Competitive teardown
Prompts don't compound. Skills do. The open-source AI toolkit for product managers — 13 Claude Code skills + 3 red-team agents for the full PM workflow.
npx -y skills add ramanbamba/10x-pm --skill competitive-teardownAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Produce a structured competitive analysis of a rival product or company, focused on strategy and positioning rather than feature checklists. Use when the user says "tear down [competitor]", "competitive analysis", "how do we compare to X", "what is [company]'s strategy", or asks to analyze a competitor's launch or pricing.
SKILL.md
3.5 KB, as published. Nobody here has run it
Competitive Teardown
Analyze a competitor the way a strategist does: infer why they're doing what they're doing, and what it means for the user's product. A feature comparison table is an input, not the deliverable.
Before analyzing
- Ask what decision this feeds: positioning? roadmap defense? pricing? a deal against them? The lens changes the analysis.
- Ask what the user's product is and where the two actually overlap. Half of "competitors" are adjacent, not competitive.
- Research with live sources — pricing pages, changelogs, job postings, earnings calls, review sites (G2, app stores). Use web search; do not rely on training-data memory for anything time-sensitive. Date every fact.
Workflow
- Facts first. Collect: pricing and packaging, last 6–12 months of shipped features, target segments (inferred from marketing language), hiring signals, funding/earnings context. Cite sources with dates.
- Infer the strategy. From the fact pattern, answer: what game are they playing? (Move upmarket? Land-and-expand? Bundle to kill a category?) State the inference as an inference with a confidence level.
- Find the strategy's shadow. Every strategy makes something hard for them. Moving upmarket abandons the low end; bundling degrades depth. This is where the user's opportunity lives.
- Steal shamelessly, once. Identify one thing they do better that the user should copy. Teardowns that find nothing to admire are propaganda.
- Threat-rank honestly. Where do they actually beat the user today, for which segment? Sugar-coating this wastes everyone's time.
Output format
# Teardown — [Competitor], [date]
**Decision this feeds:** [decision] · **Overlap:** [where you actually compete]
## Their strategy in one paragraph
[The inferred game they're playing, confidence level, and the 3 strongest facts behind it]
## Fact base
| Area | What we know | Source, date |
|---|---|---|
| Pricing/packaging | | |
| Recent ships | | |
| Target segments | | |
| Hiring/investment signals | | |
## Where they beat us
[Honest, segment-specific. Quote their customers' praise from review sites.]
## The shadow — where their strategy exposes them
[What their choices make structurally hard for them, and the segment/use case it opens for us]
## One thing to steal
[The single practice/feature/positioning move worth copying, and how]
## Implications
[3 max: what we should do differently in positioning, roadmap, or sales — each tied to a finding above]
## Watch triggers
[Specific events that would change this analysis, e.g. "if they ship X" or "if pricing drops below Y"]
Quality bar — self-check
- Every fact is dated and sourced. Undated competitive intel is folklore.
- Strategy is labeled as inference with a confidence level, never stated as fact.
- "Where they beat us" is non-empty and specific. If it's empty, the analysis is dishonest — dig again.
- Implications ≤ 3 and each traces to a finding. A teardown that implies "do everything" implies nothing.
- No feature-table-as-conclusion. Tables support the argument; they are not the argument.