watcher-gate

Verifies marketing outputs with independent watcher passes before promotion to scheduled status.

9|Updated May 8, 2026
One-click install
npx skills add https://github.com/simpletibr/simplicio-loop-marketing --skill watcher-gate-simpletibr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: watcher-gate
Source: https://github.com/simpletibr/simplicio-loop-marketing/tree/main/.skills/watcher-gate
Command: npx skills add https://github.com/simpletibr/simplicio-loop-marketing --skill watcher-gate-simpletibr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated marketing content can drift from what was actually produced or claimed, and unverified pieces risk being published. This Skill enforces a verification gate so every generated output is independently re-checked before it can move from draft to scheduled or be promoted into ads. ## Core Features & Use Cases - Independent Verification: A watcher re-computes each generated output and compares it against what the generating agent reported. - Verification Tagging: Outputs are tagged MEASURED (watcher-verified), CANON (sourced from canonical brand/pillar/compliance specs), or UNVERIFIED (no verification performed). - Gate Enforcement: UNVERIFIED pieces are blocked from the draft-to-scheduled transition and from ads-draft creation, while watcher mismatches route pieces to review with a full report. - Use Case: After generating a batch of social captions, run the watcher gate so any caption whose claims cannot be independently verified is held back from scheduling and sent to review instead. ## Quick Start Run the watcher gate on my latest generated marketing outputs and block any piece tagged UNVERIFIED from being scheduled.

Frequently Asked Questions about watcher-gate

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I verify AI-generated marketing content before publishing?

Run each generated output through a watcher gate that independently re-computes the result and compares it to what the generating agent reported. Outputs that match are tagged MEASURED and can proceed; mismatches are routed to review with a full discrepancy report.

What is a watcher gate in a content generation pipeline?

A watcher gate is a verification step that sits between content generation and scheduling. It re-checks every output and assigns a tag: MEASURED for verified pieces, CANON for content sourced from canonical specs, and UNVERIFIED for pieces with no independent check.

Can unverified marketing content be scheduled or promoted to ads?

No. Pieces tagged UNVERIFIED are blocked from the draft-to-scheduled transition by the pre-flight rule, and the claims-gate blocks them from ads-draft creation in the promote loop. They must pass watcher verification first.

What happens when the watcher finds discrepancies in generated content?

When the watcher's independent pass does not match what the agent reported, the piece is routed to review status along with a full watcher report detailing the discrepancies, preventing it from advancing until resolved.

What are the limitations of watcher-based content verification?

Watcher verification only confirms that reported outputs match independent re-computation; it does not judge creative quality or brand fit. Content sourced from canonical specs is tagged CANON and bypasses measurement, so spec accuracy must be maintained separately.