Skip to content
Back to skills

Ztx10 Evidence First Review

ASecurity

Collect browser/CI/source evidence before making quality judgments.

  • 14 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
testinggit

Security analysis

A100/100

Scanned November 7, 2026

npx -y skills add Realjustawall/Perfect-AI --skill ztx10-evidence-first-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ztx10 Evidence First Review?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Ztx10 Evidence First Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/realjustawall-ztx10-evidence-first-review/badge)](https://www.skillsdirectory.com/skills/realjustawall-ztx10-evidence-first-review)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: ztx10-evidence-first-review
description: "Collect browser/CI/source evidence before making quality judgments."
---
# Evidence First Review

**Intent:** Collect browser/CI/source evidence before making quality judgments.

## Execution protocol
1. Capture device, URL, timestamp, viewport, locale and git revision. Require tangible evidence, a clear owner, and a pass/fail check.
2. Capture screenshots including scroll checkpoints. Require tangible evidence, a clear owner, and a pass/fail check.
3. Save DOM and computed styles for critical components. Require tangible evidence, a clear owner, and a pass/fail check.
4. Record failing network/console/interaction tests. Require tangible evidence, a clear owner, and a pass/fail check.
5. Mark missing artifacts explicitly. Require tangible evidence, a clear owner, and a pass/fail check.

## Inputs/Outputs
Input: site profile, approved brand, evidence path, task brief and allowed capabilities. Output: strict machine-readable report or orchestration plan with selected roles and reasons.

## Safety and correctness
- No existing skills may be removed. No third-party repository is executed by default.
- No edits until a human explicitly authorizes a separate fix flow.
- Always report not-run tests and confidence. Do not inflate the number of independent agents from identical prompts.
- Verify the implementation and its regression tests before completion.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.