按技能名称、说明或 GitHub 作者匹配的结果。
Creating high-quality agent skills following Claude's official best practices. Use when designing, implementing, or improving agent skills, including naming conventions, progressive disclosure patterns, descrip...
Review Claude Code plugin marketplace configurations against official best practices. Use when analyzing marketplace.json and plugin.json files for structural issues, common errors, path validation, and consist...
Generate devcontainer configurations for Claude Code development environments. Use when setting up development containers with Claude Code and optional Codex CLI. Automatically detects marketplace.json for plug...
Guides evaluation-driven development (EDD) process for agent skills. Use when setting up skill testing workflows, creating skill evaluation scenarios, or establishing Claude A/B feedback loops for skill validat...
Verifies that Claude Code can detect and load Skills. Use this to test skill discovery.
Meta-skill for managing Claude Code Skills for the Ascend platform documentation.
Claude Code hook creation and configuration. PAI event-driven automation. USE WHEN: "create hook", "hook system", "modify hooks", "add hook"
Review and optimize PAI (Personal AI Infrastructure) codebases as Claude Code evolves. Use when analyzing PAI repositories against 12-factor agent principles, checking for Claude Code feature compatibility, aud...
CWF knowledge repository providing plan structure, tasklist format, checkpoint definitions, amendment rules, and validation requirements. Load this skill when: (1) executing CWF commands like /write-plan, /impl...
Create and manage ClickUp tickets directly from Claude Code or Codex. Supports multi-org workspaces, interactive ticket creation, subtasks, backlog management, and intelligent caching of your ClickUp workspace...
Upsert a single PR comment that serves as an AI session ledger (human steering, deltas, tests) across Codex + Claude Code. Not a PR description.
PRレビュー。PR番号・ブランチ名指定時またはレビュー依頼時に使用。Claude CodeとGPT-5.2-highのマルチモデルレビューでCritical/High/Medium分類の指摘を報告。
user-level指示の更新。Claudeが間違いを犯した際に、再発防止のためCLAUDE.md/context/を更新。
PJドキュメント同期。PJ CLAUDE.mdの更新依頼時やドキュメント整理依頼時に使用。user-level設定との整合性確認、ドキュメント分離原則の適用、不要ファイル削除を実施。
ドキュメント更新。コード変更後にnpm script/環境変数/API追加を検出した場合に使用。CLAUDE.md/README.md/API仕様の同期を支援。
既存設定と完全に整合したスキルを自動作成。~/.claude/CLAUDE.md、context/*.md、既存スキルを自動参照し、重複・競合を避けたスキルを生成。
プロジェクト初期化。CLAUDE.mdや.claude/がない場合にテンプレートを適用し、PJ固有設定を促す。
Create custom slash commands for Claude Code. Use when the user wants to create, generate, or build a slash command (.md file) for Claude Code, or when they ask about slash command syntax, frontmatter options,...
Package language-specific subsets of claudefiles
Package claudefiles components into a valid Claude Code plugin
Creates and configures Claude Code agent files (.claude/agents/*.md) with YAML frontmatter, tool permissions, model selection, and system prompt structure. Use when building new agents, configuring agent frontm...
Creates and configures Claude Code hooks for lifecycle automation. Use when implementing PreToolUse validation, PostToolUse formatting, PermissionRequest auto-approve, custom notifications, session management,...
Creates structured output formats (JSON, YAML, Markdown-KV, XML) and response style configurations for Claude. Use when: (1) defining agent output schemas (.json, .yaml, .xml), (2) configuring response style sc...
Creates and edits Claude Code skills with YAML frontmatter, folder structure, and depth-scaled content. Use when building new skills, updating existing skills, designing SKILL.md metadata, organizing skill fold...
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。