intelligence-collection-disciplines
Run competitive research like an intelligence agency: eight collection disciplines (OSINT to MASINT), signal-to-inference chains, and fusion. Use when one-source research isn't enough.
npx skills add deanpeters/Product-Manager-Skills --skill intelligence-collection-disciplines --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill presents eight independent disciplines (OSINT to MASINT to All-Source Fusion) for competitive or market research and then fuses them using confidence stacking to form defensible conclusions. It maps each discipline to what to collect, where to collect it, the signal-to-inference chains, and the PM artifact it feeds.
How it works
Each discipline lists free and paid sources across categories (e.g., OSINT, FININT, GEOINT/DEMOINT, TECHINT, HUMINT, SIGINT, MASINT, All-Source Fusion).
- For each discipline, it provides signal→inference chains examples (e.g., how specific signals translate into inferences like market entry, pricing shifts, roadmap bets).
- It outlines an explicit TAM/SAM/SOM workflow within GEOINT/DEMOINT, including how to compute SOM from revenue and claimed customer counts.
- It specifies feeds such as battle cards, positioning, ICPs, personas, and market-entry prioritization.
When to use it
Use when one-source research isn’t enough, and you want an eight-discipline playbook to cross-validate signals and fuse evidence into strong conclusions. It emphasizes decision-driven research: if DECISION is blank, research is discouraged.
What it can touch
The skill references tools and sources across free and paid tiers (e.g., SEC EDGAR, patents databases, industry analyses, government portals) and maps signals to PM artifacts. It includes a list of sources and chains but does not specify executing code or direct manipulations by the agent beyond suggesting channels and interpretations.
Caveats
The content describes a structured methodology for intelligence-style competitive research using multiple independent disciplines and fusion. It emphasizes that sources are public or observable and that independence reduces likelihood of unified deception across channels. No licensing or risk statements beyond the provided limitations are shown in this excerpt.
# Intelligence Collection Disciplines ## Purpose Stop doing competitive research like a term paper. The intelligence community solved this problem decades ago: they don't collect "data," they run **collection disciplines** — independent channels, each with its own sources, tradecraft, and blind spots — and then they *fuse* them. This skill gives product managers that playbook: eight disciplines, each telling you (1) what to collect, (2) where to collect it, (3) which signal → inference chains to run, and (4) which PM artifact it feeds (TAM/SAM/SOM, ICPs, personas, battle cards, roadmap bets, win/loss, positioning, pricing). One signal is an anecdote; three correlated signals from independent disciplines is intelligence. ## Input **Works best with** the six instantiation variables below — fill them once and every discipline becomes engagement-specific. Leave them blank and this stays a teaching artifact. ~~~ [TARGET] = The competitor, partner, or acquirer you're researching [MARKET] = The category and its NAICS/SIC/NACE codes (or nearest equivalent) [GEOGRAPHY] = Regions in scope, at COUNTRY level, not continent level [BUYER] = Who signs the check (drives review sites, job titles, c
- Purpose
- Input
- Key Concepts
- The Eight Disciplines
- Application
- 1. OSINT — The Journalist's Desk
- 2. FININT — The Forensic Accountant
- 3. GEOINT/DEMOINT — The Cartographer
- 4. TECHINT — The Patent Examiner
- 5. HUMINT — The Sports Scout
- 6. SIGINT — The Wiretap You're Allowed to Have
- 7. MASINT — The Satellite Photo
- 8. All-Source Fusion — The Situation Room
- Mapping disciplines to PM artifacts
What does the intelligence-collection-disciplines skill do?
Run competitive research like an intelligence agency: eight collection disciplines (OSINT to MASINT), signal-to-inference chains, and fusion. Use when one-source research isn't enough.
How do I install it?
Run `npx skills add deanpeters/Product-Manager-Skills --skill intelligence-collection-disciplines --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From deanpeters/Product-Manager-Skills, a repository with 6,255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.