Agent skill · marketing growth · deanpeters
swot-analysis
Build an evidence-cited SWOT of one company — yours or a competitor's — from public sources, ending with the S-O/W-T crossings. Use for strategy reviews, board prep, or competitor depth.
Why this skill is useful
Provides a structured methodology for conducting evidence-cited SWOT analyses that the AI wouldn't reliably generate on its own.
What it needs
About 6k tokens when loaded. Last updated 2026-07-17. 6,302 stars on the source repository.
What this skill does
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, VoC themes, a landscape scan, company-intel 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 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. Quadrant discipline. S and W are internal and current; O and T are external. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills deanpeters/swot-analysis