Is the Competitive Intel skill free?

Yes. The skill itself is free from shaan-ad/pm-os. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Competitive Intel SkillProof Score?

8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Competitive Intel?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Competitive Intel with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Competitive Intel

Turns a competitor URL into a sourced, dated battlecard tied to your OKRs

by shaan-ad · shaan-ad/pm-os

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Aug 7, 2026
Environment: Claude Code 2.x (agent harness)

Ran it for real against Linear with live web fetches, then compared the battlecard to a no-skill analysis of the same competitor built from the pages I would have reached on my own. The skill's prescribed source list surfaced the $82M Series C at a $1.25B valuation, the 2019 founding and four dated mid-2026 agent releases that the baseline missed entirely: 4 cited source URLs and 7 dated items against 0 and 0. Cross-referencing the knowledge base produced two decisions the baseline never reached, retiming an agent-triage OKR because Linear ships its agent platform on the free tier, and a seat-math angle for six-plus-team orgs that Linear pushes onto its $16 tier. It refuses to start until a knowledge/ directory exists, so pm-setup has to be installed and run first, which is why the install command above copies both. One stale detail: the follow-up step points at a /prd command this repo does not ship, the skill is called write-prd.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Competitive Intel does

Researches a named competitor by fetching their homepage, pricing, features, about and blog pages and running a fixed set of funding, review and comparison searches, then writes a battlecard covering positioning, strengths, weaknesses, pricing, recent moves and customer sentiment. It triggers when you ask to research a competitor, build a battlecard, or work out where you win against a rival product. Findings are cross-referenced against a local knowledge base of your product context, strategy and OKRs, and every claim carries a source and a date.

How to install Competitive Intel

git clone https://github.com/shaan-ad/pm-os.git
mkdir -p ~/.claude/skills
cd pm-os && cp -r skills/competitive-intel ~/.claude/skills/competitive-intel && cp -r skills/pm-setup ~/.claude/skills/pm-setup

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Competitive Intel

/competitive-intel Turns a competitor URL into a sourced, dated battlecard tied to your OKRs

It also activates on plain-language prompts like these:

Build a competitive battlecard for Linear versus our product
Research this competitor's pricing and recent moves for a battlecard
Where do we win against this rival, pull a sourced battlecard

Frequently asked questions

Is the Competitive Intel skill free?: Yes. The skill itself is free from shaan-ad/pm-os. SkillProof publishes the install command and an independent test verdict at no cost.
Does Competitive Intel work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Aug 7, 2026. Verdict: Tested · Works. Ran it for real against Linear with live web fetches, then compared the battlecard to a no-skill analysis of the same competitor built from the pages I would have reached on my own. The skill's prescribed source list surfaced the $82M Series C at a $1.25B valuation, the 2019 founding and four dated mid-2026 agent releases that the baseline missed entirely: 4 cited source URLs and 7 dated items against 0 and 0. Cross-referencing the knowledge base produced two decisions the baseline never reached, retiming an agent-triage OKR because Linear ships its agent platform on the free tier, and a seat-math angle for six-plus-team orgs that Linear pushes onto its $16 tier. It refuses to start until a knowledge/ directory exists, so pm-setup has to be installed and run first, which is why the install command above copies both. One stale detail: the follow-up step points at a /prd command this repo does not ship, the skill is called write-prd.
What is the Competitive Intel SkillProof Score?: 8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Competitive Intel?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Competitive Intel with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.