Skills

Extracts and analyzes competitors' ads from ad libraries like Facebook and LinkedIn, identifying successful messaging, problems highlighted, use cases targeted, and creative approaches that resonate.

Reviews contracts by identifying 15+ common risk patterns (unlimited liability, broad IP assignment, unilateral termination, etc.), checking completeness, explaining complex legal language in plain terms, and providing jurisdiction-specific recommendations for US, EU, China, and UK.

Thin HIPAA entrypoint that overlays BAA, PHI, covered-entity, minimum-necessary, and audit-trail decision gates on top of `healthcare-phi-compliance` (implementation) and `healthcare-reviewer` (review). Blocks PHI from logs/analytics/crash reports/LLM prompts/URLs and treats third-party SaaS, observability, support tooling, and LLM providers as blocked-by-default until BAA status and data boundaries are proven.

Helps create effective AI image generation prompts for DALL-E 3, Midjourney, and Stable Diffusion with platform-specific optimization, style keywords, negative prompting, aspect ratio guidance, and a structured prompt engineering framework.

A collection of 11 open-source plugins that turn Claude into a role-specific specialist for functions like sales, data analysis, marketing, legal, finance, and customer support, each bundling skills, connectors, and slash commands for use with Claude Cowork and Claude Code.

Procedural guide for configuring and managing GitHub secret scanning — enabling Secret Protection, turning on push protection for command line/UI/REST pushes, defining custom patterns, triaging user/partner/push-protection alerts, configuring delegated bypass, and writing `secret_scanning.yml` path exclusions. Also references pre-commit scanning via the `advanced-security@copilot-plugins` MCP plugin.

from lijigang/ljg-skills

Evidence-first terminal-execution workflow for running commands, inspecting git state, debugging CI, making a narrow fix, and reporting exactly what changed and what was proved. Uses strict status words (`inspected` / `changed locally` / `verified locally` / `committed` / `pushed` / `blocked`), refuses to widen a narrow fix into repo-wide churn, and never claims "pushed" unless the branch actually moved upstream.

Part of a skills collection for improving daily work efficiency with AI agents, including content generation tools like Xiaohongshu image card generators, AI image/video generation backends, and various utility skills installable via the skills CLI or plugin marketplace.

Generate [CodeTour](https://github.com/microsoft/codetour) `.tour` JSON files (saved to `.tours/<persona>-<focus>.tour`) for onboarding, architecture, PR, RCA, and security-review walkthroughs with real file/line anchors that open directly in the CodeTour VS Code extension. Picks persona and step count from the request shape (new-joiner, vibecoder, architect, pr-reviewer, etc.), verifies every anchor exists, and writes steps in a Situation/Mechanism/Implication/Gotcha format.

from upstash/context7

Identifies and resolves common obstacles in software fuzzing campaigns, improving coverage and vulnerability detection with advanced strategies

A skill from the Awesome GitHub Copilot community collection that helps configure and manage Dependabot for automated dependency updates and security vulnerability alerts in GitHub repositories.

Official Brave Search API skills for AI coding agents supporting 8 specialized focus modes (general, coding, news, academic, shopping, social, geo, location) with AI-powered answers and custom ranking via Goggles.

Helps product teams discover customer motivations by understanding the specific "job" customers want products to accomplish across functional, emotional, and social dimensions.

Replaces port numbers with stable, named .localhost URLs for local development, eliminating port conflicts, cookie clashes, and hardcoded port issues in monorepos. Works as a lightweight reverse proxy that both humans and AI agents can rely on.

Refactors and improves Terraform modules by analyzing code structure and suggesting modular, reusable code improvements

Inventory every live automation — local hooks, GitHub Actions, MCP configs, connector/app integrations, wrapper scripts — and classify each as configured / authenticated / recently verified / stale / missing, plus problem type (active breakage, auth outage, stale status, overlap, missing capability). Returns a keep / merge / cut / fix-next recommendation set with proof paths (file, workflow run, hook log) instead of repo rewrites.

Extracts structured web data using Python tools like BeautifulSoup, Selenium, and Scrapy, with robust error handling and ethical scraping practices.

Generates fuzzing test harnesses for security testing, from the Trail of Bits Skills Marketplace for AI-assisted security analysis and development workflows.

A Claude Code plugin marketplace from Trail of Bits providing skills for AI-assisted security analysis, testing, and development workflows.

A collection of 65 Claude Code skills and 9 workflows with progressive disclosure, covering full-stack development including context engineering and Atlassian integration.

Skill for designing, implementing, and auditing WCAG 2.2 Level AA accessibility on Web, iOS, and Android — mapping component roles, 4.5:1/3:1 contrast, 24×24 CSS pixel targets, focus appearance (SC 2.4.11), ARIA/accessibility traits, and assistive-tech compatibility.

Angular skills for building signal-based forms with Angular v21+'s Signal Forms API, including schema-based validation, two-way binding, and dynamic form patterns.

Guides iOS app design by evaluating and optimizing interfaces against Apple's Human Interface Guidelines, ensuring native, intuitive, and platform-consistent user experiences.

A comprehensive skill for automating Amazon seller operations and FBA management, covering listing optimization, order fulfillment, PPC advertising campaigns, pricing automation, inventory alerts, and sales analytics through integration with Amazon SP API and Ads API.

Scans Cosmos blockchain smart contracts for security vulnerabilities using static analysis and security best practice checks

Turn a PRD, roadmap item, or founder note into an implementation-ready capability plan (ECC's PRD→SRS lane) that makes constraints, invariants, interfaces, and unresolved decisions explicit before multi-service work begins. Writes into a durable `PRODUCT.md` / `docs/product/` artifact and ends with a handoff label — ready for implementation, architecture review, or product clarification — plus the next ECC lane to take it.

An indexion-powered skill for README construction including initialization, generation, planning, and assembly, part of a Claude Code plugin suite providing source code exploration, similarity analysis, and documentation tools.

Helps write professional investment memorandums for venture capital, private equity, hedge fund, or internal investment committee contexts, covering investment thesis structuring, due diligence synthesis, risk analysis, valuation, and actionable recommendations.