executing-plans
Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches
Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches
Structured retrospective for incidents and mistakes. Transforms problems into systematic improvements.
Break down GitHub issues into official GitHub sub-issues by parsing task lists from parent issue descriptions. Use this skill when a user wants to convert a parent issue with tasks into linked sub-issues, when managing complex features that need hierarchical breakdown. Accepts issue number as parameter or prompts user if not provided.
撰写或更新 Project Guardrails/工程规范(前端/后端/API/数据/安全/运维/发布)。用于新项目启动、技术栈变更、多团队协作、事故复盘或持续漂移出现时建立统一约束与最低标准。
Create detailed implementation plans before coding (saves tokens later)
This skill should be used when the user asks to "analyze slide quality", "review slide", "check slide design", "optimize slide", "improve slide content", "assess slide clarity", or needs evidence-based quality evaluation using the 12-point checklist for presentation slides.
Read project session context from .sessions/index.md to understand ongoing work, previous decisions, blockers, and history. Use when the user asks about project context, previous sessions, what was worked on before, architectural decisions, blockers, or when they reference "last time", "previously", "the session", or "what we decided".
Discovery questions, checklists, and techniques for gathering requirements. Use during discovery to ensure thorough understanding before creating issues.
Auto-update status metrics across governance documents - scans MCP issues/specs to calculate current counts and percentages, updates README files and NEXT_STEPS with accurate data
Fetch unresolved PR review comments from GitHub. Use when working with pull request reviews, addressing review feedback, or checking outstanding review comments on a PR. Triggers on requests like "get PR reviews", "fetch review comments", "show unresolved comments", or "what feedback is pending on this PR".
INVOKE after research or brainstorming to synthesize findings. Produces visible aggregation with conflict resolution. Use when multiple inputs need combining into coherent output. Triggers: synthesizing research, combining ideas, merging approaches, integrating findings.
Systematic questioning to clarify requirements, goals, and constraints. Use when there's ambiguity about what the user wants, hidden complexity needs uncovering, or you need to understand before proceeding. Triggers on unclear requirements, vague goals, or when other skills encounter fundamental ambiguity.
Automated technical debt identification, tracking, and prioritization system
Log work activity to a specific project folder. Maintains changelogs, session notes, and decision records for projects.
Search for features and automatically retrieve all child work items (stories, tasks, bugs) under that feature. Use when planning or reviewing feature scope.
Use BEFORE using the Task tool. Ensures you select the correct specialized subagent_type instead of generic agents.
스킬 생태계를 관리하고 품질을 유지합니다. 전체 스킬 현황 파악, 품질 분석, 문제점 진단, 개선 제안, 자동 수정, 새 스킬 생성 가이드를 제공합니다. "스킬 분석", "스킬 현황", "스킬 만들기", "스킬 개선" 요청 시 활성화됩니다.
Create a new project with proper PARA structure. Ensures consistent project setup with completion criteria and status tracking.
Use during planning to discover and document available project commands (make targets, npm scripts, etc.) for success criteria.
Transform PBIs into ready status for AI execution. Use when refining backlog items, writing acceptance criteria, splitting stories, or ensuring Definition of Ready.
Use when creating implementation plans to research codebase patterns and gather context for planning.