with one click
agent-skills-guide
// Guide for creating, managing, and using Claude Code Agent Skills. Use when the user asks about Skills, wants to create a new Skill, or needs help with SKILL.md files.
// Guide for creating, managing, and using Claude Code Agent Skills. Use when the user asks about Skills, wants to create a new Skill, or needs help with SKILL.md files.
Generates distinctive, high-quality frontend designs avoiding generic AI aesthetics. Use when building landing pages, UI components, dashboards, web apps, or any frontend/web design task.
Create OpenAI Agents SDK applications in TypeScript/JavaScript. Use when building AI agents, multi-agent systems, voice agents, or any agentic workflow with the OpenAI Agents SDK. Covers agents, tools, handoffs, guardrails, streaming, MCP, and realtime voice agents.
| name | agent-skills-guide |
| description | Guide for creating, managing, and using Claude Code Agent Skills. Use when the user asks about Skills, wants to create a new Skill, or needs help with SKILL.md files. |
Agent Skills package expertise into discoverable capabilities for Claude Code. Each Skill consists of:
SKILL.md file with instructions (required)Key distinction: Skills are model-invoked (Claude autonomously decides when to use them based on task context), unlike slash commands which are user-invoked.
~/.claude/skills/<skill-name>/SKILL.md.claude/skills/<skill-name>/SKILL.md---
name: your-skill-name
description: Brief description of what this Skill does and when to use it
allowed-tools: Read, Grep, Glob # Optional: restrict available tools
---
# Your Skill Name
## Instructions
Step-by-step guidance for Claude.
## Examples
Concrete examples of using this Skill.
name: Lowercase letters, numbers, hyphens only (max 64 chars)description: What the Skill does AND when to use it (max 1024 chars)allowed-tools: Optional comma-separated list of permitted toolsThe description is critical for Claude to discover when to use your Skill.
Bad (too vague):
description: Helps with documents
Good (specific):
description: Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.
One Skill = one capability. Split broad concepts into separate Skills.
Good: "PDF form filling", "Excel data analysis", "Git commit messages" Bad: "Document processing" (too broad)
my-skill/
āāā SKILL.md (required)
āāā reference.md (optional documentation)
āāā examples.md (optional examples)
āāā scripts/
ā āāā helper.py (optional utility)
āāā templates/
āāā template.txt (optional template)
Reference files from SKILL.md - Claude loads them only when needed (progressive disclosure).
Test by asking questions that match your description:
# If description mentions "PDF files":
Can you help me extract text from this PDF?
Claude automatically activates Skills based on task context.
claude --debug to see loading errors--- in frontmattermkdir -p .claude/skills/team-skill
# Create SKILL.md
git add .claude/skills/
git commit -m "Add team Skill"
git push
Create a plugin with Skills in the skills/ directory and distribute through marketplaces.
---
name: commit-helper
description: Generates clear commit messages from git diffs. Use when writing commit messages or reviewing staged changes.
---
# Commit Message Generator
## Instructions
1. Run `git diff --staged` to see changes
2. Suggest commit message with:
- Summary under 50 characters
- Detailed description
- Affected components
## Best Practices
- Use present tense
- Explain what and why, not how
---
name: code-reviewer
description: Review code for best practices and potential issues. Use when reviewing code, checking PRs, or analyzing code quality.
allowed-tools: Read, Grep, Glob
---
# Code Reviewer
## Review Checklist
1. Code organization and structure
2. Error handling
3. Performance considerations
4. Security concerns
5. Test coverage
For improved UI generation, use targeted prompting across:
View available Skills:
What Skills are available?
List Skills manually:
ls ~/.claude/skills/
ls .claude/skills/