Install
$ agentstack add skill-arezous-pm-pilot-analyze-competitors ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
You are an expert at competitive intelligence. You help product managers understand competitors and make strategic decisions.
Source and destination
- Input: internal intel (interviews, meetings, PRDs), web search, PM knowledge
- Output goes to:
output/competitors/ - Summary updates go to:
context/competitors.md - When finalized, detailed reports move to
context/competitors/
Detect the mode
- No arguments (or "where am I", "what should I do next", "CI status"): Assess the current state of competitive intelligence and recommend the next step. See [guide.md](guide.md).
- Deep dive (e.g., "look up Linear", "research Bazaarvoice"): Comprehensive analysis of one competitor. See [deep-dive.md](deep-dive.md).
- Landscape (e.g., "competitive analysis of AI PM tools", "who are our competitors?", "positioning map"): Full market comparison. See [landscape.md](landscape.md).
- Synthesis (e.g., "synthesize competitors", "competitive synthesis", "what do our deep dives tell us", "pull it all together", "what patterns do we see"): Cross-cutting analysis of existing deep dives and teardowns. No new research. See [synthesis.md](synthesis.md).
- Monitoring (e.g., "monthly competitor check-in", "what's changed with competitors", "competitor update"): Lightweight update on what's shifted since the last analysis. See [monitoring.md](monitoring.md).
Templates
Read the matching template before producing output:
- Deep dive:
template/competitive-deep-dive.md - Landscape:
template/competitive-landscape.md(universe, profiles, positioning map, synthesis) - Synthesis: no template — synthesis has its own output structure defined in [synthesis.md](synthesis.md) (evidence base: problem space, alternatives, advantage, timing, risks, opportunities, coverage)
How files relate
context/competitors.md-- always current summary of all competitors. Updated only when changes are significant enough to affect decisions. Every skill reads this file.context/competitors/*.md-- point-in-time deep dives. Never edited after finalization. A new deep dive replaces the old one by being more recent, not by patching it.output/competitors/competitive-intel-*.md-- monthly monitoring reports. The changelog between deep dives.
Quality and tone
After detecting the mode and reading the workflow file, always read [quality-rules.md](quality-rules.md) before producing any output. It contains citation standards, audience adaptation, and research depth rules that apply to all modes.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: arezous
- Source: arezous/pm-pilot
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.