← All skill packs

Testing & Debugging Skills

Skill pack
24 skills0 selected
herren-officialSkills in this pack

\"Review API calls, responses, and network traffic. 審API調用響應網絡流量.

English

Expert knowledge for working with Backlog.md task management. Use when managing tasks, organizing epics, handling dependencies, or tracking project progress. Automatically applies Backlog.md best practices.

English

Branch naming conventions, Git Flow vs trunk-based development, feature branch lifecycle, and release strategies. Reference when creating branches, planning releases, or choosing a branching model.

English

Show detailed view of a story or task. Auto-detects type by ID format: S001 = story, S001-001 = task.

English

Create Playwright E2E tests for user flows. Use when testing complete user journeys, protected routes, form submissions, or cross-page navigation.

English

Forked-context QA reviewer — preloads verdict schema + testing-pyramid lens + assertion/edge-case/TDD checklist.

English

Automatically extract technical requirements from design references when user mentions Figma, uploads images, or says "implement this design". Analyzes colors, typography, spacing, layout, and maps to WordPress blocks or Drupal paragraph fields. Provides detailed specifications for developers including exact values, responsive behavior, and accessibility requirements.

English

Update a plan document with the latest implementation status, test results, and completed steps. Use when the user asks to update, sync, mark progress on, or refresh a plan. Keywords: plan, update, sync, progress, status, plan document, mark complete.

English

Use when a session starts, when the user asks to "continúa", "kickoff", "arranca la siguiente rama", or when you need a fast snapshot of repo state before doing branch work. Emits a ≤12-line snapshot (branch, phase, last merge, next branch, warnings). STOPS BEFORE Fase -1 — does not create markers, does not execute branch-plan.

English

Чеклист и формат code review: severity levels (CRITICAL/MAJOR/MINOR/NIT), формат вердикта (APPROVED/CHANGESREQUESTED/BLOCKED), Django anti-patterns, N+1 detection, dbt checks, verification gate, протокол обработки фидбэка, risk-first review. Загружать при проведении code review, при запуске Reviewer агента, при форматировании результатов ревью, или когда Builder получает CHANGESREQUESTED.

English

Performance review. Detects project type and dispatches compute and/or web performance reviewers. Advisory only — no changes made.

English

White-box security audit. Blue-teamer and lead red-teamer run in parallel isolation for an independent first pass — neither sees the other's output during reconnaissance. A synthesis step categorizes findings into four prescriptive buckets (anchoring-suppressed, convergent, blue-flagged-unverified, divergent), producing a unified target list. Focused red-teamers then deep-dive each target. Iterates when exploit chains are discovered. Heavy and thorough by design.

English

Analyze and improve test coverage. Use when reviewing coverage gaps, writing missing tests, setting up coverage tooling, or improving branch/line/statement coverage for any language or framework.

English

Use when backfilling tests on existing code. Analyzes code through public interfaces, detects the project's test framework, and writes behavior-focused regression tests. Supports targeted mode (specific files) and diff-based mode (changed files from git). Use this whenever the user says write tests, add tests, cover this, or wants regression tests for existing code.

English

Compose UI 구현.

Korean

EC2 서버 SSH 접속하여 로그…

Uncertain

PR 체인 브랜치들을 순서대로 리베이스하고 force…

Korean

프로젝트 DesignSystem 모듈의 컴포넌트, Foundation 토큰, Extensions를 탐색하고 API를…

Korean

Figma URL을 분석하여 디자인 구조, 토큰, 컴포넌트를 추출하고 DesignSystem 매핑을…

Korean

Issue 番号に基づいて feature ブランチを自動作成する。「ブランチ作成」「ブランチを作って」「新しいブランチ」「feature ブランチ」「Issue からブランチ」「作業ブランチを作成」「ブランチ切って」などで起動。feature/[issue番号]…

Japanese

CareMatch용 Next.js API 라우트 생성. 인증, 입력 검증, 에러 처리가 포함된 API 엔드포인트를 생성합니다.

Korean

변경사항을 자동으로 분석하고 커밋 룰에 따라 커밋…

Uncertain

Figma MCP를 활용하여 디자인 시안을 인스타겟 프론트엔드 컨벤션(styled-components, Next.js Pages Router)에 맞게 UI…

Korean

노션 백로그에 작업 내용을 맥락 중심으로 정리. "백로그 정리", "노션 정리", "작업 내용 정리" 등 백로그 문서화 요청 시 사용.

Korean

Includes Agnt Review API, Backlog Workflow, Branch Strategy, and other workflows.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Pack stats

Skills24CategorygeneralStars0

What’s included

Agnt Review API

\"Review API calls, responses, and network traffic. 審API調用響應網絡流量. Use when: inspect API calls, review network requests, check API responses, analyze request payload, debug API issues\

Backlog Workflow

Expert knowledge for working with Backlog.md task management. Use when managing tasks, organizing epics, handling dependencies, or tracking project progress. Automatically applies Backlog.md best practices.

Branch Strategy

Branch naming conventions, Git Flow vs trunk-based development, feature branch lifecycle, and release strategies. Reference when creating branches, planning releases, or choosing a branching model.

Cctd:view

Show detailed view of a story or task. Auto-detects type by ID format: S001 = story, S001-001 = task.

Create E2E Test

Create Playwright E2E tests for user flows. Use when testing complete user journeys, protected routes, form submissions, or cross-page navigation.

Dartai QA Reviewer

Forked-context QA reviewer — preloads verdict schema + testing-pyramid lens + assertion/edge-case/TDD checklist. 對抗QA審查(fork上下文)。 Use when: dispatch qa-reviewer subagent, adversarial QA review, gate on test quality, when reviewer must not pollute main thread

Design Analyzer

Automatically extract technical requirements from design references when user mentions Figma, uploads images, or says "implement this design". Analyzes colors, typography, spacing, layout, and maps to WordPress blocks or Drupal paragraph fields. Provides detailed specifications for developers including exact values, responsive behavior, and accessibility requirements.

Plan Update

Update a plan document with the latest implementation status, test results, and completed steps. Use when the user asks to update, sync, mark progress on, or refresh a plan. Keywords: plan, update, sync, progress, status, plan document, mark complete.

Project Kickoff

Use when a session starts, when the user asks to "continúa", "kickoff", "arranca la siguiente rama", or when you need a fast snapshot of repo state before doing branch work. Emits a ≤12-line snapshot (branch, phase, last merge, next branch, warnings). STOPS BEFORE Fase -1 — does not create markers, does not execute branch-plan.

Review Checklist

Чеклист и формат code review: severity levels (CRITICAL/MAJOR/MINOR/NIT), формат вердикта (APPROVED/CHANGESREQUESTED/BLOCKED), Django anti-patterns, N+1 detection, dbt checks, verification gate, протокол обработки фидбэка, risk-first review. Загружать при проведении code review, при запуске Reviewer агента, при форматировании результатов ревью, или когда Builder получает CHANGESREQUESTED.

Review Perf

Performance review. Detects project type and dispatches compute and/or web performance reviewers. Advisory only — no changes made.

Review Security

White-box security audit. Blue-teamer and lead red-teamer run in parallel isolation for an independent first pass — neither sees the other's output during reconnaissance. A synthesis step categorizes findings into four prescriptive buckets (anchoring-suppressed, convergent, blue-flagged-unverified, divergent), producing a unified target list. Focused red-teamers then deep-dive each target. Iterates when exploit chains are discovered. Heavy and thorough by design.

Test Coverage

Analyze and improve test coverage. Use when reviewing coverage gaps, writing missing tests, setting up coverage tooling, or improving branch/line/statement coverage for any language or framework.

Test Write

Use when backfilling tests on existing code. Analyzes code through public interfaces, detects the project's test framework, and writes behavior-focused regression tests. Supports targeted mode (specific files) and diff-based mode (changed files from git). Use this whenever the user says write tests, add tests, cover this, or wants regression tests for existing code.

B2b Android Compose UI

Compose UI 구현. "UI 만들어줘", "Compose 화면", "디자인 구현", "화면 개발", "Figma 구현" 요청 시 사용

B2b Backend Ec2

EC2 서버 SSH 접속하여 로그 확인

B2b Backend PR Chain Rebase

PR 체인 브랜치들을 순서대로 리베이스하고 force push

B2c Ios Design System Explore

프로젝트 DesignSystem 모듈의 컴포넌트, Foundation 토큰, Extensions를 탐색하고 API를 분석합니다

B2c Ios Figma Analyze

Figma URL을 분석하여 디자인 구조, 토큰, 컴포넌트를 추출하고 DesignSystem 매핑을 수행합니다

Branch Creator

Issue 番号に基づいて feature ブランチを自動作成する。「ブランチ作成」「ブランチを作って」「新しいブランチ」「feature ブランチ」「Issue からブランチ」「作業ブランチを作成」「ブランチ切って」などで起動。feature/[issue番号] 形式でブランチを作成。

Create API

CareMatch용 Next.js API 라우트 생성. 인증, 입력 검증, 에러 처리가 포함된 API 엔드포인트를 생성합니다. 사용법 - "API 만들어줘", "지원 API 생성

Create Commit

변경사항을 자동으로 분석하고 커밋 룰에 따라 커밋 생성

Instaget Front Figma Publishing

Figma MCP를 활용하여 디자인 시안을 인스타겟 프론트엔드 컨벤션(styled-components, Next.js Pages Router)에 맞게 UI 퍼블리싱

Update Backlog

노션 백로그에 작업 내용을 맥락 중심으로 정리. "백로그 정리", "노션 정리", "작업 내용 정리" 등 백로그 문서화 요청 시 사용.

Quick start

  1. Choose your skills. Select individual skills above, or choose the entire pack.
  2. Copy the install prompt. Use Copy install prompt above the list.
  3. Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.

Try it with your agent

After installation, start with a request like:

Example request
Use the Agnt Review API skill to help with my task.
Ask me for the context you need before getting started.

Requirements & license

  • A coding agent that can access your project files and install skills.
  • Your agent checks each skill’s instructions, dependencies, and permissions during setup.
  • License details are not provided in these listings. Check the author’s terms before using the skills.
Testing & Debugging Skills | Agent Skills Atlas