Claude Skills by quangphu1912

Use when tracing turn loops, tool continuations, state transitions, or understanding how an AI agent or complex system actually processes requests through its execution cycle

Use when understanding how source transforms to runtime, what gets filtered/compiled/generated, or tracing build-time shaping that affects what code actually runs

Use when separating prompt-driven behavior from code-driven behavior, understanding what system prompts actually control vs what's hardcoded, or testing how behavior changes under different prompt configurations

Use when evaluating code health, finding bug hotspots, identifying anti-patterns, preparing a quality improvement plan, or assessing technical debt

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when starting any codebase analysis to determine target type, feasibility, and which skills apply before investing tokens

Use when distinguishing core modules from support/generated/test/infrastructure code, separating signal from noise, or understanding which parts of a repo actually matter for analysis

Use when investigating implicit assumptions in code — ordering dependencies, unvalidated environment variables, assumed object shapes, or temporal state requirements that aren't enforced by types or tests

Use when reducing codebase size, cleaning up before refactoring, investigating slow builds, or auditing for unused code and orphaned files

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when investigating conditional tool availability, finding tools that exist but are hidden behind gates, or mapping the full capability surface of a system

Use when onboarding to a new project, evaluating migration feasibility, auditing dependency health, or needing to know what technologies power a codebase

Use when documenting public interfaces, planning API changes, evaluating backward compatibility, or understanding what a module exposes to consumers

Use when you need to understand why capabilities differ across configurations, user types, or deployment environments, or when investigating feature flags and capability gates

Use when needing component relationships, layer boundaries, module structure, or understanding how parts of a codebase fit together before modification or refactoring

Use when you need to understand what a system was truly designed to become, where its real moat lies, or to produce a comprehensive analysis report combining all prior findings

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when predicting how a system behaves under different conditions, testing "what if" scenarios for gate combinations, or comparing behavioral fingerprints across configurations

Use when executing implementation plans with independent tasks in the current session

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when you have a specific suspicion about a codebase and want targeted analysis to confirm or deny it with evidence, rather than exploratory analysis

Use when repo origin is unclear, dealing with leaks/sourcemaps/decompiled code, or needing to distinguish source of truth from derived, generated, or reconstructed layers

Use when tracking how data enters, transforms, persists, and exits a system, or when investigating trust boundaries, validation gaps, and potential data exfiltration paths

Use when investigating coupling between modules, finding circular dependencies, understanding change impact, or before modifying shared code

Use when analyzing, auditing, reverse engineering, or understanding any codebase — especially unfamiliar, inherited, leaked, or complex systems

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when you have a spec or requirements for a multi-step task, before touching code