Autonomous skill creator for Claude Code CLI. Uses multi-phase orchestrated workflow with Task tool subagents to research domains, design architecture, generate content, and validate quality. Creates production-ready skills following Anthropic's Agent Skills specification.
SkillScore91Maintained
Automatic
◆AI Engineer pack
Last verified 9/3/2026
What it changes
Passed 19 of 21 test cases with the skill, and 11 of 21 without it.
Without skill50%
With skill91%
Checks it passed that the model alone missed
The skill is classified as an Automation type.
The metadata section is limited to approximately 100 tokens.
Template files are sourced from the references/templates/ directory.
and 7 more in the full report
9 fixed11 passed either way2 still failing0 broke
Pass-rate lift
+41 pp
Tokens
+17%
Agent turns
0%
Response time
-20%
Model gemini-3.6-flashMeasured 9/3/2026v120 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 9
Prompt
During Phase 2 domain discovery, where does the process search for existing local skill patterns to model architectural conventions?
What was checked, without and with the skill
Checked
Without skill
With skill
Local skill pattern discovery scans the ~/.claude/skills/ directory.
Missed
Passed
case-17 · gemini-3.6-flash · 9/3/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md134 linessingle file
Platxa Skill Generator
Create Claude Code skills autonomously using a multi-phase orchestrated workflow.
Overview
This skill guides you through creating production-ready Claude Code skills by:
Discovering domain knowledge through web research and existing skill analysis
Architecting the skill structure based on type (Builder/Guide/Automation/Analyzer/Validator)
Generating SKILL.md content, scripts, and reference documentation
Validating against Anthropic's Agent Skills spec with quality scoring
The workflow uses Task tool subagents for each phase, ensuring deep expertise at every step.
Workflow
Phase 1: Initialize
User: /skill-generator
Ask the user for:
Skill description (what should the skill do?)
Target users (who will use this skill?)
Phase 2: Discovery (Automatic)
Use Task tool with subagent_type="Explore" to:
Search web for domain best practices
Fetch relevant documentation
Analyze existing skills in ~/.claude/skills/ for patterns
Identify procedural knowledge (HOW) vs domain expertise (WHAT)
Determine what varies by project vs what's constant
Sufficiency Check: Evaluate if research is complete. Only ask user for clarification if gaps exist.
Portfolio allocation and rebalancing optimizer. Manages asset allocation across stocks/cash/bonds, performs periodic rebalancing, and ensures diversification according to market regime and risk tolerance.