Skip to content
Back to skills

Mk 326

ASecurity

Answer-First Paragraph Check. Use when work requires locations where answers are buried too deeply or not given directly; process the specified inputs using this method and verify the deliverable

  • 259 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added October 23, 2026
ai-agentsgo

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned October 23, 2026

npx -y skills add backtrue/thinkwithblack-skill --skill mk-326 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mk 326?

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

Security grade badge for Mk 326
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/backtrue-mk-326/badge)](https://www.skillsdirectory.com/skills/backtrue-mk-326)

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: mk-326
description: "Answer-First Paragraph Check. Use when work requires locations where answers are buried too deeply or not given directly; process the specified inputs using this method and verify the deliverable"
---

# MK-326 | Answer-First Paragraph Check

For ordinary chat, upload `packs/mk-326.md`, which includes the shared rules, this method, and required references

## Purpose

This skill delivers: **Locations where answers are buried too deeply or not given directly**

General content rewriting differs from Speak Human TW language review; do not automatically apply its review documents without an explicit trigger

## Required inputs

Provide: the full article, reader questions, sources, and actual experience or evidence

## Method steps

1. Directly answer the question in the first 2–4 sentences below each H2, then add background, reasons, examples, and differences
2. Answer-First means placing the answer first, rather than removing context
3. If the answer appears only in the latter half of the paragraph, mark it as insufficiently front-loaded

## Calculation and interpretation

Check only presence and clarity; do not invent experts, experience, or data, or guarantee AI citations

## Required output fields

| Order | Field | How to fill it in |
|---:|---|---|
| 1 | Subject / location | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 2 | Conditions for use | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 3 | Actual evidence | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 4 | Check status | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 5 | Differences / possible causes | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 6 | Next task | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 7 | Limitations | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |

## Validation cases

**MK-326-C05|Data meets the existing conditions**

Expected: Report that it is usable or should be maintained; do not invent a need for changes

**MK-326-C06|Tool returns an error**

Expected: Report that the data was not obtained; do not classify it as a business anomaly

## Method sources

Original file: SEO104_AI可引用文章檢查表

Source locator: checks

Source basis: extracted from course materials

Original URL: https://docs.google.com/presentation/d/1hmaWbUWe-BsaRUVA9IpGrLUt7wQ8wdIVHe4W_Sg4uP4/edit

English translation of source excerpt retained in the master sheet:

> The task of 104: check whether an article has the conditions needed for AI citation

Files in this skill

  • SKILL.md2.8 KB
  • assets/check-context.py14.6 KB
  • assets/context-contract.json10 KB

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.

View all in ai-agents →

Comments

Loading comments…

Newsletter

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