code-flow-viz
用于梳理和可视化代码流程,生成清晰的 ASCII 流程图、数据流图和表格分析。适用于已有代码的梳理、新功能设计的说明、以及技术文档的编写。
用于梳理和可视化代码流程,生成清晰的 ASCII 流程图、数据流图和表格分析。适用于已有代码的梳理、新功能设计的说明、以及技术文档的编写。
Capture moment of clarity before moving forward
A practical framework to map change dependencies and blast radius, including who/what is affected, what to test, rollout/rollback strategies, and stakeholder ownership
Essential rules for ensuring agents complete full multi-step workflows without stopping prematurely.
Create rich resumption points when hyperfocus breaks. Capture energy state, not just tasks. Use at the end of work sessions, when interrupted, or when sensing focus shifting.
Use when prioritizing animation features, building motion roadmaps, or when a PM needs to understand the business value of animation principles.
Analyze unlabeled GitHub issues and generate label recommendations for review. Supports batch submission after approval.
Creates project plan documents for tracking implementation work. Use when the user asks to create a project plan, implementation plan, or wants to document a new feature or refactoring task.
複雑なタスクを順次ステップに分解し、各ステップ内で並列サブタスクを実行するオーケストレーター。開発系・調査系・文書作成・データ処理など多段階タスクの計画・実行・統合を担う。複数のAgentを協調させる必要がある場合や、依存関係のあるタスク群を効率的に処理したい場合に使用する。
Track token usage and costs across agents for budget management
Track and document analytical assumptions and decisions. Use when making analytical choices, documenting trade-offs, ensuring transparency, or creating audit trails for analytical work.
Define and implement Service Level Indicators (SLIs) and Service Level Objectives (SLOs) with error budgets and alerting. Use when establishing reliability targets, implementing SRE practices, or measuring service performance.
Use when creating task documents - generates TASK.md skeletons with metadata and acceptance criteria
Use when sharing development progress publicly. Covers progress sharing, changelog writing, social media updates, community engagement, and milestone announcements.
Analyze mistakes with conversation length as potential cause (CAT-specific)
Execute backend implementation with TDD (Test-Driven Development). Write failing test first, then implement, verify each step. Use this skill when: - User asks to "implement this backend task", "implement backend" - Have an implementation plan ready and need to execute it - Executing steps from /backend.plan output - User says "start coding backend", "write backend code" - User asks to "use TDD", "write test first", "test-driven" for backend code - Fixing backend bugs (write failing test that reproduces bug first) TDD Iron Law: NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST TDD Cycle: RED (write failing test) → Verify fails → GREEN (minimal code) → Verify passes → REFACTOR Prerequisites: - MUST have task file in docs/reference/backend/tasks/ (use /backend.tasks first if not exists) - MUST read constraints.md before writing any code. Flow: Check Task File → Read Constraints → TDD Cycle (RED→GREEN→REFACTOR) → Verify Each → Run All Tests → Update Task Status → Notify PM
Define SLIs, SLOs, and implement burn-rate alerting
Naming conventions for planning documents in prompts/. Use when creating plans, PRDs, research reports, idea capture or other workflow documents. Triggers on (1) creating new planning documents, (2) naming PRDs or research reports, (3) questions about document organization in prompts/.
This skill should be used when managing project dependencies including safe updates, security audits, and compatibility analysis.
Create and manage support tickets throughout their lifecycle
Resume work on a project - discover state, verify health, clean up stale docs, suggest next tasks. Use when: (1) starting work at beginning of day, (2) after a long agent work loop completes, (3) user asks "what's next?", "what should we work on?", or similar, (4) user explicitly runs /next.