product-strategist

I've been digging through the grading framework and noticed the product-strategist skill is pulling a 60—curious what's weighing it down, since the core idea of a structured product thinking guide feels solid but maybe the execution or scope is where things got stretched thin.

Links:

• GitHub
• Your agentic skill in the SkillzWave marketplace

The TL;DR

You're at 60/100, which lands you in D territory. This is based on Anthropic's best practices for skill architecture. Your strongest area is Spec Compliance (12/15)—the YAML frontmatter and naming conventions are solid. The biggest drag is Progressive Disclosure Architecture (12/30), where you're only getting 40% of available points because everything's flattened into one SKILL.md instead of being layered out.

What's Working Well

• Spec compliance is dialed in — Your frontmatter is valid, naming follows conventions, and core metadata is correct
• Real problem being solved — OKR cascade automation fills an actual gap in product workflow automation
• Decent trigger phrases — You've got "OKR", "market analysis", "strategy" which help discoverability
• Alignment scoring adds value — The feedback mechanism for team alignment (>80% target) gives structure to the output

The Big One: Flat Architecture

Here's the core issue: you've got a 479-line script (okr_cascade_generator.py) that's basically doing all the heavy lifting, but it's being treated as a reference document instead of an execution tool. This violates the Progressive Disclosure principle—you're making users wade through implementation details when they should be seeing methodology first.

The fix: Create a references/ folder structure:

• references/okr_framework.md — Explains why and how cascading works
• references/okr_templates.json — Extracted from the script, cleaner
• references/strategy_types.md — Breakdown of Growth vs. Retention vs. Revenue strategies
• references/examples/ — Sample input/output pairs showing what a complete cascade looks like

Then strip the script down to pure execution—templates and methodology move to references. Your SKILL.md becomes a navigation hub instead of a dumping ground.

Impact: This alone gets you +8 points on PDA.

Other Things Worth Fixing

1. No workflow steps — You list capabilities but no step-by-step "here's how to run a strategic planning session". Add a ## Workflow section with 5 numbered steps from "define focus" to "export to tracking system" (+5 points on Ease of Use)

2. Hardcoded assumptions everywhere — Teams are locked to ['Growth', 'Platform', 'Mobile', 'Data'] and the 30% contribution is hardcoded (line 159). Make these CLI args or config-driven so users can customize for their org structure (+4 points on Utility)

3. Marketing language in templates — Phrases like "world-class", "best-in-class", "pioneering" read like sales copy. Replace with measurable terms: "Improve product delivery efficiency" instead of "Build world-class org" (+2 points on Writing Style)

4. Missing concrete examples — No input/output samples showing what OKR output looks like for different strategy types. Add references/examples/sample_growth_okrs.json (+3 points on Utility)

Quick Wins

• Extract script content to references/ folder (biggest bang: +8 points)
• Add numbered workflow steps to SKILL.md (+5)
• Make teams and contribution percentages configurable (+4)
• Replace marketing language with measurable objectives (+2)
• Add sample output examples (+3)

Hitting these five items gets you to 82+/100 without rearchitecting the whole thing.

Checkout your skill here: SkillzWave.ai | SpillWave We have an agentic skill installer that install skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.