What do I need to use Competitive Scan Lite?

The decision the scan feeds; The competitor set, argued; What's already known; The freshness need.

Is Competitive Scan Lite free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Competitive Scan Lite

Q: How do I know the Competitive Scan Lite output is good?

The skill verifies itself against its own quality checks: Dimensions trace to the decision and stay ≤7; Every cell is sourced and flagged claimed/observed/user-reported; Rivals got their steelman with evidence; Empty cells are labeled, not inferred.

🔵 Stable🕐 updated 2026-07-19 🔷 SkillSpec L3 pm-cowork

Run a fast, honest competitive scan — the dimension table built from public evidence (sites, docs, pricing pages, changelogs, reviews), the claims-vs-observed discipline, and the so-what synthesis that ends in moves, not a landscape mural. Use when asked what are competitors doing, quick scan of these three rivals, how does our pricing/feature set compare, or prep the competitive slide honestly. Produces the evidence-based comparison table, the marketing-vs-reality flags, the so-what synthesis, and the staleness date.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The decision the scan feeds — pricing review? Roadmap bet? A deal's competitive slide? The dimensions come from the decision, not from "everything about everyone"

▸The competitor set, argued — who actually competes for the same customer decision (the aspirational rival and the real alternative — often "spreadsheets" — both belong or don't, per the decision)

▸What's already known — the team's current beliefs and battle-scars (sales's anecdotes are evidence at anecdote grade — [evidence-grading](../evidence-grading/SKILL.md) applies)

▸The freshness need — one-shot for a decision, or a standing scan with a refresh cadence?

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Dimensions trace to the decision and stay ≤7

✓Every cell is sourced and flagged claimed/observed/user-reported

✓Rivals got their steelman with evidence

✓Empty cells are labeled, not inferred

✓The synthesis ends in moves and carries the staleness date

⚠️ What it refuses to do

Do not build the mural — a landscape without implications is wall art with a legend

Do not launder homepage claims into capability facts — the flags exist for both directions

Do not scan the convenient weaknesses — the steelman is what preps the team for real deals

Do not fill unknowable cells by vibe — "not public" is an honest, useful entry

Do not reuse a stale scan silently — pricing cells lie within a quarter; the stamp is load-bearing

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="competitive-scan-lite"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Competitive Scan Lite is one of 750 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog