By psylch
Skill development toolkit for AI coding agents: create, review, and publish skills with runtime UX best practices
Create new agent skills with best-practice templates. Guides through skill level selection (L0 pure prompt, L0+ with helper scripts, L1 with business scripts), environment strategy (stdlib/uv/venv), and generates ready-to-edit project files following runtime UX best practices. This skill should be used when creating a new skill, scaffolding a skill project, initializing skill templates, or when the user says 'help me build a skill', 'create a skill', '创建技能', '新建 skill'.
Package a agent skill into a complete GitHub repository ready for distribution via skills.sh. Generates README, LICENSE, plugin.json, marketplace.json, .gitignore, and the proper directory structure. Optionally initializes a git repo and creates a GitHub repository. This skill should be used when publishing a skill, packaging a skill for distribution, preparing a skill repo, or when the user says 'publish skill', 'package skill', 'release skill', '发布技能', '打包 skill'.
Review an agent skill by combining automated linting with structured semantic analysis. Runs hard-rule validation, evaluates contextual findings, then performs deep review against best practices (description quality, workflow design, runtime robustness, script conventions, UX patterns). Produces actionable improvement suggestions with before/after examples. This skill should be used when reviewing a skill, validating skill structure, improving skill quality, checking skill conventions, or when the user says 'review skill', 'validate skill', 'check skill', 'improve skill', 'iterate on skill', '走查技能', '验证技能', '检查 skill', '改进技能', '优化 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 skill development toolkit for AI coding agents — create, review, and publish skills with runtime UX best practices baked in.
| Skill | Purpose | Status |
|---|---|---|
| better-skill-creator | Create new skills from best-practice templates | Available |
| better-skill-review | Validate structure, suggest improvements, and apply fixes | Available |
| better-skill-publish | Package and publish skills for distribution | Available |
npx skills add psylch/better-skills -g -y
git clone https://github.com/psylch/better-skills.git ~/.claude/skills/better-skills
Restart your agent after installation.
Guides you through creating a new skill with a requirements-first workflow — understands what your skill does before making structural decisions, then auto-recommends a level (L0/L0+/L1) and environment strategy (stdlib/uv/venv). Generates ready-to-edit templates with preflight framework, JSON output conventions, and error handling baked in. Includes built-in post-scaffold validation to catch structural issues immediately.
Incorporates design principles from Vercel's skill-creator — requirements gathering before structural choices, context budget awareness, and degrees of freedom matching — combined with our deeper runtime conventions (preflight, JSON output contracts, environment strategies, setup flow integrity).
Reviews a skill by combining automated validation (22+ checks across 7 categories, graded A–F) with analytical improvement suggestions based on best practices. Presents a unified report with the grade, issues, and prioritized suggestions with before/after examples. Can interactively apply fixes.
Packages a skill into a complete GitHub repository: generates README (EN + ZH), LICENSE, plugin.json, marketplace.json, .gitignore, and the proper directory structure. Optionally initializes git and creates a GitHub repo.
L0 — SKILL.md is the entire skill. Best for workflow guides and domain knowledge.
L0+ — SKILL.md plus lightweight helper scripts for environment detection and status caching.
L1 — Scripts handle core business logic. SKILL.md orchestrates. Scripts follow MCP tool design principles.
better-skills/
├── .claude-plugin/
│ ├── plugin.json
│ └── marketplace.json
├── skills/
│ ├── references/ # Shared knowledge base (symlinked into each skill)
│ ├── better-skill-creator/ # L1: scaffold.py + templates
│ ├── better-skill-review/ # L1: validate.py + analyze.sh
│ └── better-skill-publish/ # L1: publish.py + templates
├── README.md
├── README.zh.md
└── LICENSE
MIT
npx claudepluginhub psylch/better-skills --plugin better-skillsConfigures a complete Ghostty-based terminal AI coding environment with Fish, yazi, lazygit, Neovim (LazyVim), fzf, zoxide, atuin on macOS with Apple Silicon — with CJK font optimization for Chinese/Japanese/Korean users
Search, validate, and save cloud drive resources via PanSou aggregation API and local Quark desktop APP integration
All-in-one media acquisition toolkit: Hi-Res music downloads, cloud drive resource search, and book downloads
Initialize a project-level context management system with docs/ directory structure, Claude Code hooks (session-start, quality-gate), and CLAUDE.md navigation. Use when starting a new project, bootstrapping context management, or when the user says '/ch-project-context init', 'init project context', 'setup context management', 'initialize docs structure'.
Multi-source tech research — dispatches parallel agents to Grok (X/Twitter), DeepWiki (GitHub repos), and WebSearch, then synthesizes findings into a unified report
Professional skill creation with TDD workflow. Features dual-mode (fast/full), behavioral validation, and automated quality gates for 9.0/10+ scores.
Ultimate 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.
建立新技能、修改和改進現有技能、衡量技能效能。用於從零開始建立技能、編輯或優化現有技能、執行評估測試、基準測試效能分析、或優化技能描述以提升觸發準確度
Open collection of AI agent skills — reusable, framework-agnostic SKILL.md packages
Agent Skills for improving SKILL.md files: mine repeated workflows from history, personalize and audit existing skills, or generalize personal skills for publication.
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.