claude-collaboration
Best practices for using Claude Code in team environments. Covers skill management, knowledge capture, version control, and collaborative workflows.
Découvrez les skills Contenu et médias, comparez leurs dépôts et consultez leurs instructions.
Best practices for using Claude Code in team environments. Covers skill management, knowledge capture, version control, and collaborative workflows.
Best practices for organizing project folders, file naming conventions, and directory structure standards for research and development projects
Project-specific architecture, maintenance tasks, and unique conventions for UI Tweaker.
Audit devloop against Claude Code updates to identify integration opportunities. Use after Claude Code releases, monthly maintenance, or when exploring new features.
Use ai-rules CLI to manage and synchronize AI coding rules across multiple AI assistants (Cursor, Claude Code, GitHub Copilot, Opencode, etc.). Use when: (1) Setting up ai-rules in a new project, (2) Updating A...
Use CodeRabbit CLI to perform automated code review and iterative improvement in an AI agent workflow. Use when: (1) After generating non-trivial code (new features, refactors, algorithms), (2) Improving code q...
Use when wanting AI-powered improvements for your spec. Triggers on "suggest improvements", "improve my spec", "speakeasy suggest", "better operation names", "suggest error types", "AI suggestions"
Use when SDK methods have ugly auto-generated names. Triggers on "ugly method names", "GetApiV1Users", "improve operation IDs", "sdk.users.list() style", "better SDK naming", "x-speakeasy-group"
Second command does something useful for testing wrap lines in codex skills.
Second command does something useful for testing wrap lines in codex skills.
Use when you have lint errors but can't modify the source spec. Triggers on "fix with overlay", "can't edit spec", "add missing descriptions", "fix validation errors", "overlay fix"
Use when checking if an OpenAPI spec is valid or has errors. Triggers on "validate spec", "lint spec", "check OpenAPI", "spec errors", "is my spec valid", "run speakeasy lint"
Git workflow commands: commit, branch, pr, push, sync, review, fixup, update-pr, commit-push, clean-gone. Use with command argument.
Zero-downtime deployment with Kamal for kw-app (staging on Raspberry Pi ARM64, production on VPS x86_64). Covers deployment workflows, console access, and troubleshooting.
Git workflow commands: commit, branch, pr, push, sync, review, fixup, update-pr, commit-push, clean-gone. Use with command argument.
Complete development workflow for Claude Code. Defines philosophy, task classification, hard requirements, anti-patterns, and 8-phase development process.
Complete development workflow for Codex. Defines philosophy, task classification, hard requirements, anti-patterns, and 8-phase development process with spawn_agent.
当创建新技能、编辑现有技能或在部署前验证技能工作时使用
当准备声称工作已完成、修复或通过时使用,在提交或创建 PR 之前——要求运行验证命令并确认输出,然后再做出任何成功声明;证据永远先于主张
Use when SDK generation failed or seeing errors. Triggers on "generation failed", "speakeasy run failed", "SDK build error", "workflow failed", "Step Failed", "why did generation fail"
Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, or integrating with MCP servers. Triggers on...
Git and GitHub CLI mastery for version control operations. Use proactively for commits, branches, PRs, rebases, conflict resolution, and git history management. Covers conventional commits, branching strategies...
Skill for handling PR code reviews. Use when triggered by a PR review comment, review request, or when asked to review code changes. Provides workflow for reading review comments, understanding feedback, and it...
Skill for GitHub Actions CI environment. Use when running inside a GitHub Actions workflow to update tracking comments, commit code, and interact with GitHub.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.