メニュー
Discovers and invokes the repo-local skill set. Use when starting work or when you need to choose the right workflow for the current task.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | using-agent-skills |
| description | Discovers and invokes the repo-local skill set. Use when starting work or when you need to choose the right workflow for the current task. |
Entry routing skill for minimal context loading. Use it to understand the request, resolve only the ambiguity that matters, and choose the next workflow skill without preloading the whole chain.
AGENTS.md by default.nx-workspace immediately for Nx exploration/debugging and nx-generate immediately for Nx scaffolding/setup when repo rules require them.product-and-scope-reviewspec-driven-developmentdebugging-and-error-recoveryaddress-review-feedbackqa-verificationrelease-readinessfrontend-ui-engineeringapi-and-interface-designrefactoring-and-simplification, test-driven-development, and code-review-and-quality load only at their checkpoints, not during entry. Do not add the refactor checkpoint to entry workflow selection.references/reviewer-routing.md rather than restating the full lifecycle here.../../references/behavioral-guidelines.mdreferences/skills-catalog.mdreferences/reviewer-routing.md.agents/references/stack-conventions/<stack>.mdDelivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
Runs a conditional behavior-preserving refactor checkpoint. Use after a verifiable implementation slice creates large-file pressure, semantic duplication, mixed responsibility, hard-to-test logic, or current-change orphan code. Use before feature implementation only when an approved plan says a preparatory refactor is needed.
Verifies implemented behavior with evidence. Use after implementation to gather proof, reproduce user flows, and decide whether the session is report-only or fix-enabled. Browser-visible work uses interactive verification paths; backend and Tauri-runtime work use smoke checks, task commands, and structured findings.
Builds production-quality UIs. Use when building or modifying user-facing interfaces. Use when creating components, implementing layouts, managing state, or when the output needs to look and feel production-quality rather than AI-generated.
Explore and understand Nx workspaces. USE WHEN answering questions about the workspace, projects, or tasks. ALSO USE WHEN an nx command fails or you need to check available targets/configuration before running a task. EXAMPLES: 'What projects are in this workspace?', 'How is project X configured?', 'What depends on library Y?', 'What targets can I run?', 'Cannot find configuration for task', 'debug nx task failure'.
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.