CtrlK
BlogDocsLog inGet started
Tessl Logo

e2e-tests

Run, monitor, and fix frontend Cypress E2E tests. Handles local execution, CI monitoring, failure diagnosis, flaky test detection, and accessibility regression checks. Use this skill whenever the user mentions Cypress, E2E tests, end-to-end tests, test failures, CI failures, "CI is red", flaky tests, accessibility testing, or wants to run/debug/fix any frontend integration test — even if they don't say "e2e" explicitly.

75

Quality

94%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A strong, highly actionable skill body: every workflow ships executable commands, pre-flight checks, and verification loops, and it avoids generic Cypress tutorials entirely. The main weaknesses are mild redundancy (the gh pre-flight block repeated three times, Important Notes restating the config table) and an all-inline structure that keeps reference material in SKILL.md rather than in bundle files.

Suggestions

State the gh pre-flight check once (e.g., in a shared 'Pre-flight' section referenced by the monitor/fix/flaky workflows) instead of repeating the identical 3-line block verbatim in three sections.

Move the Custom Cypress Commands listing and the Local vs CI Configuration Differences table into a references/ file linked from the body, keeping only the commands needed per workflow inline.

Trim 'Important Notes' of facts already covered by the config table (retry counts, timeout differences) and keep only genuinely new guidance there.

DimensionReasoningScore

Conciseness

Nearly every token is project-specific operational detail with no time wasted explaining concepts Claude already knows, but there is verifiable padding: the identical 3-line 'gh' pre-flight check block is repeated verbatim three times (monitor, fix, flaky sections), and 'Important Notes' restates retry counts already shown in the Local vs CI table. This fits 'efficient; minor instances of over-explanation that could be trimmed' rather than the lean level-5 anchor.

4 / 5

Actionability

Commands are fully executable and copy-paste ready: exact docker/gh invocations with jq filters ('gh run view "$RUN_ID" --json jobs | jq -r ...'), the a11y gate invocation with env var and explicit spec list, and a concrete failure-category taxonomy (selector changed, timing, data dependency, API change, new behavior). Common cases are covered with runnable code, matching the top anchor.

5 / 5

Workflow Clarity

The 7-step fix flow is clearly sequenced with explicit validation checkpoints: pre-flight service/gh checks before any action, 'Step 7: Verify the fix locally' as a re-run loop, and explicit error-recovery branches (services down → suggest 'docker compose up --build -d'; gh unavailable → stop and tell the user). This matches the anchor requiring explicit validation steps and feedback loops.

5 / 5

Progressive Disclosure

The body is well-sectioned with clear headers and easy navigation, and no bundle files exist to split content into, so structure rests on SKILL.md alone. However, the ~330-line body inlines reference-style material — the full Custom Cypress Commands API listing, the Local vs CI config table, and the Key File Locations index — that would sit better in separate reference files; this is the level-4 'good structure, minor organization gaps' fit rather than the fully split level-5 pattern.

4 / 5

Total

18

/

20

Passed

Description

100%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.

An exemplary description: third-person voice, comprehensive and concrete capability list, explicit 'Use this skill whenever...' trigger clause with natural synonyms and colloquialisms ('CI is red'), and a tightly bounded niche. All four dimensions sit at the top anchor.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete, distinct actions — 'Run, monitor, and fix frontend Cypress E2E tests. Handles local execution, CI monitoring, failure diagnosis, flaky test detection, and accessibility regression checks' — giving comprehensive coverage of the skill's capabilities, matching the level-5 anchor rather than the level-4 'minor gaps' anchor.

5 / 5

Completeness

It explicitly answers both questions: the first two sentences state what the skill does, and 'Use this skill whenever the user mentions...' provides an explicit when-clause with concrete trigger phrases — the pattern of the level-5 exemplar. It is not the level-4 case, where the 'when' could be more specific.

5 / 5

Trigger Term Quality

Trigger terms are natural user phrasings with synonym coverage: 'Cypress, E2E tests, end-to-end tests, test failures, CI failures, "CI is red", flaky tests, accessibility testing, frontend integration test'. The colloquial 'CI is red' and the explicit note that triggering works 'even if they don't say "e2e" explicitly' match the comprehensive-synonyms level-5 anchor.

5 / 5

Distinctiveness Conflict Risk

A clear Cypress/frontend-E2E niche with distinct, well-scoped triggers; overlap risk with generic testing or CI skills is minimal. The clause 'or wants to run/debug/fix any frontend integration test' broadens scope slightly, but it is explicitly bounded to frontend integration tests and does not create meaningful conflict with other skill descriptions.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
HHS/OPRE-OPS
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.