scqa-framework

A framework for explaining complex topics in four parts: situation, complication, question, and answer. It gives a narrative a clear starting point, problem, question, and conclusion.

In plain words
What is it for?
Use it to structure design proposals, technical documents, presentations, and explanations of difficult decisions.
Why use it?
It helps prevent technical explanations from becoming a list of disconnected facts. Readers understand why the answer matters before they receive it.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/stefan-jansen/claude-code-toolkit/scqa-framework
Any agent
npx skills add stefan-jansen/claude-code-toolkit --skill scqa-framework
Clone the repo
git clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkit

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,634 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.02634
Opus 5 $0.00010 $0.01317
Sonnet 5 $0.00004 $0.00527
Haiku 4.5 $0.00002 $0.00263

Measured 2d ago against content hash eb0c11b9f776, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scqa-framework scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

examples/writing/skills/scqa-framework/SKILL.md · 412 lines

How it starts

The opening of the file, as written. The whole thing — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SCQA Framework Skill

Foundation: McKinsey's SCQA (Situation-Complication-Question-Answer) framework, derived from Barbara Minto's pyramid principle

Core Concept: Build compelling narrative by establishing situation, introducing complication, raising question, then delivering answer.

Why This Works:

  • Engages reader with familiar situation
  • Creates tension with complication (problem)
  • Raises question reader now wants answered
  • Delivers answer with impact (reader is primed)
  • Natural storytelling flow

The SCQA Structure

Four elements in sequence:

1. Situation (S)

What: The stable, uncontroversial starting point everyone agrees on

Purpose: Establish common ground with reader

Example:

"Software engineers use AI coding assistants to boost productivity."

Characteristics:

  • Non-controversial (reader nods along)
  • Familiar to target audience
  • Sets the stage for complication

2. Complication (C)

What: The problem, change, or challenge that disrupts the situation

Purpose: Create tension and make reader care

Example:

"But generic AI agents produce unreliable code - state corruption, context loss, hallucinations. Teams abandon them after weeks of frustration."

Characteristics:

  • Introduces conflict/problem
  • Makes status quo untenable
  • Resonates with audience pain
  • Creates urgency

3. Question (Q)

What: The question reader now wants answered (often implicit)

Purpose: Focus attention on the answer you're about to provide

Example:

"How can we get AI productivity benefits without the reliability chaos?"

Characteristics:

  • Natural question arising from complication
  • What reader is now thinking
  • Can be explicit or implicit
  • Sets up your answer

4. Answer (A)

What: Your solution, recommendation, or core message

Purpose: Deliver the answer reader is now primed to receive

Example:

"CAF provides production-grade architecture that prevents AI chaos through stateless, file-based patterns proven over 6 months."

Read the full file on GitHub · 412 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 412 lines · 19 tokens per session scan A eb0c11b9f776

Subscribe to this mod's changes

scqa-framework is a skill published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 2,634 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.