Agent skill

User Behavior QA

by wannabespace in wannabespace/conar

Test the running app through its visible browser UI as a real user.

AGPL-3.0Auto-check passedTesting & QA

Install User Behavior QA

skills CLI
$ npx skills add wannabespace/conar --skill user-behavior-qa -a claude-code

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

GitHub CLI
$ gh skill install wannabespace/conar user-behavior-qa --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/wannabespace/conar.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/user-behavior-qa .claude/skills/user-behavior-qa && 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
user-behavior-qa
GitHub stars
1.5k
Token cost
~1.4k tokens
SKILL.md length
784 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Test the running app through its visible browser UI as a real user.

  • Works in 5 steps: Intake → Operate like a user → Exercise the scoped journey → …
  • A developer asks for QA
  • SKILL.md covers 1. Intake, 2. Operate like a user, 3. Exercise the scoped journey and 4. Evidence rules, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

User Behavior QA is an agent skill from wannabespace/conar. Test the running app through its visible browser UI as a real user. Use when a developer asks for QA, a smoke test, user journey testing, to click through a feature or test it like a user, or wants a list of user-visible gaps without inspecting implementation code.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering QA and bug reports and Customer journey mapping. The repository describes itself as: AI-powered tool for working with Postgres, MySQL, MSSQL and Clickhouse. The licence is AGPL-3.0.

When your agent uses it

  • A developer asks for QA
  • User journey testing
  • Click through a feature
  • Test it like a user

Example prompts

  • “/user-behavior-qa”

Workflow steps

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

  1. Intake
  2. Operate like a user
  3. Exercise the scoped journey
  4. Evidence rules
  5. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 53c9289. 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

    No URLs in SKILL.md.

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

User Behavior QA loads about 1.4k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 784 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 wannabespace/conar at commit 53c9289, republished under its AGPL-3.0 licence (© wannabespace). 784 words, ~1,392 tokens.

Download SKILL.mdSave it as .claude/skills/user-behavior-qa/SKILL.md (or your agent's skills folder).
name
user-behavior-qa
description
Test the running app through its visible browser UI as a real user. Use when a developer asks for QA, a smoke test, user journey testing, to click through a feature or test it like a user, or wants a list of user-visible gaps without inspecting implementation code.

User Behavior QA

Review the product from the user's side. Treat the browser as the product boundary: use visible controls, navigation, forms, feedback, and persisted results. Do not inspect source code, internal APIs, database clients, server logs, or implementation details unless the user explicitly expands the scope. The browser console is fair evidence (see §4).

1. Intake

Defaults, unless the developer says otherwise:

  • Target: https://app.local.tamery.app, or the worktree's own dev URL when testing a branch (see monorepo.md).
  • Mutations: create, edit and delete test data on local dev. Any other environment, or an unclear one, is read-only.
  • Browser: the user's Chrome (mcp__claude-in-chrome__*), because the app is behind auth and the CLI browsers are signed out.

Only ask about what is still missing, in one message: the pages, workflows, entities, database engines (listed in .agents/rules/dialects.md) and roles in scope, and the expected behavior or baseline. If the invocation already covers these, do not ask. State the test charter in one sentence and start.

Before the first browser action, read:

  • .agents/rules/monorepo.md → Opening the running app in a browser, including the user's-Chrome traps;
  • .agents/rules/domain.md and the user docs for the area in scope. These give the product terms to use in the report and show which gaps are deliberate.

2. Operate like a user

  • Stay inside the product UI. A built-in query editor or admin screen is allowed because it is part of the user experience.
  • Use ordinary clicks, typing, keyboard navigation, and visible menus. Never call internal endpoints, inject application state, edit storage, or mutate the DOM to manufacture a result.
  • Use browser evaluation only to read the rendered page or activate the same visible control when normal browser references fail.
  • Use a recognizable test prefix such as qa_<feature>_<purpose> and record every artifact created.
  • Do not enter credentials. If authentication is required, ask the developer to provide an authenticated browser session.
  • Treat production or unclear environments as read-only until the developer explicitly allows mutations.
  • Continue past isolated failures when another path remains testable. Do not repair the application during the review.

3. Exercise the scoped journey

Discover available surfaces from the UI itself. For every page or workflow in scope, test the applicable path end to end:

  1. Open it through normal navigation and, when useful, its direct URL.
  2. Check loading, empty, populated, and unsupported states that naturally occur.
  3. Create a safe representative object or record. Cover meaningful subtypes when one form creates materially different objects.
  4. Exercise required-field validation and one realistic database or server error that is safe to trigger, such as a duplicate name or a wrong type. Never run a destructive statement against shared cloud databases.
  5. Verify success feedback, count, list row, displayed values, search, filters, and refresh persistence.
  6. Open the created item and verify the detail or edit view reflects what was submitted.
  7. Test visible lifecycle actions such as edit, enable or disable, revoke, and delete when offered.
  8. Check labels, instructions, default values, disabled and loading states, focus, keyboard use, and accessible names while following the journey.

Use the smallest starter state that unlocks the workflow. If one created table or record supports several tests, reuse it.

A page is complete when every applicable step above has either been observed or recorded as untestable with the visible reason.

Show full SKILL.md (238 more words)Show less

4. Evidence rules

  • Report only what was observed through the UI. A browser console error seen during the journey can support a finding. Label it as console evidence and do not guess the cause from it.
  • Before reporting that a control does not respond or an animation is stuck, rule out the user's-Chrome traps in monorepo.md: a hidden tab, or a dev-server reload.
  • A gap that domain.md or the docs describe as deliberate is not a finding.
  • Quote exact labels and errors when they identify the problem.
  • Separate defects, missing capabilities, intentional unsupported states, and untested paths.
  • Do not infer implementation causes.
  • Do not label a database-native limitation as an application defect. State the visible limitation and its effect.
  • Preserve useful test artifacts unless cleanup was requested. Always list the qa_* artifacts left behind, and name any that cannot be removed through the UI.
  • Restore any UI preferences you changed, such as pane sizes, close the MCP tab, and ask the developer to reload their own tab.

5. Report

Return a concise report with:

Tested

List the environment, role, pages, workflows, and objects created.

Working

List completed user journeys without narrating every click.

Missing or broken

For each finding include:

  • page or workflow;
  • short reproduction path;
  • observed result;
  • expected user-facing result or practical impact.

Order findings by how strongly they block the journey.

Untested and cleanup

List blocked paths, their visible blockers, and any test artifacts left behind.

© wannabespace, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/user-behavior-qa of wannabespace/conar.

Open the folder on GitHubat commit 53c9289

Compare with similar skills

User Behavior QA 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.

User Behavior QA compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
User Behavior QA this skillwannabespace/conar1.5k—~1.4kAutomated safety check: PassAGPL-3.0
Verify Bbget-bb/bb4.2k—~3.2kAutomated safety check: PassMIT
Plugin TestNanmiCoder/dsh-auto-mode1651 repos~2.9kAutomated safety check: PassMIT
Run Smoke Teststamdogood/builder-essential-skills219—~1.9kAutomated safety check: PassMIT
Solution Testingkid-sid/claude-spellbook189—~3.9kAutomated safety check: PassMIT
Triage IssuesClickHouse/clickhouse-java1.6k—~904Automated safety check: PassApache-2.0

Similar skills

  • Verify Bb

    get-bb/bb

    Verify BB user journeys in an isolated source dev app using dev-browser@next and the matching source CLI.

    4.2k GitHub stars~3.2k tokensUpdated today
    Testing & QAAuto-check passed
  • Plugin Test

    NanmiCoder/dsh-auto-mode

    A skill your agent uses when writing or reviewing tests for DeepSeek Harness plugins, external DSH plugin packages, or package changes in the deepseek-harness repository.

    165 GitHub starsUsed in 1 repo~2.9k tokens
    Testing & QAAuto-check passed
  • Run Smoke Tests

    tamdogood/builder-essential-skills

    Inspect an unfamiliar repository, interpret a broad Markdown user journey at runtime, operate the real product through its supported web, API, CLI, desktop, or mobile surface, and produce an…

    219 GitHub stars~1.9k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed
  • Solution Testing

    kid-sid/claude-spellbook

    A skill your agent uses when writing Playwright E2E tests for critical user journeys, setting up post-deployment smoke tests, debugging flaky browser automation, or implementing BDD feature files…

    189 GitHub stars~3.9k tokensUpdated 2 mo ago
    Testing & QAAuto-check passed
  • Triage Issues

    ClickHouse/clickhouse-java

    Analyzes a single GitHub issue at a time. An agent skill from ClickHouse/clickhouse-java.

    1.6k GitHub stars~904 tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Dogfood Exploratory QA

    vercel-labs/agent-browser

    Official

    Explores a web app with the agent-browser CLI to find bugs and UX problems, then writes a report with screenshots, repro videos and step-by-step reproduction for each issue.

    44k GitHub starsUsed in 8 repos~2.7k tokens
    Testing & QAAuto-check passed

More from wannabespace/conar

  • Cleanup

    wannabespace/conar

    Review the current branch's diff against its base (tamery, else main), then shrink it — delete code that carries no logic, split files that hold more than one subject, make new code look like the…

    1.5k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • PR Triage

    wannabespace/conar

    Speed up a GitHub PR review — sort every changed file into trivial / skim / review, mark the trivial ones as viewed on GitHub, and hand back a reading order for the rest.

    1.5k GitHub stars~811 tokensUpdated yesterday
    Auto-check passed
  • Tamery UI

    wannabespace/conar

    Tamery's UI design system and hard rules — native macOS look, three-level color system, typography tokens, motion recipes, and the kit's known gotchas.

    1.5k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

Questions about User Behavior QA

What does User Behavior QA do?

Test the running app through its visible browser UI as a real user. User Behavior QA is an agent skill from wannabespace/conar. Test the running app through its visible browser UI as a real user.

When should I use User Behavior QA?

User Behavior QA fits situations like: A developer asks for QA; user journey testing; click through a feature; test it like a user.

How do I install User Behavior QA in Claude Code?

Run `npx skills add wannabespace/conar --skill user-behavior-qa -a claude-code`. Or copy the skill folder (.agents/skills/user-behavior-qa in wannabespace/conar) into .claude/skills/user-behavior-qa in your project. Claude Code loads it when a task matches its description.

How do I install User Behavior QA in Codex?

Run `npx skills add wannabespace/conar --skill user-behavior-qa -a codex`. Or copy the skill folder (.agents/skills/user-behavior-qa in wannabespace/conar) into .agents/skills/user-behavior-qa in your project. Codex loads it when a task matches its description.

Can I use User Behavior QA 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 wannabespace/conar --skill user-behavior-qa -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/user-behavior-qa, .gemini/skills/user-behavior-qa, .github/skills/user-behavior-qa and .opencode/skills/user-behavior-qa in your project.

What does User Behavior QA need to run?

SKILL.md names no scripts, command-line tools or credentials: User Behavior QA is instructions for the agent only.

Does User Behavior QA access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is User Behavior QA 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 User Behavior QA use?

User Behavior QA is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does User Behavior QA use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to User Behavior QA?

Skills that share tags, products or a category with User Behavior QA: Verify Bb (get-bb/bb, 4.2k stars), Plugin Test (NanmiCoder/dsh-auto-mode, 165 stars), Run Smoke Tests (tamdogood/builder-essential-skills, 219 stars) and Solution Testing (kid-sid/claude-spellbook, 189 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains User Behavior QA?

wannabespace (a GitHub organization) maintains it in wannabespace/conar, which has 1,452 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 7, 2026.

Source: wannabespace/conar on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.