Menu

Not in the top 1,000 by GitHub stars

QAMarcos/claude-qa-flow

QA workflow for AI coding agents: ticket → reviewed test plan → real-browser run with independent evidence review → bug tickets. Claude Code, OpenCode, any Agent Skills harness.

Claude CodeTestingEngineeringOperations

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/create-test-plan-scenarios/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

f7f1441e5c86 → f7f1441e5c86

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → f7f1441e5c86

No earlier version was observed for comparison.

Compare on GitHub

skills/file-bug-ticket/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

f7f1441e5c86 → f7f1441e5c86

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → f7f1441e5c86

No earlier version was observed for comparison.

Compare on GitHub

skills/manual-test/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

f7f1441e5c86 → f7f1441e5c86

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → f7f1441e5c86

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit f7f1441e5c86ff289afb7189a16e4cff52769279

git clone --filter=blob:none --no-checkout https://github.com/QAMarcos/claude-qa-flow.git .hotskills/qamarcos-claude-qa-flow && git -C .hotskills/qamarcos-claude-qa-flow checkout --detach f7f1441e5c86ff289afb7189a16e4cff52769279 # Copy each selected skill directory from .hotskills/qamarcos-claude-qa-flow into .claude/skills/<skill-name>/
12GitHub stars
0stars in 7 days
3skills in this repository
13commits in 30 days

Heat

1.6
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Oct 25, 202612

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

create-test-plan-scenarios

When your agent uses it

Turn a task/ticket into a structured, professional QA test plan — a checklist of atomic, executable scenarios — and (optionally) post it back to your issue tracker. Use whenever the user asks to "create a test plan", "list test scenarios", "criar cenários de teste", "QA checklist for TICKET-XXXX", or otherwise wants a ticket turned into a verifiable QA plan. Works for any story type (UI, API, mobile, infra). Always runs a self-review pass before writing anything back.

What it loads into context

Frontmatter

178 tokens

Always available to the agent

SKILL.md

2,316 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Step 0 — Triage & delegation (mandatory)
  2. Configuration (fill these in for your setup)
  3. Inputs
  4. Workflow
  5. Errors
  6. Notes

Files

  • ../../.claude-plugin/marketplace.jsonasset613 bytes
  • ../../.claude-plugin/plugin.jsonasset515 bytes
  • ../../hooks/hooks.jsonasset301 bytes
  • ../../hooks/hooks.jsonasset301 bytes
  • SKILL.mdcore9,952 bytes
  • SKILL.mdcore9,952 bytes
  • SKILL.mdcore9,952 bytes
  • SKILL.mdcore9,952 bytes
  • SKILL.mdcore9,952 bytes
Read SKILL.md

# Create Test Plan Scenarios

Turns any task/ticket into a structured, professional QA test plan: a checklist of atomic, observable, independently-runnable scenarios. Optionally posts the checklist back to your issue tracker as native sub-tasks. Works for UI, API, mobile, and infra stories. Always runs a self-review pass before writing anything.

> These scenarios are the source of truth consumed by the `manual-test` skill, which executes them against the running app. Keep each one atomic and observable so it maps cleanly to an executable step.

## Step 0 — Triage & delegation (mandatory)

This skill is a **router**: generation and self-review go to a subagent; the posting gate stays with
the user in the main conversation.

**Delegated (subagent, fresh context):** read the ticket, draft the checklist, and run the
self-review — Steps 1–5. The subagent **returns the checklist; it does not post.** Suggested brief:
View the complete source on GitHub

Skills included

  • create-test-plan-scenarios
  • file-bug-ticket
  • manual-test

Repository facts

License
MIT
Created
Jul 3, 2026
Last pushed
Nov 3, 2026
Forks
0
Open issues
0
Project activity
Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 8 notes
  • hooks/hooks.json:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/create-test-plan-scenarios/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/create-test-plan-scenarios/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/create-test-plan-scenarios/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/create-test-plan-scenarios/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/file-bug-ticket/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/file-bug-ticket/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/manual-test/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 29 signals by file

.claude-plugin/plugin.json

  • Network accessline 4
    "description": "Ticket → reviewed QA test plan → real-browser execution with evidence → independent review → terse bug tickets. Tracker-agnostic, Playwright-driven.",   "author": { "name": "Marcos Pereira" },   "homepage": "https://github.c
  • Network accessline 5
    "author": { "name": "Marcos Pereira" },   "homepage": "https://github.com/QAMarcos/claude-qa-flow",   "repository": "https://github.com/QAMarcos/claude-qa-flow",
  • Network accessline 6
    "homepage": "https://github.com/QAMarcos/claude-qa-flow",
  • Network accessline 7
    "repository": "https://github.com/QAMarcos/claude-qa-flow",

skills/create-test-plan-scenarios/SKILL.md

  • Network accessline 3
    description: Turn a task/ticket into a structured, professional QA test plan — a checklist of atomic, executable scenarios — and (optionally) post it back to your issue tracker. Use whenever the user asks to "create a test plan", "list test
  • Network accessline 4
    license: MIT compatibility: Any Agent Skills harness (Claude Code, OpenCode, Codex, ...). Tracker write-back needs shell access with curl (or equivalent) and an API token. Subagents recommended. metadata:
  • Network accessline 5
    compatibility: Any Agent Skills harness (Claude Code, OpenCode, Codex, ...). Tracker write-back needs shell access with curl (or equivalent) and an API token. Subagents recommended.
  • Network accessline 54
    - **`TRACKER_API_BASE`** — base URL of your tracker's REST API (e.g. `https://your-tracker.example.com/api/v3`).
  • Network accessline 56
    - **`TRACKER_STORY_URL`** — the human-facing URL pattern for a ticket (e.g. `https://your-tracker.example.com/story/<ID>`).
  • Network accessline 63
    - a bare id: `1234` - a prefixed id: `TICKET-1234` - a full URL: `https://your-tracker.example.com/story/1234/anything-after`
  • Network accessline 65
    - a full URL: `https://your-tracker.example.com/story/1234/anything-after`
  • Network accessline 78
    [Credential-related source omitted]
  • Access to secretsline 78
    [Credential-related source omitted]
  • Network accessline 141
    [Credential-related source omitted]
  • Access to secretsline 141
    [Credential-related source omitted]
  • Access to secretsline 142
    [Credential-related source omitted]

skills/file-bug-ticket/SKILL.md

  • Network accessline 3
    description: File a bug (or feature/chore) ticket in your issue tracker via its REST API with a terse, budgeted description, attached screenshot evidence, owner/priority/placement filled in, and a verification GET before reporting done. Use
  • Network accessline 4
    license: MIT compatibility: Any Agent Skills harness (Claude Code, OpenCode, Codex, ...). Needs shell access with curl (or equivalent) and a tracker API token. Subagents optional. metadata:
  • Network accessline 5
    compatibility: Any Agent Skills harness (Claude Code, OpenCode, Codex, ...). Needs shell access with curl (or equivalent) and a tracker API token. Subagents optional.
  • Network accessline 151
    [Credential-related source omitted]
  • Access to secretsline 151
    [Credential-related source omitted]
  • Access to secretsline 152
    [Credential-related source omitted]

skills/manual-test/references/playwright-templates.md

  • Network accessline 23
    test("manual: <one-line description>", async ({ page }) => {   await page.goto("https://staging.<your-app>.example.com/<entry-point>");
  • Network accessline 24
    await page.goto("https://staging.<your-app>.example.com/<entry-point>");
  • Access to secretsline 46
    [Credential-related source omitted]
  • Access to secretsline 65
    [Credential-related source omitted]
  • Network accessline 90
    const NOISE = /(analytics|googletagmanager|google-analytics|sentry|fonts\.|\.(png|jpe?g|svg|woff2?|css|js)(\?|$))/i; const requests: string[] = []; page.on("request", r => { if (!NOISE.test(r.url())) requests.push(`${r.method()} ${r.url()}`
  • Network accessline 91
    const requests: string[] = []; page.on("request", r => { if (!NOISE.test(r.url())) requests.push(`${r.method()} ${r.url()}`); }); page.on("response", async r => { if (!NOISE.test(r.url())) console.log(`  <- ${r.status()} ${r.url()}`); });
  • Network accessline 92
    page.on("request", r => { if (!NOISE.test(r.url())) requests.push(`${r.method()} ${r.url()}`); });

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 25 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/create-test-plan-scenarios/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/create-test-plan-scenarios/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/create-test-plan-scenarios/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/create-test-plan-scenarios/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/create-test-plan-scenarios/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

loukan42/chaosfolk

Simulated users explore web apps, with replayable browser evidence.

20GitHub stars

PramodDutta/qaskills

QA Skills Directory QA Skills is a curated directory of testing-specific skills for AI coding agents (Claude Code, Cursor, Copilot, etc.).

245GitHub stars

shenysun/skills-manager

CLI-first hub for agent skills: one npx install, manage in chat, distribute to 70+ agents

242GitHub stars

GulajavaMinistudio/awesome-copilot-id

A curated collection of custom agents, skills, rules, and prompts for GitHub Copilot, Google Antigravity, OpenCode, ChatGPT Codex, and Oh My Pi. Tailored for Indonesian and Intern…

93GitHub stars

fishzjp/qa-skills

Testing skills for AI coding agents: evidence-backed strategy, executable cases, Playwright/API testing, regression and QA memory. 面向 AI Agent 的测试工程技能。

61GitHub stars

geekjourneyx/readme-generator

Generate professional README.md with 16:9 infographics, SEO-optimized metadata, and structured author sections — powered by Playwright and AI agent skills

50GitHub stars