, or learning state.

Usage

hyv strict-check draft.md profile-v3.json sample-a.md sample-b.md sample-c.md sample-d.md sample-e.md

Behavior

  • Requires a Profile v3 built from at least five samples, five or more local validation samples, 1,500 validation-sample words, no duplicate samples, a consistent visible format baseline, and calibrated fingerprint tolerances.
  • Returns strict-ready, needs-human-review, or blocked as JSON and exits 0 only for strict-ready.
  • blocked covers missing strict evidence, every active AI Editor pattern, hard calibrated fingerprint drift, red VoiceDNA findings, and unresolved hidden text.
  • needs-human-review covers remaining non-blocking VoiceDNA or editorial review findings. It is not a clean result.
  • It remains local-first and never sends samples or drafts to a provider.

Handoff

Fix only the named finding, then rerun the command. Do not rewrite unflagged text or promote any edit into learning from this command. Only after strict-ready, run hyv-final-check on the exact text that will be delivered; that final output boundary remains required after any later edit or formatting step.

Signals

GitHub stars
32
Last commit
Sep 2026
Advanced
Item type
skill
Key
hyv-strict-check
Source
github.com/shashank-sn/holdyourvoice