hyv-fact-lint

SkillDev tools

Lint factual claims in a draft against named sources.

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-fact-lint skill

What this skill tells your AI

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

Lint factual claims in a draft against one or more named sources passed as --source=id:path. Optional --metadata provides fact metadata, --strict raises severity, and --human selects the human-readable report.

Usage

hyv fact-lint <draft|-> --source=id:path [--source=id:path] [--metadata=metadata.json] [--strict] [--human]

Behavior

  • Deterministic and local-first: this command never calls a provider and never sends drafts, samples, profiles, or telemetry to a service.
  • Commands that write use an explicit output path. Confirm that path before running the command.
  • This agent describes how to invoke the command and what it returns. It does not change command behavior or exit codes.

Handoff

Run hyv fact-lint directly to execute the operation. Follow-on agents: hyv-verify.

Signals

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