feature-spec-reviewing
Reviews feature specifications for completeness, testability, and implementation readiness. Validates acceptance criteria, edge cases, and technical constraints. Use when reviewing feature specs before implementation or during sprint planning.
agile-requirement-analyzer
从客户原始需求到验收标准的完整敏捷需求分析工作流。适用于需要进行需求澄清、Epic分解、用户故事生成、INVEST评估和验收标准编写的场景。支持Epic/Feature/Story三个层次的需求分析，包含自动质量检查和优化决策机制。Use when analyzing customer requirements, breaking down Epics into user stories, evaluating story quality with INVEST principles, or generating acceptance criteria for agile development.
traceability-auditor
Validates complete requirements traceability across EARS requirements → design → tasks → code → tests. Trigger terms: traceability, requirements coverage, coverage matrix, traceability matrix, requirement mapping, test coverage, EARS coverage, requirements tracking, traceability audit, gap detection, orphaned requirements, untested code, coverage validation, traceability analysis. Enforces Constitutional Article V (Traceability Mandate) with comprehensive validation: - Requirement → Design mapping (100% coverage) - Design → Task mapping - Task → Code implementation mapping - Code → Test mapping (100% coverage) - Gap detection (orphaned requirements, untested code) - Coverage percentage reporting - Traceability matrix generation Use when: user needs traceability validation, coverage analysis, gap detection, or requirements tracking across the full development lifecycle.
github-issues-bug-workflow
Standard Agile process for bug reporting, triage, assignment, and resolution using GitHub Issues
executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
reflect
Perform reflection after completing work to capture learnings in KB. Ensures knowledge is preserved for future sessions. WHEN TO USE: - After completing a ticket (before archiving) - After completing a phase - Before session ends (user says "wrapping up", "stopping for now") - When user says "reflect", "capture learnings", "what did we learn" CAPTURES: - Patterns: problems solved (resolved) OR issues found (open) - Decisions: architectural/design choices made - Code flows: new understanding of codebase - Procedures: repetitive tasks worth documenting - Learnings: in ticket's 5-final.md
generating-quarterly-charters
Use when planning a quarter and need to convert signals (truth base, VOC, KTLO) into 3-5 strategic charters with clear problem statements and success metrics.
catcollect-results
Gather results from completed subagent including commits, metrics, and state updates
receiving-code-review
Collects and organizes code review feedback into actionable tasks.
skill-validator
Validate skills against production-level criteria. Use when reviewing, auditing, or improving skills to ensure they meet quality standards. Evaluates structure, content quality, user interaction patterns, documentation completeness, domain standards compliance, and technical robustness. Returns actionable validation report with scores and improvement recommendations.
session-learnings
Extract and codify learnings from planning-with-files sessions
74-mid-session-save-150
[74] CLOSE. Quick checkpoint during active work when context is running low. Use multiple times per development cycle to preserve progress and lessons. Lighter than close-session — no full handoff needed. Triggers on 'save progress', 'checkpoint', 'context low', or automatically when nearing token limits.
summarize-to-apple-notes
Summarize conversation content and save to Apple Notes app using HTML format. Use when user asks to "总结并保存到备忘录", "summarize and save to Notes". Handles both summarization and saving in one step. Can save to custom folder if user specifies.
manage-sprint
This skill MUST be used when the user asks to "create sprint", "start sprint", "end sprint", "complete sprint", "close sprint", "new sprint", "begin sprint", "finish sprint", "update sprint", "rename sprint", or otherwise wants to create or change sprint state/details.
using-vertical-tdd
OpenSpec駆動の垂直TDDスケルトン戦略。提案作成・技術検証・設計・実装・アーカイブの全ライフサイクルをサポート。 使用タイミング: (1) OpenSpecスラッシュコマンド実行時（`OpenSpec: Propose`, `OpenSpec: Apply`, `OpenSpec: Archive`） (2) 新機能開発の開始時（「新機能を追加」「〜を実装」リクエスト、OpenSpec提案がまだ存在しない場合） (3) 提案の修正・継続（openspec/changes/配下にファイルが存在、「提案を修正」「設計を見直し」リクエスト） (4) 実装の再開（tasks.mdに未完了タスクがある、「実装を続ける」「次のステップ」リクエスト） (5) 技術検証が必要（design.md作成前、複数技術選択肢がある、「技術検証」「ライブラリ調査」リクエスト） 使用しない場合: バグ修正、タイポ修正、ドキュメント更新のみ、設定ファイル変更のみ
feature-spec-critic
Review and score engineering specs against a startup-focused quality rubric. Penalize over-engineering and reward simplicity.
implementation-sequencer
验证代码构建顺序，分析依赖关键路径，建议Sprint划分和交付优先级。当STRUCT和GOAL确定后使用。
feature-roadmap-decomposition
Converts a decision-complete PRD into a concise, roadmap-ready list of features with explicit dependencies and Markdown output including a Mermaid dependency diagram.
next-bead
Find and safely claim the next Beads task with conflict checking. Use when looking for work, when finishing a task and need the next one, when the user mentions "next task" or "what should I work on", or when coordinating with other agents on task ownership.
executing-plans
Use when given 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
