Skip to content
Back to skills

Mk 037

ASecurity

Information-gap assessment. Use when the task requires information each need still requires before action. Apply this method to the specified inputs and verify the deliverable

  • 259 stars
  • 0 votes
  • 0 copies
  • 6 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-037 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mk 037?

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

Security grade badge for Mk 037
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/backtrue-mk-037/badge)](https://www.skillsdirectory.com/skills/backtrue-mk-037)

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-037
description: "Information-gap assessment. Use when the task requires information each need still requires before action. Apply this method to the specified inputs and verify the deliverable"
---

# MK-037 | Information-gap assessment

For a regular chat, upload `packs/mk-037.md`. It includes the shared rules, this method, and required references

## Purpose

This skill delivers: **Information each need still requires before action**

Task stages are analytical categories, not a claim that every customer follows the same path

## Required inputs

Provide: The product or service, customers' own words, existing pages, and actions the company can support

## Method

1. For every search/path, mark the points that are currently only inferred
2. Focus on whether the customer problem is real, the recommended page actually exists, and the customer would actually want to take the next step
3. If evidence is missing, mark "insufficient evidence"; do not invent stories to fill the table

## Calculations and interpretation

Search phrases and paths are planning hypotheses; check them against real search terms and evidence of how pages support the need

## Required output fields

| Order | Field | How to complete |
|---:|---|---|
| 1 | Unit of analysis | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 2 | Original clue | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 3 | Classification definition | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 4 | Classification result | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 5 | Support/counterexample | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 6 | Unknown | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 7 | Downstream use | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |

## Verification cases

**MK-037-C05 | One record meets opposing conditions**

Expected: Mark it contradictory or undetermined; do not arbitrarily assign the most common category

## Method sources

Source file: Google Ads 第一堂|看懂需求,才知道廣告怎麼接

Location: Intent

Source basis: extracted from course materials

Source URL: https://docs.google.com/presentation/d/15ZOg0pX_xikpdA3FwGEoCSVgWortvCnxSe4hz4ugizg/edit

English translation of source excerpt:

> From need triggers and search intent to supporting ads and pages

Files in this skill

  • SKILL.md2.6 KB
  • assets/check-context.py14.6 KB
  • assets/context-contract.json8.9 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.