swot-analysis

# SWOT Analysis (Evidence-Cited)

## Purpose

Build an evidence-cited SWOT of one company — yours or a competitor's — from the public record:
**use or gather evidence → four labeled quadrants → crossings → next-step options.** Strengths and
weaknesses come from documented capability and customer voice; opportunities and threats from market,
competitor, and macro signals. Every entry carries a source and a label, and the analysis ends with
the S-O and W-T crossings — because a SWOT without "so what" is a parking lot with four sections.

## Input

**Works best with:** the company to analyze, the scope (whole company or one product line/market),
and **the decision this SWOT should support**.
**Also useful:** the perspective — theirs, or yours competing with them — and any research already in
session (a [`competitive-research-snapshot`](../competitive-research-snapshot/SKILL.md), VoC themes, a
landscape scan, [`company-intel`](../company-intel/SKILL.md) output): the SWOT then *synthesizes*
instead of re-searching.

Input supplied inline with the invocation — text after the skill name, a pasted context dump, or an
appended `ARGUMENTS:` line — counts as answers already given. Use it against the question budget;
don't re-ask.

**Arriving empty-handed? That works too.** The skill opens with at most 3 questions (company + scope,
decision, perspective) and proceeds on labeled assumptions if they go unanswered.

**Example invocation:** `Evidence-cited SWOT on [Competitor A]'s mid-market product line, from our
perspective — supports the Q3 positioning refresh. Last month's snapshot is attached.`

## Key Concepts

- **Governing protocol:** honors the [`autonomous-investigation`](../autonomous-investigation/SKILL.md)
  contract — question budget of 3, search-plan gate, Fact/Inference/Assumption labels, Just Enough
  Mode (max 5 ranked entries per quadrant), stable schema, 4-option Final Step. Disciplines: OSINT +
  FININT + HUMINT per [`intelligence-collection-disciplines`](../intelligence-collection-disciplines/SKILL.md).
- **Quadrant discipline.** S and W are *internal and current*; O and T are *external*. The most
  common SWOT error is an "opportunity" that requires the company to act — that's a strategy, not an
  opportunity. Flag it when you catch it; catching it is half the teaching.
- **Claimed vs. evidenced advantage.** Strengths sourced from the company's own marketing are
  claims; strengths corroborated by customer voice, filings, or independent coverage are evidence.
  Customer voice weighs heaviest on weaknesses — buyers document weaknesses vendors won't.
- **The crossings are the deliverable.** S-O names the attack (which strength unlocks which
  opportunity); W-T names the exposure (which weakness a threat finds first). SWOT is an input to
  moves, not a wall poster.
- **Companion, not substitute:** [`porters-five-forces`](../porters-five-forces/SKILL.md) reads the
  *industry's* structure; this reads *one company's* position within it. Run both when the decision
  is market entry.
- **When NOT to use:** internal-only SWOT from private knowledge → run it as a team workshop with
  your evidence; the whole competitor set → snapshot first, SWOT the one or two that matter.
- **Do-not-invent list:** financials, customer wins, market share, product claims, roadmap items.

## Application

1. **Check session for existing evidence** (snapshot, VoC themes, landscape scan, company-intel).
   Present → synthesize from it; search only gaps and staleness.
2. **Credit inline context**, then ask only the unanswered questions (max 3):
   1. Which company, and whole-company or one product line?
   2. What decision should this support?
   3. From whose perspective — theirs, or yours competing with them?
3. **If researching fresh, show the 3-bullet search plan** — source sweep (filings, reviews, press,
   pricing pages, hiring signals), how internal vs. external evidence will be separated, how facts
   split from inference. Continue unless revised.
4. **Emit the schema below exactly.**

### Output schema (do not reorder)

~~~markdown
# SWOT: [Company / Scope]
**As-of date:** | **Decision supported:** | **Perspective:**

## 1. Strengths (internal, evidenced)
- [Entry] — [evidence: URL, date] — [Fact/Inference]
- [Max 5, ranked by defensibility]

## 2. Weaknesses (internal, evidenced)
- [Entry — customer voice weighs heaviest here] — [URL] — [label]
- [Max 5, ranked by exploitability]

## 3. Opportunities (external)
- [Entry — market/macro signal] — [URL] — [label]
- [Max 5, ranked by fit to their strengths]

## 4. Threats (external)
- [Entry — competitor/regulatory/technology signal] — [URL] — [label]
- [Max 5, ranked by likelihood x damage]

## 5. The Crossings (the "so what")
- **S-O (attack):** [strength that unlocks which opportunity — 1-2 moves, labeled Inference]
- **W-T (exposure):** [weakness a threat will find first — 1-2 risks, labeled Inference]
- **For your decision:** [what this SWOT says about the decision named above, in 2 sentences]

### Assumptions to Validate
- [Assumption 1] / [Assumption 2] / [Assumption 3]
~~~

A copy/paste fill-in version of this schema, with quality checks, lives in [`template.md`](template.md).

### Final Step (offer exactly 4 options)

1. Run the W-T exposure into a battle card or risk plan ([`battle-card-builder`](../battle-card-builder/SKILL.md))
2. SWOT a second company for side-by-side comparison
3. Feed the crossings into a positioning statement ([`positioning-statement`](../positioning-statement/SKILL.md))
4. Schedule-ready version: which entries should a quarterly re-run watch?

Accept `1`, `2`, `3`, `4`, `1 and 2`, `Verbose Mode`, or a custom path.

## Examples

**The quadrant discipline catching a disguised strategy (fictional):**

> Draft opportunity: "expand into the compliance-automation segment." Caught and reclassified — that
> requires *them* to act, so it's a candidate strategy, not an opportunity. The underlying
> opportunity, restated externally: