company-intel
Research a company, industry, or competitor set using web search and seven analytical lenses. Use when you need structured intel that feeds downstream PM skills.
npx skills add deanpeters/Product-Manager-Skills --skill company-intel --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
Research engine that builds deep, structured understanding of companies, industries, and competitor sets through seven analytical lenses, producing a stable output format for downstream PM skills (battlecards, SWOT, positioning, PESTEL, market sizing, workshop content).
How it works
Act as a live research engine using seven lenses on the target. It auto-detects entry point (single company, industry, named competitor set, or discover competitors). It gathers data from web sources (investor materials, product pages, regulatory filings, patents, hiring, leadership) and formats the result into an 11-section output per entity, plus a cross-company comparison when applicable. It includes citations for every factual claim and prioritizes sources from the last 12-24 months. If the input requests discovering competitors, it first researches the named company, identifies 3-5 likely competitors with rationale, then presents a list for confirmation before proceeding with full analysis.
When to use it
Use when you need structured intel to feed downstream PM skills, such as battlecards, SWOT analyses, positioning statements, PESTEL assessments, market sizing, or workshop content. Applicable to a single company, an industry/sector, or a named competitor set; can also perform a discover-competitors flow.
What it can touch
Uses live web search to gather data across seven lenses and outputs sourced claims with citations. No code execution or tool invocations are described beyond web research and structured reporting.
Caveats
Outputs are conditioned on live data availability and source quality, with recency emphasized (12-24 months). The method requires citing sources for every factual claim and distinguishing between primary, secondary, and inferred signals. The approach aims for stable, repeatable outputs suitable for downstream consumption.
## Purpose Research engine that builds deep, structured understanding of companies, industries, and competitor sets. Produces a stable output format that you can hand off to other skills and agents to generate battlecards, SWOT analyses, positioning statements, PESTEL assessments, market sizing, and workshop content. This is not a generic encyclopedia lookup. Every section pushes toward commercial understanding, product implications, and actionable intelligence. The output is a research primitive — structured data other skills consume — not a final deliverable. ## Input **Works best with:** The research target: a company, an industry, or a set of competitors. **Also useful:** The downstream use (battlecard, SWOT, positioning, market sizing) so the research emphasizes the right lenses, plus any constraints on depth or recency. Anything supplied with the invocation itself — text after the skill name, a pasted context dump, or an appended `ARGUMENTS:` line — counts as answers already given. Use it and skip whatever it covers; don't re-ask. **Arriving empty-handed? That works too.** The workflow opens by asking for the target and what the intel will feed. **Example invocation:** `Resea
- Purpose
- Input
- Key Concepts
- Four Entry Points
- Seven Research Lenses
- Key Distinctions to Maintain
- Tensions Worth Surfacing
- Why This Works
- Anti-Patterns
- Research Expectations
- Application
- Step 1: Detect Entry Point
- Step 1b: Discover Competitors (when entry point is "discover competitors")
- Step 2: Research and Produce Output
What does the company-intel skill do?
Research a company, industry, or competitor set using web search and seven analytical lenses. Use when you need structured intel that feeds downstream PM skills.
How do I install it?
Run `npx skills add deanpeters/Product-Manager-Skills --skill company-intel --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.