Install
$ agentstack add skill-julianoczkowski-product-manager-pm-opportunity-scoring ✓ 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Opportunity Scoring (Pragmatic Framework: Focus / Business)
Evaluate candidate opportunities objectively so a decision rests on evidence, not the loudest voice. Score each opportunity on four attributes using a 1-to-5 scale where 1 = Least Favorable and 5 = Most Favorable. See ../pm-copilot/references/framework.md.
The four attributes (1 = least favorable, 5 = most favorable)
| Attribute | What it measures | 1 (least) → 5 (most) | | :--- | :--- | :--- | | Distinctive Competencies | How much it relies on abilities we already have (valued, different, provable) | 1 = requires building a new competency → 5 = directly uses existing strong competencies | | Competitive Landscape | Size/strength of alternatives | 1 = highly competitive (rival has pricing power/brand equity) → 5 = low competition (we can freeze out the market) | | Investment Level | Resources (people, material, facilities) required | 1 = very high (ground-up build) → 5 = very low (re-use existing assets) | | Impact to Buyers/Users | Consequences for current & potential customers | 1 = negative outweighs positive → 5 = significant positive impact / high ROI for buyer |
Total = sum of the four scores (4–20). Rank opportunities by total, but read the per-attribute scores too — a low Investment + high Impact "no brainer" may beat a higher total that depends on a competency you don't have.
Method
- List the candidate opportunities (ideally ones already validated as urgent, pervasive
and willing-to-pay — see pm-market-problems).
- Score each attribute 1–5 and write the rationale (the evidence) for each score.
- Sum, rank, and discuss — especially where scores are low on Distinctive Competencies
(can we really win?) or Investment (can we afford it?).
Interview the user for inputs (batch questions)
- What are the opportunities to compare? (Name each + the market problem it solves.)
- For each: do we already have the competencies to deliver it, or must we build them?
- How competitive is the space (who else, how entrenched)?
- Rough investment — reuse existing assets, or ground-up?
- Expected impact/ROI for buyers and users (and any downside)?
Artifact template
# Opportunity Scorecard —
**Company:** · **Feature / Product:**
**Author:** · **Date created:** · **Version:** 1.0
**Scale:** 1 = Least Favorable → 5 = Most Favorable
| Opportunity | Distinctive Competencies | Competitive Landscape | Investment Level | Impact to Buyers/Users | Total | Rank |
| :--- | ---: | ---: | ---: | ---: | ---: | ---: |
| | 4 | 3 | 2 | 5 | 14 | 2 |
| | 5 | 4 | 4 | 4 | 17 | 1 |
## Rationale (evidence behind each score)
###
- **Distinctive Competencies (4):**
- **Competitive Landscape (3):**
- **Investment Level (2):**
- **Impact to Buyers/Users (5):**
## Recommendation
Deliver the artifact
Follow ../pm-copilot/references/artifact-output.md: confirm inputs, ask Markdown or .docx, write the .md, convert via your environment's native document-creation capability on request. Next stage: build the full business case for the winner with pm-product-canvas.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: julianoczkowski
- Source: julianoczkowski/product-manager
- 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.