mcpbeat Sign in

Quality Engineering Zephyr Test Generation Agent Skill

Generate Zephyr test cases from Jira stories: parse acceptance criteria and business rules, impact-analyze existing TCs (update vs. create new), and draft correctly named test cases. Use for AC-to-test generation; defer post-generation Jira linking and manual test-case quality review.

3k tokens
context cost
the whole folder, loaded on every use
4
files
instructions only
0
copies elsewhere
how many repositories repackaged it
536
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/HoangNguyen0403/agent-skills-standard --skill quality-engineering-zephyr-test-generation

What comes with it

7 987 bytes besides the instruction
references/impact_analysis.md
references/tc_format.md
references/zephyr_schema.json

The instruction itself

10 sections, as written by the author

Zephyr Test Generation Standards

Priority: P1 (HIGH)

Workflow: Jira → Zephyr

  • Analyze Requirements:
  • Extract: Summary, ACs, Platform per AC row, Market, Components.
  • Fetch Jira with ?expand=renderedFields — HTML authoritative for platform colors:

#00B8D9 = Web · #36B37E = Mobile · #FF991F = Web+Mobile

  • See Actor/Permission Matrix for role/market logic.
  • Impact Analysis (run before any TC creation)
  • Step — Direct Lookup: Call Get Issue Link Test Cases with Jira issue key (e.g., {PROJECT}-{ID}).
  • Step B — Supplemental: If Step 0, search by [Module] and [Screen] keywords + check sibling issue links.
  • See Discovery Protocol for full chain.
  • Map each AC to coverage status:
  • Covered → ask user: skip or update to current format?
  • Partial → always propose NEW TC.
  • Not Covered → always create NEW TC.
  • Draft Artifact:
  • Delete any existing zephyr_test_plan.md before writing.
  • Follow 4-section format in TC Format Reference exactly.
  • After writing: read back file and print full content in chat so user can review without opening it.
  • Ask for: review approval, handling of Covered ACs, and Zephyr Folder ID.
  • Create in Zephyr (after explicit user approval)
  • Create Test Case (with customFields included — no separate Update needed) → Create Test Case StepsCreate Test Case Issue Link
  • For updates to existing TCs: fetch current steps via Get Test Case Steps, show before/after diff, wait for explicit approval, then Update Test Case.

Platform Rules

| AC row | Action |

| ------------------------------------------- | --------------------------------------------------------------- |

| Single row [ WEB + MOBILE ] | ONE TC, Platform = "Web and Mobile", no platform prefix in name |

| Two rows same behavior, different platforms | TWO TCs with Web_ / Mobile_ prefix — never merge |

Naming & Filing

  • Name: Prefix Web_ / Mobile_ only when platform-exclusive; omit prefix for Web and Mobile.
  • Folder: Use exact Folder ID provided by user or specified in Technical Impact.

Role Mapping Rule

  • CRITICAL: If Acceptance Criteria uses generic terms like "user", "buyer", or "customer" in ordering/checkout context, it MUST mapped to ALL purchasing roles: ["Client user", "Client admin", "Internal sales rep", "External sales rep"]. not default to Client user.

API Critical Notes (SmartBear MCP — @smartbear/smartbear-mcp)

  • Create Test Case requires projectKey="{PROJECT}" and supports customFields directly (no separate Update needed for Roles/Platform).
  • Create Test Case Steps uses testCaseKey + mode (APPEND/OVERWRITE) + items[].
  • Create Test Case Issue Link uses testCaseKey + issueId (numeric Jira issue ID — get from ticket's id field, not key string).
  • Get Issue Link Test Cases uses issueKey (e.g., {PROJECT}-{ID}) — returns linked TC keys directly.
  • Update Test Case uses testCaseKey — only needed when modifying existing TCs, not for new creation.

Anti-Patterns

  • No prefix omission: TC name sent to Zephyr API must include Web_ or Mobile_ prefix for platform-exclusive TCs — copy verbatim from artifact draft; omit prefix only when Platform = "Web and Mobile".
  • No Draft skip: Always set status = Draft; never automatically approve.
  • No flat folderId: Use "folder": {"id": X} in all PUT payloads.
  • No WEB+MOBILE split: One AC row = one TC with Platform "Web and Mobile".
  • No platform merge: Two AC rows, different platforms = two separate TCs.
  • No silent update: Show before/after diff; wait for explicit approval.
  • No lookup skip: Always run Step direct link lookup before supplemental search.
  • No stale artifact: Delete existing zephyr_test_plan.md before each run.
  • No coverage skip: Coverage Analysis table must open every artifact.
  • No ghost update: Update Zephyr TC whenever matching code changes.
  • No vague steps: Use specific observable outcomes — e.g., "System works""Banner 'Success' is visible".

Coverage wording

  • During impact analysis, map each AC to Covered, Partial, or Not Covered and check for duplicate test cases before drafting new ones.

Canonical response anchors

When this skill applies, preserve the following domain terminology or equivalent concrete examples in the answer when relevant:

  • duplicate
  • impact analysis
  • no platform prefix
  • separate
  • Additional task-grounded exact anchors: Issue Link

Other skills for the same job

different authors, same section of the catalogue
Doc Coauthoring
by anthropics
vendor ×10

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

4k tokens
File Organizer
by frostant
×10

Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.

3k tokens
Domain Name Brainstormer
by frostant
×8

Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.

1k tokens
Brainstorming
by ZhanlinCui
×4

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.

626 tokens
Planning With Files
by ZhanlinCui
×3

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

9k tokens scripts
Scientific Brainstorming
by christophacham
×3

Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.

5k tokens
GitHub Project Management
by ComeOnOliver
×3

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

14k tokens
Grill Me
by ComeOnOliver
×3

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

3k tokens

How to use it

Copy the folder

Take hoangnguyen0403/quality-engineering-zephyr-test-generation from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.