xfi-execute-plan
Guide for executing engineering plans through coordinated subagent work. Use when executing existing plans from knowledge/plans/ directory.
Guide for executing engineering plans through coordinated subagent work. Use when executing existing plans from knowledge/plans/ directory.
Lightweight Linear skill for fetching issue details. Returns only essential data (title, description, state, assignee) to optimize context usage compared to full Linear MCP.
Personal research backlog. Quick-capture ideas for later exploration. Check when you have unstructured time.
Cost-effective task delegation strategy using Haiku model for straightforward work. Use when planning how to approach simple, pattern-following tasks to minimize costs.
開発作業のタスクリスト(tasklist.md)を生成します。このスキルは単独で使用することも、generate-working-docsから呼び出されることもあります。
Apply SPARC methodology (Specification, Pseudocode, Architecture, Refinement, Completion) for systematic development. Use for feature development, TDD workflows, and structured problem-solving.
Use when requirements specify risky technical assumptions, unfamiliar APIs, or complex integrations before implementing full features - creates sequential POC plans with parallel research validation, design documentation, and risk mitigation for incremental confidence building
Manages GitHub issue blocking/blocked-by relationships using the native dependencies feature via GraphQL API. Use when showing that one issue must complete before another can proceed, querying dependency relationships, or preventing circular dependencies.
Route work items to correct tables (feedback, features, build_tasks)
A leadership cadence where the CEO/Leader reviews actual work (designs, prototypes, copy) weekly rather than just metrics or status slides. Use when feeling product quality is slipping or team is moving too slowly.
When writing, reviewing, or validating user stories. Used by ARCHITECT-AGENT and PRODUCT-OWNER.
Generate a checklist for the legacy reskin given a specific criteria
Refactoring Techniques refactoring skill
A feedback approach where the manager acts as a curious investigator rather than an authoritarian expert, using observation and questions to help direct reports self-diagnose issues. Use during 1:1s and performance reviews.
Orchestrate end-to-end feature development from requirements through implementation, testing, and review. Use when: (1) planning feature development stages, (2) coordinating multi-agent feature workflows, (3) understanding SDLC phases for new features.
Classifies tasks by complexity pattern for smart routing. Auto-invoked for all implementation requests.
Calculate story point estimates for user stories using structured formula (Complexity × Effort + Risk). Analyzes acceptance criteria, assesses complexity (1-5), effort (1-5), and risk (0-3), then documents estimation rationale. Use during backlog grooming or sprint planning when stories need sizing.
Human-in-the-loop iterative development. Use when requirements will emerge during implementation, decisions need human approval at each step, or work will span multiple sessions with frequent feedback loops. Creates problem statement, decisions log, runbook, and progress tracking.
Prepare a Jira task with enrichment and subtask creation. Use when the user wants to "prepare task", "enrich issue", "create subtasks", or "prepare for development".