By taisukeoe
Skills for creating, reviewing, and improving effective AI agent skills following Claude's official best practices
Creating high-quality agent skills following Claude's official best practices. Use when designing, implementing, or improving agent skills, including naming conventions, progressive disclosure patterns, description writing, and appropriate freedom levels. Helps ensure skills are concise, well-structured, and optimized for context efficiency.
Evaluate skills by executing them across sonnet, opus, and haiku models using sub-agents. Use when testing if a skill works correctly, comparing model performance, or finding the cheapest compatible model. Returns numeric scores (0-100) to differentiate model capabilities.
Improve existing agent skills based on user feedback and best practices. Use when the user wants to fix, enhance, or refactor an existing skill. Gathers user feedback first, then applies technical analysis and implements improvements.
Review skill files for best practices compliance (naming, description, structure, size). Use when checking SKILL.md quality or getting feedback before publishing. Static analysis only - does NOT execute the skill.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin marketplace providing skills for creating and reviewing effective AI agent skills following Claude's official best practices.
This project must NOT contain any confidential information from specific companies or projects.
All examples, documentation, and code samples in this repository use generic, fictional names and scenarios. Any resemblance to actual company names, project names, or proprietary information is unintentional and should be reported immediately.
Skills for AI agent skill development.
| Skill | Description |
|---|---|
creating-effective-skills | Guide for creating skills with 9-step workflow |
evaluating-skills-with-models | Evaluate skills across sonnet, opus, haiku models |
improving-skills | Improve existing skills based on user feedback |
reviewing-skills | Review skills against best practices with compliance checks |
Skills for marketplace configuration.
| Skill | Description |
|---|---|
reviewing-plugin-marketplace | Review marketplace configurations, detect common errors |
setting-up-devcontainers | Generate devcontainer configurations for marketplaces |
Experimental skills for skill development.
| Skill | Description |
|---|---|
running-skills-edd-cycle | Guide EDD (evaluation-driven development) process |
Works with Claude Code, Cursor, Cline, GitHub Copilot, and other AI agents.
# Install all skills
npx skills add taisukeoe/agentic-ai-skills-creator
# Install specific skill only
npx skills add taisukeoe/agentic-ai-skills-creator --skill creating-effective-skills
/plugin marketplace add taisukeoe/agentic-ai-skills-creator
/plugin install skills-helper@agentic-skills-creator
/plugin install marketplace-helper@agentic-skills-creator
/plugin install skills-helper-experimental@agentic-skills-creator # Optional
/plugin marketplace add /path/to/agentic-ai-skills-creator
/plugin install skills-helper@local
/plugin install marketplace-helper@local
After installation, restart Claude Code to activate the skills.
Create a skill for processing PDF files
Claude will guide you through the 9-step workflow to create a properly structured skill.
Review the skill at .claude/skills/my-skill/
Claude will analyze the skill and provide feedback with priorities.
processing-pdfs)Copyright 2025 Softgraphy GK
Licensed under the Apache License, Version 2.0. See LICENSE for details.
See CONTRIBUTING.md for development setup and guidelines.
npx claudepluginhub taisukeoe/agentic-ai-skills-creator --plugin skills-helperSkills for reviewing and validating Claude Code plugin marketplace configurations
taisukeoeExperimental skills for AI agent skill development, including testing and iteration workflows
Open collection of AI agent skills — reusable, framework-agnostic SKILL.md packages
crystianUltimate Claude Code skill creator. Design, scaffold, build, review, evolve, and publish production-grade AI agent skills following the Agent Skills open standard and 3-layer architecture.
AgriciDanielCreate and validate production-grade agent skills with 100-point marketplace grading
jeremylongshoreProfessional skill and subagent creation with dual-mode workflow: 12-step fast mode and 15-step full mode with behavioral pressure testing and TDD integration.
rfxlamiaCollection of agent skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling
j5ik2oshareAI Lab's skills for AI agents - knowledge packages that extend agent capabilities
shareAI-lab