CtrlK
BlogDocsLog inGet started
Tessl Logo

e2e

Write end-to-end tests for OpenMeter against a live server. Use when adding tests under e2e/ that exercise API endpoints over HTTP (v1 generated SDK or v3 SDK).

71

Quality

88%

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 dense, highly actionable body of e2e-specific guidance with executable examples and strong workflow feedback loops. It is long but almost every line earns its place; the main improvement would be offloading some reference-style material into bundle files.

Suggestions

Move the error-shape triage table and validation-moment details into a references/ file, keeping SKILL.md as an overview with a one-line pointer.

Tighten the per-request-timeout and async-billing-logging paragraphs to their essential rules.

Consider extracting the gotchas and SDK-union constructor notes into a references/cheatsheet to shorten the main body.

DimensionReasoningScore

Conciseness

Assumes Claude's competence throughout (no explaining what e2e testing or Kafka is) and every section carries non-obvious domain value; a few prose blocks (per-request timeout, async billing logging) could be trimmed without loss.

4 / 5

Actionability

Copy-paste ready Go test examples, concrete shell commands, and named helpers (initClient, newV3Client, validPlanRequest, requireProblem) cover the common cases exhaustively.

5 / 5

Workflow Clarity

Multi-step flows are explicitly sequenced with validation checkpoints and feedback loops, e.g. the error-shape triage ('write the test, run it once, inspect the raw problem, then pick the helper') and the create→GET→publish validation-moment guidance.

5 / 5

Progressive Disclosure

Well-organized single file with clear sections and one-level-deep pointers to real repo files (e2e_test.go, AGENTS.md, api/v3/client); no nested skill references, though the ~290-line body could plausibly split some reference material (error-shape triage, gotchas) into bundle files.

4 / 5

Total

18

/

20

Passed

Description

87%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.

A tight, third-person description that clearly states what the skill does and when to invoke it, with concrete triggers and a well-scoped niche. Slight room to surface more natural synonyms, but strong overall.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Write end-to-end tests', 'exercise API endpoints over HTTP') plus two SDK variants (v1 generated SDK, v3 SDK), with only minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what ('Write end-to-end tests for OpenMeter against a live server') and when ('Use when adding tests under e2e/ that exercise API endpoints over HTTP') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural terms a user would say ('end-to-end tests', 'e2e/', 'API endpoints over HTTP') alongside the SDK qualifiers; a few common synonyms (e.g. 'e2e tests') are implicit rather than explicit.

4 / 5

Distinctiveness Conflict Risk

A clear niche (OpenMeter e2e tests under e2e/ over HTTP with specific SDKs) with distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

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

Warning

Total

15

/

16

Passed

Repository
openmeterio/openmeter
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.