行動開發

Upgrade dependencies safely using pnpm catalog, checking for breaking changes, and testing upgrades. Use when updating packages, applying security patches, or upgrading major versions.

Use when fixing Rubocop violations. Runs Rubocop to identify issues, applies fixes following project conventions, and explains non-obvious corrections.

Profile application performance, identify bottlenecks, and optimize slow operations. Use when investigating performance issues, optimizing response times, or improving resource usage.

Use when creating or refactoring Stimulus controllers. Applies Hotwire conventions, controller design patterns, targets/values usage, action handling, and JavaScript best practices.

When creating tests and using tests for testing of application operation

For understanding what each mode does, which mode is best (most appropriate mode) for a given situation, and establishing a pattern for choosing when and how a mode delegates or passes operation to another mode

Product discovery frameworks for PMs - customer interviews, assumption mapping, JTBD, RICE prioritization, and opportunity solution trees. Transforms research into product decisions.

Structured business decision-making using Tree of Thoughts methodology with expert consultants exploring multiple approaches

Track errors with CloudWatch Logs, implement structured logging, and monitor application health. Use when debugging production issues, investigating errors, or improving observability.

Set up Claude Code cloud/mobile environments for AILANG development. Use when starting a new cloud session, when tools are missing (Go, make, gh), or when user says "setup cloud", "setup environment", or mentions mobile Claude Code.

Creates Stories from IDEAL plan (CREATE) or appends user-requested Stories (ADD). Generates 8-section documents, validates INVEST, creates in Linear. Invoked by ln-220.

Digital forensic skill for recovering passwords and sensitive data from disk images, deleted files, and binary data. This skill should be used when tasks involve extracting passwords from disk images, recovering deleted file contents, analyzing binary files for fragments, or forensic data recovery scenarios. Applies to tasks mentioning disk images, deleted files, password fragments, or data recovery.

Use when creating new skills, editing existing skills, or verifying skills work - applies TDD to documentation by testing with subagents before writing

Manage coordinator daemon tasks, approve/reject work, monitor autonomous agents. Use when user asks to delegate tasks, check task status, review agent work, manage the coordinator, or use GitHub-driven approval workflow.

Review technical recommendations before presenting them to the user. Use BEFORE suggesting config changes, optimizations, refactors, or architecture decisions. Spawns a subagent to challenge assumptions and filter out generic advice that doesn't apply to the user's context.

Market analysis and competitive intelligence for startups. Use when analyzing market opportunities, sizing TAM, profiling segments, or mapping competition.

LLM evaluation and testing patterns including prompt testing, hallucination detection, benchmark creation, and quality metrics. Use when testing LLM applications, validating prompt quality, implementing systematic evaluation, or measuring LLM performance.

Use when developing Salesforce applications, Apex code, Lightning Web Components, SOQL queries, triggers, integrations, or CRM customizations. Invoke for governor limits, bulk processing, platform events, Salesforce DX.

Use when the user asks why something happened, what’s wrong, root cause analysis, debugging, or incident explanation.

Identifies anti-patterns specific to amplihack philosophy. Use when reviewing code for quality issues or refactoring. Detects: over-abstraction, complex inheritance, large functions (>50 lines), tight coupling, missing __all__ exports. Provides specific fixes and explanations for each smell.