CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

moai-e2e

Create and run E2E tests across web, mobile, and desktop with auto-detection and CLI-first toolchains

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/moai-e2e/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-5

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

The skill body is a minimal delegation stub: maximally lean, but it provides no substance of its own. It forwards an 'e2e' invocation to an external skill that is not present in the bundle, with no argument examples, error handling, or fallback guidance, so its value is entirely contingent on the referenced skill.

Suggestions

Add 2-3 concrete examples of valid e2e arguments (e.g., 'e2e --target web', 'e2e --detect') so the $ARGUMENTS placeholder is actionable without the reader inspecting the moai skill.

Add a brief fallback instruction for when Skill("moai") is unavailable or the invocation fails (e.g., how to run E2E tests directly via the CLI-first toolchain mentioned in the description).

Add one or two sentences describing what the delegation returns and what to do with the result (reports, failing tests, next steps) so the post-invocation workflow is not entirely implicit.

DimensionReasoningScore

Conciseness

The entire body is a single line — 'Use Skill("moai") with arguments: e2e $ARGUMENTS' — with zero padding, no over-explanation of concepts Claude already knows, and every token earning its place. This matches the anchor 'Lean and efficient; assumes Claude's competence'.

5 / 5

Actionability

The line is a concrete, syntactically complete delegation command, but it is missing key details: it depends entirely on an external Skill("moai") that is not part of this bundle, and '$ARGUMENTS' is an unexpanded placeholder with no examples of valid e2e arguments. This sits between anchor 2 (minimal concrete guidance) and anchor 4 (mostly executable guidance).

3 / 5

Workflow Clarity

The single delegation action is unambiguous in form, but there are no checkpoints, no error handling, and no guidance for what to do if the moai skill is unavailable or the invocation fails. It fits anchor 3 ('sequence present but checkpoints missing or implicit') rather than a 5, because the post-invocation workflow is entirely unspecified.

3 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and the one-line body means nothing is inlined that should be separate, but the only reference in the body — Skill("moai") — is unresolvable within this bundle, and there is no signposted structure or navigation. This fits anchor 3 ('references present but not clearly signaled') better than anchor 4.

3 / 5

Total

14

/

20

Passed

Description

53%Weight 40%Scale 1-5

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 states a clear, third-person 'what' with a distinct E2E-testing niche, but it omits any 'when to use' guidance and lacks natural trigger variations such as 'end-to-end' or tool names. It is serviceable but sits at the midpoint of the rubric rather than exemplifying it.

Suggestions

Append an explicit trigger clause, e.g., 'Use when the user asks for end-to-end, E2E, or UI tests, or mentions Playwright, Cypress, or Appium.'

Spell out 'end-to-end' alongside 'E2E' and add common synonyms users naturally say (e.g., 'browser tests', 'UI tests') to improve trigger term coverage.

Replace the attribute phrase 'with auto-detection and CLI-first toolchains' with one more concrete action (e.g., 'auto-detects the project's test framework and generates runner configs') to strengthen specificity.

DimensionReasoningScore

Specificity

'Create and run E2E tests' names the domain plus two concrete actions, but 'with auto-detection and CLI-first toolchains' describes attributes rather than additional actions, so coverage is not comprehensive. This matches anchor 3 ('names domain and 1-2 concrete actions') rather than anchor 4 ('lists several specific actions').

3 / 5

Completeness

The 'what' is clear (create and run E2E tests across three platforms), but there is no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3, matching anchor 3 ('clear what but when is missing or only weakly implied').

3 / 5

Trigger Term Quality

'E2E tests', 'web', 'mobile', and 'desktop' are relevant keywords a user might say, but common natural variations are missing — 'end-to-end', 'UI tests', 'browser tests', and tool names like Playwright/Cypress/Appium. This matches anchor 3 ('some relevant keywords but missing common variations or synonyms').

3 / 5

Distinctiveness Conflict Risk

The E2E-testing niche scoped across web, mobile, and desktop with auto-detection is mostly distinct, with only minor overlap risk against generic testing skills or tool-specific skills (e.g., a Playwright skill). This fits anchor 4 ('mostly distinct; minor overlap risk') better than anchor 5, which would require explicit distinct trigger phrases.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

modu-ai/moai-adk

Path

.agents/skills/moai-e2e/SKILL.md

Reviewed

Table of Contents

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.