scqa

A four-part structure for clear communication: Situation, Complication, Question, and Answer. It starts with shared context, explains what changed, states the issue, and gives the answer.

In plain words
What is it for?
Use it to write executive briefings, stakeholder emails, consulting presentations, product proposals, and other messages that need a strong opening.
Why use it?
It creates a clear line from context to problem to response, helping readers understand why the message matters.

Skill for Claude CodeCodex

Part of the instinct plugin — 54 skills, 1 hook shipped together

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/tupe12334/instinct/scqa
Any agent
npx skills add tupe12334/instinct --skill scqa
Clone the repo
git clone --depth 1 https://github.com/tupe12334/instinct

Made for: Claude Code, Codex.

Or install instinct, the plugin that ships this one along with the rest of its 54 skills, 1 hook.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,159 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 $0.00022 $0.02159
Opus 5 $0.00011 $0.01079
Sonnet 5 $0.00004 $0.00432
Haiku 4.5 $0.00002 $0.00216

Measured 2d ago against content hash b3a16447c3a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scqa 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.

skills/scqa/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SCQA (Situation → Complication → Question → Answer)

Overview

SCQA is a narrative opening structure from Barbara Minto's Pyramid Principle. It hooks the audience by establishing shared ground (Situation), introducing tension (Complication), crystallizing the implied question (Question), and delivering the answer upfront (Answer). The result is communication that earns attention instead of demanding it.

┌─────────────────────────────────────────────────────────────┐
│  S ──► C ──► Q ──► A                                        │
│                                                             │
│  Situation     Complication    Question       Answer        │
│  (agreed       (something      (what the      (your         │
│   context)      changed or      audience is    governing    │
│                 went wrong)     now asking)    message)     │
└─────────────────────────────────────────────────────────────┘

Tension builds across S → C → Q, then releases at A.

Use SCQA to open executive briefings, emails to senior stakeholders, consulting decks, product proposals, and any communication where you need to be read — not skimmed.

Element Breakdowns

S — Situation

State facts the audience already accepts as true. This is not your argument — it is shared ground that anchors everything that follows.

Include:

  • The stable background state before anything went wrong
  • Scope: the business, team, product, or market being discussed
  • Enough context for the audience to recognize the world you are describing

Keep it to 1–3 sentences. If the audience challenges anything in your Situation, you have started too far into disputed territory — move earlier.

Bad: "Our product is struggling and we need to fix it." Good: "For the past two years, our enterprise tier has been our highest-margin segment, accounting for 60% of ARR."

C — Complication

Introduce the tension that makes the Situation unstable. This is the reason you are communicating at all.

Types of complications:

  • Something changed (market shift, new competitor, regulation)
  • Something failed (metric missed, project slipped, assumption proven wrong)
  • Something is about to happen (deadline, board review, contract renewal)
  • A contradiction emerged (two true things that cannot both stand)

Read the full file on GitHub · 166 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 · 166 lines · 22 tokens per session scan A b3a16447c3a0

Subscribe to this mod's changes

scqa is a skill published in the GitHub repository tupe12334/instinct (1 stars, last pushed 16d ago), licensed MIT. It adds 22 tokens to every session and 2,159 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 2026-08-31.