REPO PACKAGE
anthropics claude-code
OFFICIAL10skills
10ready to use
LABSCO SUMMARY
Agent Development, Command Development, Hook Development, MCP Integration, Plugin Settings, Plugin Structure, Skill Development, and Writing Hookify Rules cover the plugin system end to end: how to write a subagent, a slash command, a hook, an MCP integration, a settings file, or a skill of your own, each keyed to the specific frontmatter fields and file layout this repository defines. Anyone building a plugin for distribution, rather than using Claude Code day to day, is the intended reader for all eight.
claude-opus-4-5-migration and frontend-design are the other two, and neither is about plugins. The migration skill updates prompts and code from Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5 model strings and known behavioral differences, and says explicitly that it does not cover Haiku 4.5. frontend-design is generic visual-design guidance for building or reshaping a UI, with no dependency on Claude Code at all -- the same skill also ships, close to word for word, in anthropics/skills.
READ THE FULL ANALYSIS
Nothing here is for someone who only uses Claude Code. If the goal is to run slash commands, hooks, or MCP servers someone else already wrote, these ten skills teach how to author those things, not how to configure or use ones that already exist -- that material lives in the product documentation, not in this repository's skills.
ALSO IN THIS PACKAGE
PLUGINS
13 itemsPLUGIN
agent-sdk-dev
Claude Agent SDK Development Plugin
PLUGIN
claude-opus-4-5-migration
Migrate your code and prompts from Sonnet 4.x and Opus 4.1 to Opus 4.5.
PLUGIN
code-review
Automated code review for pull requests using multiple specialized agents with confidence-based scoring
PLUGIN
commit-commands
Streamline your git workflow with simple commands for committing, pushing, and creating pull requests
PLUGIN
explanatory-output-style
Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)
PLUGIN
feature-dev
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
PLUGIN
frontend-design
Frontend design skill for UI/UX implementation
PLUGIN
hookify
Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns
PLUGIN
learning-output-style
Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)
PLUGIN
plugin-dev
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices.
PLUGIN
pr-review-toolkit
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
PLUGIN
ralph-wiggum
Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.
PLUGIN
security-guidance
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.
AGENT PERSONALITIES
15 itemsAGENT PERSONALITY
agent-sdk-verifier-py
Use this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a Python Agent SDK app has been created or modified.
AGENT PERSONALITY
agent-sdk-verifier-ts
Use this agent to verify that a TypeScript Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a TypeScript Agent SDK app has been created or modified.
AGENT PERSONALITY
code-architect
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences
AGENT PERSONALITY
code-explorer
Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development
AGENT PERSONALITY
code-reviewer
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter
AGENT PERSONALITY
conversation-analyzer
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks.
AGENT PERSONALITY
agent-creator
Use this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", or describes agent functionality they need. Trigger when user wants to create autonomous agents for plugins.
AGENT PERSONALITY
plugin-validator
Use this agent when the user asks to "validate my plugin", "check plugin structure", "verify plugin is correct", "validate plugin.json", "check plugin files", or mentions plugin validation. Also trigger proactively after user creates or modifies plugin components.
AGENT PERSONALITY
skill-reviewer
Use this agent when the user has created or modified a skill and needs quality review, asks to "review my skill", "check skill quality", "improve skill description", or wants to ensure skill follows best practices. Trigger proactively after skill creation.
AGENT PERSONALITY
code-reviewer
Use this agent when you need to review code for adherence to project guidelines, style guides, and best practices. This agent should be used proactively after writing or modifying code, especially before committing changes or creating pull requests.
AGENT PERSONALITY
code-simplifier
Use this agent when code has been written or modified and needs to be simplified for clarity, consistency, and maintainability while preserving all functionality. This agent should be triggered automatically after completing a coding task or writing a logical chunk of code.
AGENT PERSONALITY
comment-analyzer
Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes: (1) After generating large documentation comments or docstrings, (2) Before finalizing a pull request that adds or modifies comments, (3) When reviewing existing comments for potential technical debt or comment rot, (4) When you need to verify that comments accurately reflect the code they describe.\n\n
AGENT PERSONALITY
pr-test-analyzer
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases.
AGENT PERSONALITY
silent-failure-hunter
Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. This agent should be invoked proactively after completing a logical chunk of work that involves error handling, catch blocks, fallback logic, or any code that could potentially suppress errors.
AGENT PERSONALITY
type-design-analyzer
Use this agent when you need expert analysis of type design in your codebase. Specifically use it: (1) when introducing a new type to ensure it follows best practices for encapsulation and invariant expression, (2) during pull request creation to review all types being added, (3) when refactoring existing types to improve their design quality.
WHAT'S INSIDE
10 showing · 10 totalReady to use
Nothing else to set up — install it and go.
10 of 10
SETUP
Showing all 10 skills
Agent Development
Make your own specialist helper inside Claude Code — a code reviewer, a test writer, a security checker — that Claude can hand a whole job to and leave to get on with it.
claude-opus-4-5-migration
A one-pass upgrade to Claude Opus 4.5: every mention of an older Claude model in the code gets swapped over, and the instructions written for the old model get adjusted where the new one behaves differently.
Command Development
A slash command is a prompt you save once and re-run by typing its name, the way /review or /deploy works — this is how to write your own.
frontend-design
Makes a new page or app screen look designed on purpose — color, type and layout picked for this particular product rather than reached for out of habit.
Hook Development
Automatic checkpoints that sit between Claude and your project — one can run just before it uses a tool, another when it thinks it is finished — and each can let the action through, block it, or feed something back.
MCP Integration
Plugs an outside service — a database, GitHub, Asana — into Claude Code, and ships that connection inside a plugin so whoever installs it gets the service's tools without having to connect it themselves.
Plugin Settings
A place to keep a plugin's settings for one project — a small file in the project folder that the plugin reads each time it runs, so the same plugin can behave differently in different projects.
Plugin Structure
The folder layout a Claude Code plugin has to follow: put each piece where it belongs, add the one small file that names the plugin, and Claude Code finds everything by itself.
Skill Development
Packaging know-how that Claude does not come with — your company's rules, a process your team follows, a script you keep rewriting — so it picks that up by itself when the task calls for it.
Writing Hookify Rules
House rules that watch what Claude is about to do — you say which commands or edits you do not want, and whether it should get a warning or be stopped outright.
No skill in this package matches that.
HOW TO GET IT
WHOLE PACKAGEInstall the whole package (10 skills)
npx skills add anthropics/claude-codeSINGLE SKILLOr install a single skill
npx skills add anthropics/claude-code --skill <name> --full-depthPick the skill name from the Skills tab — each entry there installs independently.
PLUGIN MARKETPLACEAdd the marketplace, then install the plugins you want
/plugin marketplace add anthropics/claude-code/plugin install agent-sdk-dev@claude-code-plugins/plugin install claude-opus-4-5-migration@claude-code-plugins/plugin install code-review@claude-code-pluginsTyped inside the agent's own prompt, not in a terminal. The marketplace lists 13 plugins; three are shown. Every one installs the same way, with its own name before @claude-code-plugins.