output-workflow-trace
Analyze Output SDK workflow execution traces. Use when debugging a specific workflow, examining step failures, analyzing input/output data, understanding execution flow, or when you have a workflow ID to investigate.
Boost efficiency with task automation and organizers.
Analyze Output SDK workflow execution traces. Use when debugging a specific workflow, examining step failures, analyzing input/output data, understanding execution flow, or when you have a workflow ID to investigate.
How Claude Code handles git commits and pull requests, including git safety protocols and best practices. Use when user asks about creating commits, making PRs, git workflows, or git safety.
Project management orchestration for website design and development projects. Use this skill when coordinating multi-agent website projects that require design, frontend development, quality control, accessibility compliance, SEO optimization, and performance analysis. Specifically use for (1) Planning website project workflows, (2) Coordinating design and development agents, (3) Enforcing quality gates and standards, (4) Managing project risks and timelines, (5) Handling stakeholder communication, (6) Ensuring WCAG AAA accessibility compliance, (7) Australian Consumer Law compliance for e-commerce sites, (8) Mobile-first responsive design enforcement.
Subskill zur Marker Engine für strikt markerbasierte JSON-Annotationen mit Farbhervorhebung; enthält Overlapping-Span-Merging, Dark-Mode-Farben und eine In-Page-SIT-UI (ohne Popup). Erzwingt ZIP-Entpacken, Supabase-Nutzung und Anti-Halluzination (Only-Original-Marker + 3×-Schwelle).
Break down PM story into backend tasks following LAYERED ARCHITECTURE order: Data Models → Database → Repository → Service → API → Validation → Tests. UNIQUE VALUE: Ensures proper dependency order and separation of concerns. Tasks are ordered by architectural layers, not random order. Use this skill when: - Running /backend.tasks command - User asks to "break down story for backend", "create backend tasks", "split into backend tasks" - Have story at docs/reference/pm/stories/ and need organized task list - Need tasks ordered by architectural layers (not random order) - Starting backend work and want organized, layered task list Layer order is CRITICAL: Types/Entities → Migrations → Repository → Service → API → Validation → Tests Output: ALWAYS write to docs/reference/backend/tasks/{story-name}.md
Manage Amplenote notes and tasks through natural language. Use when users ask to create notes, manage tasks, search their knowledge base, or mention 'Amplenote'.
Create well-structured Todoist tasks with Description and Definition of Done sections. Use this skill when creating new Todoist tasks to ensure they have enough context for any team member to understand and clear completion criteria.
Comprehensive guide to understanding and using this AI-assisted task management repository. Use this skill when users ask about how the repository works, what components are available, how to use agents/skills/prompts, or need guidance on the issue-tracking workflow.
Lifecycle management of plan documents from creation to automatic cleanup after merge. Use when creating, referencing, or cleaning up plans.
Review user stories from a developer perspective. Use when user wants to review user stories, check story quality, or says 'review this story', 'is this story clear', 'story feedback', or has user stories that need developer review before implementation.
PROACTIVELY USED when reviewing a PR, branch, or Jira story. Handles code review against requirements and provides actionable feedback.
Generate Sarah Briefs and maintain STATUS/TODO files for session continuity. Use for: (1) End-of-session documentation, (2) STATUS.md updates, (3) TODO.md task management, (4) Session context preservation. Triggers: Sarah Brief, brief, handoff, session end, status update, TODO update, documentation, end session.
주간 Claude Code 사용 분석 리포트 생성. 이번 주 모든 세션 로그를 분석하여 프로젝트별 시간 분포, 작업 유형, Jira 이슈 진행 현황 제공. "주간 분석", "Claude 사용 통계", "weekly analytics" 등의 요청 시 자동 적용.
Use for workflow guidance on HOW to work effectively. Covers task execution, decision escalation, and team coordination.
Create detailed handoff documents for session transitions. Captures task status, learnings, decisions, and next steps in a structured format.
Process and analyze action items discovered by watchers in the Personal AI Employee system. This skill should be used when new files appear in the Obsidian vault's /Needs_Action folder (created by Gmail watcher, filesystem watcher, or other monitoring scripts). It reads action item files, analyzes their content using Company_Handbook.md rules, creates structured Plan.md files with actionable steps, and updates Dashboard.md with system status. Use this skill whenever Claude Code detects new .md files in /Needs_Action that need processing, triage, or planning.
Create or update project issues following the standardized format with Functional Specifications (Preconditions/Workflow/Postconditions), Technical Specifications, and hierarchical task lists. Use when user asks to create/update an issue, document requirements, or write specifications for a new feature.
OpenSpec task management workflow. Use for creating, tracking, and closing tasks.
Diversion (dv) cloud-native version control. When Claude needs to help with source control operations using Diversion including: initializing repositories, cloning, committing changes, branching, merging, viewing diffs and logs, or any other version control tasks. This skill covers all dv CLI commands.
List Output SDK workflow execution history. Use when finding failed runs, reviewing past executions, identifying workflow IDs for debugging, filtering runs by workflow type, or investigating recent workflow activity.