bmad-qa-generate-e2e-tests

Generate end to end automated tests for existing features. Use when the user says "create qa automated tests for [feature]"

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./src/bmm-skills/4-implementation/bmad-qa-generate-e2e-tests/SKILL.md

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content delivers a clear, sequenced workflow with a working test-run feedback loop, but it stops short of providing executable test templates and contains a broken checklist reference that undermines its progressive-disclosure structure.

Suggestions

Include a concrete, copy-paste-ready test file template (e.g. a Playwright/Jest spec skeleton) so generated tests are executable rather than described.

Either add the missing checklist.md bundle file referenced by 'Validate against ./checklist.md' or remove the dangling reference.

Trim the 'Keep It Simple' Do/Avoid section, which largely restates the Execution-step guidance, to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly directive and avoids explaining basic concepts, but the 'Keep It Simple' Do/Avoid section reiterates guidance already implied by the Execution steps, so it could be tightened.	2 / 3
Actionability	Concrete guidance exists (status codes 200/400/404/500, semantic locators, specific resolver commands, output paths), but no executable test-code template is provided — the test-generation instructions describe what to test rather than giving copy-paste-ready examples.	2 / 3
Workflow Clarity	Steps 0–5 plus activation steps are explicitly sequenced, and Step 4 provides a validate→fix feedback loop ('Execute tests to verify they pass. If failures occur, fix them immediately.'), matching the level-3 anchor.	3 / 3
Progressive Disclosure	The skill is a single well-sectioned file with no bundle directories present, but the 'Validate against ./checklist.md' reference points to a file that does not exist in the bundle, leaving a broken, unclearly-signaled reference.	2 / 3
	Total	9 / 12 Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description cleanly answers both what the skill does and when to invoke it via an explicit trigger, but it captures only one action and one trigger phrasing, leaving it narrower than the strongest examples.

Suggestions

List the concrete test types the skill produces (e.g. API status-code tests, E2E workflow tests, test-summary reports) to raise specificity.

Broaden trigger coverage with natural variations such as 'write automated tests', 'add test coverage for [feature]', or 'automate testing for [feature]'.

Dimension	Reasoning	Score
Specificity	Quotes 'Generate end to end automated tests for existing features' — a single concrete action in the testing domain, but not the multiple distinct actions (e.g. API tests, E2E tests, coverage analysis) that would warrant a 3.	2 / 3
Completeness	Explicitly answers what ('Generate end to end automated tests for existing features') and when ('Use when the user says ...') with an explicit trigger clause, matching the level-3 anchor.	3 / 3
Trigger Term Quality	Quotes 'Use when the user says "create qa automated tests for [feature]"' — one natural phrasing is provided, but coverage of common variations (e.g. 'write tests', 'add test coverage', 'automate testing') is missing.	2 / 3
Distinctiveness Conflict Risk	The QA test-generation niche is reasonably specific, but the single trigger phrasing could still overlap with general testing or code-review skills rather than being unmistakably distinct.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: bmad-code-org/BMAD-METHOD
Path: src/bmm-skills/4-implementation/bmad-qa-generate-e2e-tests/SKILL.md
Commit: bb45db4

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.