slash-command-factory

I've been digging into how skills handle CLI argument parsing, and I'm curious how you're thinking about the command pattern here—the factory approach seems like it's trying to solve the "too many conditional branches" problem, but I wonder if you've hit any rough edges with skill registration or command composition at scale.

Links:

• GitHub
• Your agentic skill in the SkillzWave marketplace

The TL;DR

You're at 72/100, solid C-grade territory. This is based on Anthropic's grading rubric for agentic skills. Your strongest area is Ease of Use (20/25)—the metadata and trigger terms are really well thought out. The real drag is Progressive Disclosure Architecture (18/30)—you've got a 1007-line SKILL.md that's trying to do way too much in one place.

What's Working Well

• Excellent metadata design — Your description with multiple trigger terms ("slash commands", "custom commands", "presets") makes discoverability solid. The skill name and structure are clean.
• 10 useful presets — The preset command patterns (error_handler, logger, formatter, etc.) solve real problems and show you've thought about common use cases.
• Good workflow clarity — The 5-7 question flow and the dual paths (official patterns + custom generation) give users real flexibility without overwhelming them.

The Big One: Token Economy is Killing Your Score

Your SKILL.md at 1007 lines violates Progressive Disclosure Architecture principles. You're repeating full preset details 3+ times, showing verbose naming convention algorithms, and packing everything into one file when you should be layering it.

Here's what needs to happen:

• Cut SKILL.md down to 200-300 lines: frontmatter + overview + the 3 main command patterns + a summary of the question flow
• Move full preset details (lines 501-740) to references/presets.json or a separate PRESETS.md
• Move the naming algorithm to HOW_TO_USE.md (which you already have—leverage it!)
• Add a Table of Contents at the top so people don't have to scroll through 1007 lines sequentially

Impact: This alone gets you +5 points in PDA (token economy +3, layered structure +2).

Other Things Worth Fixing

1. Add trigger phrases to the description — The frontmatter description is missing explicit triggers. Change it to include "Use when asked to 'slash command factory', 'run slash command factory'". Gets you +2 points in Spec Compliance.

2. Standardize terminology — You're using "slash command", "command", "preset command" and "allowed-tools" vs "tool selection" all over the place. Pick one term per concept and stick with it. A glossary in references would help here (+1 point, Ease of Use).

3. Strip the marketing language — Phrases like "powerful commands", "Complete ecosystem!", and the ⚡ emoji feel out of place. Be objective and instructional instead. Remove "Build powerful custom slash commands in minutes!" and replace with factual descriptions (+1 point, Writing Style).

4. Show clearer feedback loops — You mention validation but don't have a clear "generate → validate → test → fix" loop. Add a troubleshooting section that walks through common issues (e.g., "command doesn't register → check allowed-tools"). Small fix, +1 point.

Quick Wins

• Most impactful: Refactor to layered structure (SKILL.md 200-300 lines, move presets to references). +5 points.
• Second: Add trigger phrases, fix terminology, remove marketing language. +4 points together.
• Third: Add TOC and clarify feedback loops. +3 points.

That gets you to 84/100 territory with minimal rework—mainly reorganizing what you've already built rather than starting over.

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.