pr-review-loop
Monitor PR for code review, analyze feedback with AI, implement fixes, and merge when approved with CI green.
发现 商业与营销 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Monitor PR for code review, analyze feedback with AI, implement fixes, and merge when approved with CI green.
Generate comprehensive E2E test plans from PRDs, task lists, or descriptions with environment-aware prerequisites and issue tracking.
Generate high-level tasks and gated sub-tasks from a PRD, with agent assignments, commit/PR strategy, and relevant files.
Generate operational runbooks documenting what needs to be running locally and in production for effective system testing and deployment.
Process tasks using async background subagents for massive parallelization and speedup.
Create and update CHANGELOG.md with entries that include AI model/CLI attribution, PRD context, and task references.
Map user flows and journeys through your application for UX design and workflow visualization, independent of testing.
Orchestrate adversarial player-coach loop for high-quality code synthesis. Based on dialectical autocoding methodology.
Applying consistent visual design to HTML tools in this repository. Use when creating new tools, updating UI components, or adding buttons/icons/controls. Based on Vercel Geist design system with Claude app inf...
Analyze and improve the AI agent workforce system, ensuring compatibility across environments (CLI, IDE, GitHub) and leveraging emerging technologies.
Manage the workspace roadmap by adding tasks, updating status, and maintaining the project backlog.
Standardized procedure to generate developer API documentation for C++ libraries and Python modules.
Scan overlay repositories for GitHub issues and triage them into the workspace roadmap.
Standardized procedure to document ROS 2 packages using the UNH Marine Autonomy format.
Create distinctive, mobile-first Next.js interfaces with high design quality. Use when building pages, components, or layouts. Generates polished code that avoids generic AI aesthetics.
CLI toolkit for infrastructure, development, and system administration. Use when Claude needs to execute git operations or GitHub CLI commands, provision AWS/GCP/Azure/DigitalOcean infrastructure, build or debu...
Create git commits with Conventional Commits format. Analyzes changes to write meaningful messages. Use when committing changes, committing staged files, creating commits, making commits, or writing git commit...
Communicate with the STAR orchestrator agent. Use this to report progress, send results, or request input when working on delegated tasks.
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design,...
Session continuity for Claude Code. Gather context at start, archive state at end. Use when user mentions handoff, saving progress, or resuming work.
Write effective CLAUDE.md files that serve as persistent memory for Claude Code. Use when creating, reviewing, or improving project instructions for AI assistance. Triggers: CLAUDE.md, project instructions, mem...
Write effective Claude Code hooks for automation, validation, and workflow control. Use when creating hooks, configuring PreToolUse/PostToolUse events, or automating Claude behavior. Triggers: hooks, PreToolUse...
Implement Zettelkasten-inspired knowledge management for building and maintaining context libraries with automated cross-referencing. Use when organizing executive knowledge, building context libraries, or impl...
Use PROACTIVELY when creating .cdc files, writing Cadence contracts/scripts/transactions, configuring flow.json, or using Flow CLI for local development and deployments. Covers Cadence 1.0 syntax with modern ac...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。