call-review-kit

I found your call-review-kit while evaluating some emerging skill patterns, and I'm curious about the design choice to focus on review workflows—that's a pretty specific problem space. With a score sitting at 52, there's solid foundation here, but it looks like there are some gaps worth exploring around progressive disclosure and spec alignment that could really unlock its potential.

Links:

• GitHub
• Your agentic skill in the SkillzWave marketplace

The TL;DR

You're at 52/100, which puts you in F territory. This is based on Anthropic's progressive disclosure architecture and skill spec best practices. Your strongest area is Spec Compliance (11/15)—the frontmatter and naming conventions are solid. But Progressive Disclosure Architecture (12/30) and Utility (9/20) are dragging you down hard. The core issue: you're promising templates and workflows that don't actually exist in the skill, which tanks both discoverability and practical usefulness.

What's Working Well

• Clean YAML frontmatter – Valid structure with required fields present
• Logical framework organization – The 5-part framework (Call Selection, Agenda, Scorecard, Facilitation, Follow-up) is conceptually sound
• Good grep-friendly structure – Clear headers and sections make the content scannable, even at <100 lines
• Stays objective – No marketing fluff; purely instructional tone

The Big One: Missing Reference Files

Here's what's killing your score: You mention "Templates" and reference specific deliverables (Call review agenda, Scorecard worksheet, Follow-up email template) but none of these files actually exist. This tanks your Progressive Disclosure Architecture (supposed to be 30 points, you got 12) and your Utility score.

The fix: Create a references/ directory with actual template files:

• references/agenda-template.md – Pre-filled agenda with time blocks
• references/scorecard-template.md – Actual scorecard structure (criteria, scoring rubric)
• references/followup-email.md – Email template with placeholders

Then in SKILL.md, link to these: "See references/agenda-template.md for a pre-built template with facilitation notes." This alone gets you +8 points.

Other Things Worth Fixing

1. Add trigger phrases to the description – Currently it says "Use to facilitate structured call review sessions..." but no specific triggers. Change it to: "Structured call review and coaching sessions. Use when asked to 'call review kit', 'film session prep', 'scorecard template', or 'call coaching agenda'." That's +2 points for spec compliance.

2. Convert framework to numbered workflow steps – Right now it's a list of components. Convert it to: "1. Select call using criteria (stage, persona, outcome) 2. Prepare agenda from template 3. Distribute scorecard..." Adds clarity and gets you +3 points on Ease of Use.

3. Add validation/success metrics – You mention "success metrics" but don't define them. Add: "After session: Verify all scorecard sections completed, action items assigned with dates, follow-up email sent within 24h." That's +3 points on Utility.

Quick Wins

Most impactful first:

• Create the three reference templates (+8 points) – This is the heavyweight
• Add specific trigger phrases (+2 points) – Dead simple, huge for discoverability
• Define success validation steps (+3 points) – Turns theory into a feedback loop
• Rewrite framework as numbered steps (+3 points) – Better workflow clarity

You're looking at a potential +16 points (from 52 to 68) with these focused fixes. The architecture is there—you just need to flesh out the actual templates and tighten the language around triggers and workflow steps.

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.