Agent Skills Hub

plugin-best-practices

Validates Claude Code plugins against architectural standards, checking manifest files, frontmatter, and tool invocation patterns to ensure high-quality, compliant plugin development.

shift-left-testing

Accelerate software delivery by shifting testing to the earliest development phases, using AI-driven requirements validation, TDD, and automated CI pipelines to reduce defect costs.

git-advanced

Advanced Git workflow automation including rebase strategies, bisect debugging, cherry-picking, and conflict resolution with safety guardrails.

with-context-agent

Lints, validates, and auto-fixes AI agent configuration files like SKILL.md, CLAUDE.md, and MCP configs.

acceptance-testing

Plan, implement, and execute user acceptance tests (UAT) and end-to-end scenarios to validate requirements against user-visible behavior.

performance-security

Optimize React performance, implement security hardening, and ensure WCAG accessibility compliance with automated patterns and checklists.

novelty-check

Verify research idea novelty against recent literature. Use when user says '查新', 'novelty check', or needs to confirm if a method is original.

verification-before-completion

Enforces a strict evidence-before-assertion protocol for coding agents, requiring fresh command-line verification output before any claim of completion, success, or bug fixes.

dinero-best-practices

Enforce best practices for Dinero.js. Use when handling monetary values, performing arithmetic, or refactoring code to ensure safe, type-safe, and accurate currency calculations in JS/TS applications.

looped-builder

Scaffold complex, multi-step coding tasks into actionable implementation plans and execute them autonomously using a Claude-driven bash loop.

svelte-code-writer

CLI tools for Svelte 5 documentation lookup and code analysis. Automate Svelte component creation, debugging, and linting with real-time documentation retrieval and code autofixing.

vitest

Vitest testing patterns for reliable unit and integration tests. Focuses on critical business logic, edge cases, and mocking strategies for high-impact functions.