hyv-strict-check
SkillDev toolsRun the local strict AI-pattern and calibrated voice-match gate.
Available today. Use it from your connected AI after setup.
No other account needed.
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, orblockedas JSON and exits0only forstrict-ready. blockedcovers missing strict evidence, every active AI Editor pattern, hard calibrated fingerprint drift, red VoiceDNA findings, and unresolved hidden text.needs-human-reviewcovers 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