Навыки: Тестирование

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

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

requesting-code-review

Dispatch code-reviewer subagent to review implementation against plan or requirements before proceeding

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

Use when completing tasks or major features. Know when and how to request reviews. Provides git commit range to code-rev...

Model a requirement/system: extract goals, scope, roles, rules, exceptions, dependencies from PRD, docs, bugs, code; out...

Apply requirement quality principles when generating or validating feature specifications. Enforces feature completeness...

Classifies requirements using BABOK's four types (business, stakeholder, functional, non-functional, transition), checks...

Applies repository-specific requirements standards to requirement documents. Use this skill when creating, editing, or r...

Convert vague requests into clear functional and non-functional requirements.

Transform stakeholder needs into structured, testable specifications with user stories, acceptance criteria, and busines...

Spec Kit を使って要件定義や仕様作成（仕様策定・仕様書作成・仕様設計を含む）を新規作成または既存仕様へ追記し、spec.md/plan.md/tasks.mdまで生成・更新する。要件定義、要件追加/変更、TDD前提の要件整理、仕様の...

Master requirements gathering, user story writing, acceptance criteria definition, and scope management. Transform insig...

Validates PRD, user stories, or feature requirements against SMART criteria. Use when reviewing requirements to catch va...

Use when you need to review, validate, and improve requirements documents, acceptance criteria, or implementation briefs...

Write clear, testable requirements using User Stories and Gherkin scenarios. Capture functional and non-functional requi...

Delegate a substantial diagnosis, implementation, or follow-up task to Claude Code through the tracked-job runtime. Args...

Fast agent specialized for exploring codebases and searching for code patterns. Use via spawn_subagent with skill='resea...

Use the /research skill when performing background research from the literature or the web to create a RESEARCH.md file;...

Deep research with multi-source gathering, source evaluation, contradiction detection, and structured synthesis

Validates medical claims with external evidence using web search, providing citations for the final report.

Use when reviewing, revising, or deciding whether to complete a Research Architect draft, especially when its reference...

Generate a `ResearchPlan` from `input.md` or equivalent raw research input.

Use when the user has a vague research direction and wants to explore feasible specific topics. Outputs a structured ana...

Identify and visualize research gaps, coverage, and conflicts with explicit constraints and evidence.

Turn papers, PDFs, reports, lecture notes, datasets, or research material into an evidence-aware AI podcast for deep div...

Use when the user has a research proposal (problem + proposed methodology + planned experiments) and wants it iterativel...

Route scholarly literature synthesis, study-method review, and citation-integrity checking; not for general market resea...

Turn messy research into a sourced, structured synthesis with conclusions, uncertainty, and next actions.

Spawn a research agent team for multi-source investigation. Use when researching topics requiring multiple URL fetches,...

Performs quality control, citation validation, and fact-checking before human review. Use after research is complete to...

Checklist for reliability engineering

Given a Pull Request (PR) number, resolves in two phases: (1) automatically detects and semantically resolves merge conf...

Resolves stuck review findings via a put-up-or-concede exchange. Invoked by the facilitator when a finding survives arbi...

Fix test failures in a worktree without merging. Leaves worktree green and unmerged for the orchestrator's merge gate. U...

Specialized test resolution that works in parallel to fix specific test failures, enabling faster resolution of test sui...

Resource capacity planning and allocation skill for managing people and skillsacross multiple projects. Identifies confl...

Implement advanced caching with precise invalidation for highly dynamic data domains.

Use when creating data containers in Godot — custom Resources for configuration, items, stats, and editor integration

Apply findings from a /findings review to an ADR and write a response file

Respond to review comments on a PR after evaluation and fixes

Pre-send quality review for accuracy, clarity, and completeness

Checks desktop, tablet, and mobile UI for overflow, clipping, navigation, grid, canvas, and breakpoint regressions.

Tests the running app at multiple viewport breakpoints (mobile, tablet, desktop) to detect layout overflow, clipped text...

Verify composition across breakpoints.

Test website responsiveness across viewport widths using browser automation. Resizes a single session through breakpoint...

Production-grade REST API automation framework with REST Assured, POJO serialization using GSON, PayloadManager pattern,...