Skip to content
Agentmart
Submit a tool

business-rule-e2e

Design, implement, run, diagnose, and refresh business-rule-driven end-to-end tests for web and React Native projects.

Skill by deepaktiwari09

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/deepaktiwari09-business-rule-e2e

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Design, implement, run, diagnose, and refresh business-rule-driven end-to-end tests for web and React Native projects. Use for requests to test a business rule, module, user role/persona journey, UI-to-API flow, Playwright headless web flow, Detox headless mobile flow, E2E coverage audit, flaky E2E repair, or business-rule test refresh. Organize coverage as atomic rules, molecular module scenarios, and full persona flows with traceability to project business documentation.

Use cases: design, frontend, backend, testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/business-rule-e2e

What's inside

Skill name
business-rule-e2e
Description
Design, implement, run, diagnose, and refresh business-rule-driven end-to-end tests for web and React Native projects. Use for requests to test a business rule, module, user role/persona journey, UI-to-API flow, Playwright headless web flow, Detox headless mobile flow, E2E coverage audit, flaky E2E repair, or business-rule test refresh. Organize coverage as atomic rules, molecular module scenarios, and full persona flows with traceability to project business documentation.
License
MIT
Instructions
90 lines in SKILL.md · view on GitHub

Files (6)

  • SKILL.md
  • openai.yaml · agents/
  • detox.md · references/
  • playwright.md · references/
  • refresh.md · references/
  • test-model.md · references/

SKILL.md (first lines)

# Business Rule E2E

Build confidence from business intent outward. Treat UI actions, API effects, persisted state, authorization, and user-visible outcomes as one flow.

## Start

1. Read repository instructions completely.
2. Inspect package manifests, E2E configuration, existing tests, app routes/screens, API clients/routes, fixtures, and `docs/` business rules.
3. Read [references/test-model.md](references/test-model.md).
4. Select platform:
   - Web: read [references/playwright.md](references/playwright.md).
   - React Native: read [references/detox.md](references/detox.md).
   - Mixed project: read both; keep suites separate and share rule IDs.
5. Determine request scope: one rule, module, persona, or refresh.
6. If business intent is missing or contradictory, stop and ask the product decision needed. Never encode guessed business policy.

## Establish traceability

Before broad changes, report concisely:

- Problem/request
- Proposed test layers and flow
- Affected files
- Fixtures/data/environment needed
- Tradeoffs or team decision needed

Assign stable IDs such as `BR-BILLING-001`. Connect each rule to:

```text
Business rule -> atomic tests -> module scenarios -> persona flows -> evidence
```

Prefer existing project identifiers. Otherwise create a documented convention. Maintain business logic under `docs/`; default to `docs/testing/e2e/` when no project convention exists.

## Scope modes

### One business rule

Test the rule's complete observable lifecycle, not only its happy-path screen:

1. Arrange valid role, preconditions, and data through API/fixture when possible.
2. Trigger the rule through the user-facing UI.
3. Observe the relevant request/response when useful.
4. Assert visible outcome.
5. Verify durable state through API, DB-safe helper, or a second UI view.
6. Cover denial, boundary, and state-transition cases relevant to that rule.

### One module

Inventory module rules and states. Implement atomic coverage first, then molecular scenarios spanning related rules. Include role permissions, validation, lifecycle transitions, error recovery, and module boundary integrations.

### One user type

Map the persona from entry to terminal outcome: authentication, navigation, permitted actions, forbidden actions, cross-module handoffs, persistence, logout/session expiry where relevant. Use a few high-value journeys; do not duplicate every atomic case.

### Refresh

Read [references/refresh.md](references/refresh.md), then reconcile business docs, code, tests, and coverage. Refresh means update stale coverage and evidence, not blindly rewrite passing tests.

## Implement safely

- Reuse existing framework/configuration before adding dependencies.
- Ask before decisions affecting architecture, APIs, data models, UI flows, CI/deployment, QA ownership, or another teammate.
- Prefer accessibility locators and stable `testID`s; avoid CSS/layout coupling.
- Use API setup for speed; exercise UI for behavior under test.
- Keep tests isolated, deterministic, parallel-safe, and independently runnable.
- Never use production data or production mutation paths.
- Never log secrets, tokens, passwords, or PII.
- Add dev-only structured diagnostics when implementation adds or changes application behavior; follow repository logging rules.
- Do not weaken assertions, add arbitrary sleeps, or disable synchronization to make a test pass.
- Preserve user changes and avoid broad refactors.

## Verify

Run smallest scope first, then relevant module/flow suite. Use one worker initially while diagnosing. Capture:

- Command and environment
- Passed/failed/skipped counts
- Duration
- Trace/screenshots/video/logs on failure
- Rule IDs covered
- Remaining gaps and risk

Classify failures as product defect, test defect, environment defect, or unclear rule. Fix only within requested authority.

## Finish

Report what changed, why, verification evidence, risk, and team confirmation still needed. Update the coverage artifact and business-rule docs. Keep handoff concise and QA-friendly with exact reproduction commands.

From deepaktiwari09/team-agent-skills, MIT.

More from deepaktiwari09/team-agent-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 10, 2026 (2 months ago)
Last release
Aug 10, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from deepaktiwari09

Cite this page

business-rule-e2e skill. Agent Mart. https://agentmart.dev/skills/deepaktiwari09-business-rule-e2e (last updated 2026-10-24)