New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Generate Test Plan

by openshift-eng in openshift-eng/ai-helpers

Generate a comprehensive manual testing guide from a Jira issue, GitHub PR URLs, or both.

Apache-2.0Auto-check passedTesting & QA

Install Generate Test Plan

skills CLI
$ npx skills add openshift-eng/ai-helpers --skill generate-test-plan -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install openshift-eng/ai-helpers generate-test-plan --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/openshift-developer/skills/generate-test-plan .claude/skills/generate-test-plan && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
generate-test-plan
GitHub stars
120
Token cost
~1.6k tokens
SKILL.md length
712 words
Files
2 (incl. references)
Skills in repo
118
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generate a comprehensive manual testing guide from a Jira issue, GitHub PR URLs, or both.

  • Works in 6 steps: Parse input and gather sources → Analyze changes → Generate test scenarios → …
  • The user wants test steps
  • SKILL.md covers Name, Synopsis, Description and Implementation, plus 3 more sections
  • Reaches github.com; needs JIRA_KEY

What it does

Generate Test Plan is an agent skill from openshift-eng/ai-helpers. Generate a comprehensive manual testing guide from a Jira issue, GitHub PR URLs, or both. Use when the user wants test steps, a QE test plan, or a testing guide for code changes.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/ocpstrat-feature.md`).

It sits in Testing & QA, covering Test generation and QA and bug reports. It works with Jira and GitHub. The repository describes itself as: Developer productivity tools for Claude Code & other AI assistants. The licence is Apache-2.0.

When your agent uses it

  • The user wants test steps
  • A testing guide for code changes

Example prompts

  • “/generate-test-plan”

Requirements

  • A credential in JIRA_KEY

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Parse input and gather sources
  2. Analyze changes
  3. Generate test scenarios
  4. Apply smart filtering
  5. Create the test guide
  6. Report

What it can do on your machine

Read from SKILL.md and the folder at commit a627176. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • JIRA_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Generate Test Plan loads about 1.6k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 49 tokens; SKILL.md has 712 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from openshift-eng/ai-helpers at commit a627176, republished under its Apache-2.0 licence (© openshift-eng). 712 words, ~1,561 tokens.

Download SKILL.mdSave it as .claude/skills/generate-test-plan/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
generate-test-plan
description
Generate a comprehensive manual testing guide from a Jira issue, GitHub PR URLs, or both. Use when the user wants test steps, a QE test plan, or a testing guide for code changes.

Name

openshift-developer:generate-test-plan

Synopsis

text
/openshift-developer:generate-test-plan <JIRA_KEY | PR_URL> [additional PR URLs...]

Description

Generates a comprehensive manual testing guide by analyzing a Jira issue, one or more GitHub PRs, or both. Consolidates context from Jira acceptance criteria, PR diffs, commit messages, and changed files into actionable test scenarios.

When given a Jira key, it auto-discovers linked PRs. When given PR URLs directly, it works without Jira. Both can be combined.

Implementation

Step 1: Parse input and gather sources

  1. Parse arguments:

    • If $1 matches a Jira issue key pattern (e.g. CNTRLPLANE-205, OCPBUGS-12345): treat as Jira key
    • If $1 is a GitHub URL: treat as PR URL (no Jira context)
    • Remaining arguments ($2, $3, ...): additional PR URLs

  2. If a Jira key was provided, fetch Jira issue details using the Jira MCP tools (mcp__atlassian__jira_get_issue):

    • Issue summary, description, acceptance criteria
    • Steps to reproduce (for bugs)
    • Issue type (Story, Bug, Task, etc.)
    • Project key (e.g. OCPSTRAT, OCPBUGS, CNTRLPLANE)

  3. OCPSTRAT feature routing: If the issue's project is OCPSTRAT and the issue type is Feature, read references/ocpstrat-feature.md and follow its instructions for template parsing, analysis, scenario generation, document structure, and reporting in all subsequent steps. For non-OCPSTRAT issues (or OCPSTRAT issues that do not follow the feature template), do not read the reference — continue with the generic flow below.

  4. Discover PRs:

    • If explicit PR URLs were provided: use only those
    • If only a Jira key was provided: use mcp__atlassian__jira_get_issue with include: "remote_links" and look for GitHub PR links. Also check the issue description and comments for PR URLs.
    • For each PR, fetch details:
      bash
      gh pr view <PR_NUMBER> --repo <owner/repo> --json title,body,commits,files,labels,state
    • Read changed files and their diffs to understand implementation
Step 2: Analyze changes
  1. Identify the type of change (feature, bug fix, refactor)
  2. Determine affected components (API, CLI, operator, control-plane, etc.)
  3. Find platform-specific changes (AWS, Azure, KubeVirt, etc.)
  4. When multiple PRs exist:
    • Map which PR addresses which component or aspect
    • Identify dependencies between PRs
    • Determine testing order
  5. Use Grep and Glob to find related test files, configuration, and documentation
Step 3: Generate test scenarios
  1. Map Jira acceptance criteria to test cases (when Jira context available)
  2. For bugs: derive test cases from reproduction steps
  3. Generate scenarios covering:
    • Happy path (based on acceptance criteria or PR description)
    • Edge cases and error handling
    • Platform-specific variations if applicable
    • Regression scenarios for related features
  4. For multiple PRs: create integration scenarios verifying PRs work together
Step 4: Apply smart filtering

Skip PRs that don't require testing:

  • PRs with only documentation changes (.md files)
  • PRs with only CI/tooling changes (.github/, .claude/ directories)
  • PRs with labels like skip-testing or docs-only

Note skipped PRs in the output with reasoning.

Show full SKILL.md (291 more words)Show less
Step 5: Create the test guide

Filename convention:

  • Jira-based: test-{jira-key-lowercase}.md (e.g. test-cntrlplane-205.md)
  • PR-only: test-pr-{number1}-{number2}.md (e.g. test-pr-6888-6889.md)

Document structure:

  • Summary: Jira key + title (if available), list of PRs with titles, overall objective
  • Prerequisites: Required infrastructure, tools, environment setup, access requirements
  • Test Scenarios: Numbered test cases with:
    • Clear step-by-step instructions
    • Expected results and verification commands
    • Mapping to acceptance criteria (when Jira context available)
    • Platform-specific variations where applicable
  • Regression Testing: Related features to verify, areas that might be affected
  • Success Criteria: Checklist mapping to Jira acceptance criteria (when available)
  • Troubleshooting: Common issues and debug steps
  • Notes: Known limitations, links to Jira and PRs, dependencies between PRs

Exclusions: Do NOT include build/deploy steps or cleanup steps. Assume the environment is already set up. Focus purely on testing procedures.

Step 6: Report
  • Show the file path where the guide was saved
  • Summarize: Jira issue (if applicable), number of PRs analyzed, number of test scenarios, critical test cases
  • Highlight skipped PRs and reasoning
  • Ask if the user wants modifications

Examples

  1. From a Jira issue (auto-discovers PRs):

    text
    /openshift-developer:generate-test-plan CNTRLPLANE-205

  2. From a Jira issue with specific PRs only:

    text
    /openshift-developer:generate-test-plan CNTRLPLANE-205 https://github.com/openshift/hypershift/pull/6888

  3. From PR URLs only (no Jira):

    text
    /openshift-developer:generate-test-plan https://github.com/openshift/hypershift/pull/6888

  4. Multiple PRs without Jira:

    text
    /openshift-developer:generate-test-plan https://github.com/openshift/hypershift/pull/6888 https://github.com/openshift/hypershift/pull/6889

  5. From an OCPSTRAT feature (generates IEEE 829-style plan with deployment matrix, interop, NFR sections):

    text
    /openshift-developer:generate-test-plan OCPSTRAT-3266

Arguments

  • $1 — Jira issue key (e.g. CNTRLPLANE-205) or a GitHub PR URL (required)
  • $2, $3, ..., $N — Additional GitHub PR URLs (optional)

Guidelines

  • Use Jira MCP tools for Jira data, gh CLI for PR data
  • Derive test scenarios from actual code changes, not assumptions
  • Keep test steps concrete with exact commands and expected output
  • When Jira acceptance criteria exist, map every criterion to at least one test case

© openshift-eng, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in plugins/openshift-developer/skills/generate-test-plan of openshift-eng/ai-helpers.

  • SKILL.md
  • references/ocpstrat-feature.md

Open the folder on GitHubat commit a627176

Compare with similar skills

Generate Test Plan next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Generate Test Plan compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Generate Test Plan this skillopenshift-eng/ai-helpers120—~1.6kAutomated safety check: PassApache-2.0
Quality Engineering Quality AssuranceHoangNguyen0403/agent-skills-standard571—~629Automated safety check: PassMIT
Weavebench Cua ReproduceAMAP-ML/LongHorizon-Harness1.7k—~1.6kAutomated safety check: PassMIT
Evidence-Driven Testingmichaelshimeles/skills1.3k1 repos~3.9kAutomated safety check: PassNone
Senior QAnicepkg/auto-company1923 repos~1.1kAutomated safety check: NotesNone
Create GitHub IssueNVIDIA/OpenShell15k—~1.7kAutomated safety check: PassApache-2.0

Similar skills

  • Quality Engineering Quality Assurance

    HoangNguyen0403/agent-skills-standard

    Write or review manual Zephyr test cases with 1-condition-per-TC granularity, ModuleAction on Screen when Condition naming, platform prefix rules, and High/Normal/Low priority classification.

    571 GitHub stars~629 tokensUpdated today
    Testing & QAAuto-check passed

  • Weavebench Cua Reproduce

    AMAP-ML/LongHorizon-Harness

    Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout.

    1.7k GitHub stars~1.6k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed

  • Evidence-Driven Testing

    michaelshimeles/skills

    Records an annotated screen recording of the agent testing an app hands-on, then posts the video and a results summary to the PR and tracker issue.

    1.3k GitHub starsUsed in 1 repo~3.9k tokens
    Testing & QAAuto-check passed

  • Senior QA

    nicepkg/auto-company

    Comprehensive QA and testing skill for quality assurance, test automation, and testing strategies for ReactJS, NextJS, NodeJS applications.

    192 GitHub starsUsed in 3 repos~1.1k tokens
    Testing & QAAuto-check: notes

  • Create GitHub Issue

    NVIDIA/OpenShell

    Official

    Create GitHub issues using the gh CLI. An agent skill from NVIDIA/OpenShell.

    15k GitHub stars~1.7k tokensUpdated today
    Testing & QAAuto-check passed

  • QA Test Planner

    meshery/meshery-operator

    Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers.

    151 GitHub starsUsed in 5 repos~4.6k tokens
    Testing & QAAuto-check passed

More from openshift-eng/ai-helpers

All 118 skills in this repo

  • Investigate CI Reliability

    openshift-eng/ai-helpers

    Find and independently validate actionable reliability defects across OpenShift release jobs and presubmits, then export portable issue handoffs.

    120 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

  • Address Review PR

    openshift-eng/ai-helpers

    Fetch and address all PR review comments — categorize by priority, make code changes, post replies, and push.

    120 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

  • Categorize Activity Types

    openshift-eng/ai-helpers

    Categorize Jira issues into Red Hat Sankey Activity Type categories using MCP Jira tools.

    120 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed

  • Has Review Work

    openshift-eng/ai-helpers

    Decide whether a GitHub PR has unanswered authorized review comments or new required CI failures worth a follow-up agent.

    120 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

  • Must Gather Analyzer

    openshift-eng/ai-helpers

    Analyze OpenShift must-gather diagnostic data including cluster operators, pods, nodes, and network components.

    120 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed

  • Payload Autodl JSON

    openshift-eng/ai-helpers

    Schema for the autodl JSON data file produced by payload-analysis for database ingestion — you must use this skill whenever generating the autodl JSON file

    120 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Generate Test Plan

What does Generate Test Plan do?

Generate a comprehensive manual testing guide from a Jira issue, GitHub PR URLs, or both. Generate Test Plan is an agent skill from openshift-eng/ai-helpers. Generate a comprehensive manual testing guide from a Jira issue, GitHub PR URLs, or both.

When should I use Generate Test Plan?

Generate Test Plan fits situations like: the user wants test steps; A testing guide for code changes.

How do I install Generate Test Plan in Claude Code?

Run `npx skills add openshift-eng/ai-helpers --skill generate-test-plan -a claude-code`. Or copy the skill folder (plugins/openshift-developer/skills/generate-test-plan in openshift-eng/ai-helpers) into .claude/skills/generate-test-plan in your project. Claude Code loads it when a task matches its description.

How do I install Generate Test Plan in Codex?

Run `npx skills add openshift-eng/ai-helpers --skill generate-test-plan -a codex`. Or copy the skill folder (plugins/openshift-developer/skills/generate-test-plan in openshift-eng/ai-helpers) into .agents/skills/generate-test-plan in your project. Codex loads it when a task matches its description.

Can I use Generate Test Plan in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openshift-eng/ai-helpers --skill generate-test-plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/generate-test-plan, .gemini/skills/generate-test-plan, .github/skills/generate-test-plan and .opencode/skills/generate-test-plan in your project.

What does Generate Test Plan need to run?

Going by SKILL.md and its folder, Generate Test Plan needs credentials named JIRA_KEY. Our summary lists: A credential in JIRA_KEY.

Does Generate Test Plan access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Generate Test Plan safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Generate Test Plan use?

Generate Test Plan is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Generate Test Plan use?

About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.4k tokens, read only when the agent opens those files.

What are the alternatives to Generate Test Plan?

Skills that share tags, products or a category with Generate Test Plan: Quality Engineering Quality Assurance (HoangNguyen0403/agent-skills-standard, 571 stars), Weavebench Cua Reproduce (AMAP-ML/LongHorizon-Harness, 1.7k stars), Evidence-Driven Testing (michaelshimeles/skills, 1.3k stars) and Senior QA (nicepkg/auto-company, 192 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Generate Test Plan?

openshift-eng (a GitHub organization) maintains it in openshift-eng/ai-helpers, which has 120 GitHub stars. The repository holds 118 skills in this directory. The repository was last updated on October 6, 2026.

Source: openshift-eng/ai-helpers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.