launch-tiering

I took a look at your launch-tiering skill and noticed the spec could use more rigor around the edge cases—like what happens when tier thresholds overlap or when you're dealing with dynamic pricing models that shift mid-campaign.

Links:

• GitHub
• Your agentic skill in the SkillzWave marketplace

TL;DR

You're at 62/100, squarely in D territory. This is graded against Anthropic's skill best practices. Your strongest area is Spec Compliance (12/15)—the YAML frontmatter and naming conventions are solid. The weak spots are Progressive Disclosure Architecture (15/30) and Utility (10/20)—basically, you need better structure and more actionable decision logic.

What's Working Well

• Clean metadata—Frontmatter is valid YAML with all required fields; name follows hyphen-case correctly
• Consistent terminology—You use "Tier 1/2/3" and "tiering" consistently throughout, which makes the skill easier to follow
• Objective tone—No marketing fluff; stays instructional and professional without overselling

The Big One: Missing Reference Files & Templates

This is your main blocker. You mention templates for "tier scoring matrix", "tier playbook", and "approval checklist" but never actually provide them. This violates Progressive Disclosure Architecture (PDA)—the whole point is to keep SKILL.md lean while offloading details to references.

The fix: Create three new files:

• references/tier-scoring-matrix.md — Actual criteria, weights, scoring thresholds
• references/tier-playbook.md — Workstreams, artifacts, checkpoints for each tier
• references/approval-checklist.md — Gate criteria for tier changes

Then link them from SKILL.md. This alone could add +7 points and fix your biggest PDA gap.

Other Things Worth Fixing

1. No executable workflow — Your "Framework" section lists criteria but doesn't walk someone through how to actually tier a launch. Add a numbered Workflow: gather details → score against criteria → calculate total → assign tier → validate. (+3 points)

2. Vague trigger phrases — Your description says "sizing go-to-market launches" but users search for "tier this launch" or "tier 1 vs tier 2". Add specific search terms to metadata. (+2 points)

3. Zero decision examples — No sample tier assignments with scoring breakdowns. A references/examples.md with 3 real launches (one per tier) showing how criteria map to decisions would make this immediately useful. (+3 points)

4. Missing validation steps — You mention "reassess tier mid-cycle" in Tips but no actual process. Add a validation checklist with gates like "score validated by 2+ stakeholders" or "mid-cycle review scheduled for >6 week launches". (+2 points)

Quick Wins

Focus here first—these are highest impact:

1. Create reference files for templates (scoring matrix, playbook, checklist)
2. Add a numbered workflow section with actual decision steps
3. Include 2-3 worked examples showing tier assignments with scoring rationale
4. Expand trigger phrases in metadata description

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.