skill▌

$22

A skill for creating new skills and iteratively improving them.

Create and automatically share new Claude skills with your team via Slack. \n \n Generates properly structured skill directories with standardized SKILL.md templates, metadata, and organized subdirectories (scripts/, references/, assets/) \n Validates skill format, naming conventions, and metadata completeness before packaging \n Creates distributable zip files and automatically posts skill summaries to designated Slack channels using Rube integration \n Enforces hyphen-case naming and YAML fron

template-skill

This skill provides guidance for creating effective skills.

Custom Playwright scripts for any browser automation task, with auto-detected dev servers and visible browser execution. \n \n Auto-detects running localhost servers; writes all test scripts to /tmp to avoid project clutter \n Supports responsive design testing, login flows, form filling, link validation, screenshots, and arbitrary browser interactions \n Includes helper utilities for safe element interactions, cookie handling, table data extraction, and custom HTTP headers \n Executes via run.j

freee accounting, HR, invoicing, project management, and sales API access through MCP with detailed references and operation guides. \n \n Provides MCP tools for OAuth authentication, company management, and five service APIs: accounting (deals, expenses), HR (employees, attendance), invoicing (invoices, quotes), project management (projects, timesheets), and sales (opportunities, orders) \n Includes API reference documentation for major endpoints (deals, expense applications, employees, attenda

$21

Comprehensive guide for building modular skills that extend agent capabilities with specialized knowledge and workflows. \n \n Skills are self-contained packages providing specialized workflows, tool integrations, domain expertise, and bundled resources for agents \n SKILL.md must stay under 200 lines; use progressive disclosure by splitting detailed content into references/ files to reduce context load and activation time \n Structure includes required YAML frontmatter (name, description) and m

Security-first vetting workflow for evaluating ClawHub skills before installation. \n \n Mandatory code review scanning for exfiltration, secrets access, eval/exec, and obfuscation across all files \n Six-step vetting process covering source reputation, permission scope, recent activity, community feedback, and safe installation practices \n Produces structured SKILL VETTING REPORT with go/no-go recommendation, confidence scoring, and explicit red flag callouts \n Includes reference checklist wi