Loading...
Loading...
Found 3,847 Skills
Conduct effective daily standup meetings for agile teams. Use when facilitating standups, tracking blockers, or improving team synchronization. Handles standup format, time management, and blocker resolution.
LLM 정확도 향상을 위한 프롬프트 반복 기법. 70개 벤치마크 중 67%(47/70)에서 유의미한 성능 향상 달성. 경량 모델(haiku, flash, mini)에서 자동 적용.
Standardize and validate SKILL.md files to match the project specification. Use when creating new skills, converting existing skills to standard format, or validating skill file structure. Handles section heading conversion, frontmatter standardization, and missing section detection.
Detect patterns, anomalies, and trends in code and data. Use when identifying code smells, finding security vulnerabilities, or discovering recurring patterns. Handles regex patterns, AST analysis, and statistical anomaly detection.
Configure and manage development, staging, and production environments. Use when setting up environment variables, managing configurations, or separating environments. Handles .env files, config management, and environment-specific settings.
Fast headless browser CLI for AI agents. Supports deterministic element selection via accessibility tree snapshots and refs (@e1, @e2).
Facilitate effective sprint retrospectives for continuous team improvement. Use when conducting team retrospectives, identifying improvements, or fostering team collaboration. Handles retrospective formats, action items, and facilitation techniques.
AI 코딩 에이전트를 시각적 Kanban 보드에서 관리. To Do→In Progress→Review→Done 흐름으로 병렬 에이전트 실행, git worktree 자동 격리, GitHub PR 자동 생성.
Install npm packages directly from GitHub repositories using git URLs. Use when installing packages from private repos, specific branches, or unreleased versions not yet on npm registry.
Manage Git submodules for including external repositories within a main repository. Use when working with external libraries, shared modules, or managing dependencies as separate Git repositories.
Interactive plan and diff review for AI coding agents. Visual browser UI for annotating agent plans — approve or request changes with structured feedback. Supports code review, image annotation, and auto-save to Obsidian/Bear Notes.
oh-my-claudecode — Teams-first multi-agent orchestration layer for Claude Code. 32 specialized agents, smart model routing, persistent execution loops, and real-time HUD visibility. Zero learning curve.