Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Problem Definition

ASecurity

Turns a vague symptom or an over-broad brief into a one-page SCQA problem statement and a single decision-shaped key question the work must answer.

8 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgoreact

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add andreworia/claude-consulting-skills --skill problem-definition --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Problem Definition?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Problem Definition
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/andreworia-problem-definition/badge)](https://www.skillsdirectory.com/skills/andreworia-problem-definition)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: problem-definition
description: Turns a vague symptom or an over-broad brief into a one-page SCQA problem statement and a single decision-shaped key question the work must answer.
---

# Problem Definition

## When to use
Use this when the problem is stated as a symptom ("sales are down"), as a solution in disguise ("we need a rebrand"), or as something too broad to solve ("fix growth"). It is the right skill whenever the team could spend weeks analyzing and still not agree on what question they were answering. Define the problem before scoping any work.

## What it does
It converts a fuzzy starting point into a crisp, agreed problem statement using the SCQA structure (Situation, Complication, Question, Answer-space), and it distills the whole engagement down to one key question. That key question is decision-shaped: answering it forces a choice, and it is narrow enough to be answered with evidence. A sharp key question is the single highest-leverage artifact in a strategy project.

## Method
The skill runs the SCQA discipline and then pressure-tests the resulting question.

1. Capture the raw ask verbatim. Write down exactly how the problem was handed over, in the sponsor's own words. This is the thing you will improve, and keeping it visible prevents scope drift later.

2. Establish the Situation. State the stable, uncontested context that everyone already agrees on. No tension yet, no blame. If a reader would nod along, it belongs in Situation.

3. Name the Complication. State what changed or what tension makes the situation no longer acceptable. This is the "but" that creates the need to act. Most weak briefs fail here because they never make the complication explicit.

4. Derive the Question. The Question follows directly from the Complication: given this tension, what must we now decide or resolve? Force it into a single interrogative sentence.

5. Bound the Answer-space. State the type of answer that would satisfy the sponsor: a go/no-go, a choice among options, a number, a plan. This stops the team from answering a different question than the one asked.

6. Sharpen the key question against five tests. Rewrite until it passes all five:
   - Decision-shaped: answering it changes what someone does.
   - Single: it asks one thing, not three joined by "and."
   - Scoped: the unit, market, and time horizon are explicit.
   - Answerable: evidence could in principle settle it inside the timeframe.
   - Neutral: it does not assume the answer or a preferred solution.

7. Separate the question from sub-questions. Anything that is really a component of the answer is parked. It belongs in the issue tree, not in the key question. The key question stays singular.

8. Confirm scope boundaries. State explicitly what is in and out of scope, and list the decisions this work will and will not make. Get the sponsor to agree to the one-pager before analysis begins.

## Inputs
- The raw ask as it was given, ideally verbatim.
- The sponsor and the decision the work is meant to inform.
- Any known constraints: timeframe, budget, non-negotiables, and what has already been decided.

## Output format
A one-page problem statement:
- The raw ask, quoted.
- Situation: the agreed context, two to three sentences.
- Complication: the tension that forces action, one to two sentences.
- Key question: one decision-shaped sentence, in bold.
- Answer-space: the shape of a satisfying answer.
- In scope / out of scope: two short lists.
- Sub-questions parked for the issue tree: a short list.

## Example
Raw ask: "Our margins are getting crushed, we need to cut costs."

Situation: The company sells a mid-market hardware product through distributors and has held roughly stable revenue for two years.

Complication: Gross margin has fallen for several consecutive quarters while revenue held flat, so the decline is coming from price or cost, not volume.

Weak question (rejected): "How do we cut costs?" It assumes the answer is cost, it is not decision-shaped beyond "cut," and it ignores price.

Sharpened key question: "Should we defend margin primarily through pricing and mix or through cost, and which specific move recovers the most margin within four quarters without losing share?"

Answer-space: a recommended primary lever plus the two or three specific moves under it, with the margin recovery each is expected to deliver.

In scope: pricing, product mix, and direct cost. Out of scope: acquisitions and a new product line. Parked sub-questions (for the issue tree): which segments are least price-sensitive, where cost is genuinely above benchmark, and how distributors would react to a price move.

Attribution

andreworiaandreworia
View sourceMore from andreworia →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →