write-e2e
Write E2E tests for the Datadog Agent using the new-e2e framework with fakeintake assertions
54
62%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/write-e2e/SKILL.mdQuality
Discovery
40%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 targets a very specific niche (Datadog Agent E2E testing with new-e2e and fakeintake), which gives it strong distinctiveness. However, it lacks an explicit 'Use when...' clause and could benefit from listing more concrete actions and natural trigger term variations to help Claude reliably select it.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to write, update, or debug end-to-end tests for the Datadog Agent using the new-e2e testing framework.'
Include natural trigger term variations such as 'end-to-end tests', 'e2e testing', 'fake intake', 'test assertions', and 'datadog-agent tests'.
List more specific actions beyond just 'write tests', e.g., 'Sets up test environments, writes fakeintake assertions to validate telemetry data, configures new-e2e test suites for Datadog Agent components.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (E2E tests for Datadog Agent) and a key action (write tests), and mentions specific tools (new-e2e framework, fakeintake assertions), but doesn't list multiple concrete actions beyond 'write E2E tests'. | 2 / 3 |
Completeness | Describes what it does (write E2E tests using new-e2e framework with fakeintake assertions) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric should cap completeness at 2, and the 'what' is also fairly thin, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes relevant domain-specific keywords like 'E2E tests', 'Datadog Agent', 'new-e2e framework', and 'fakeintake', which are terms a user in this domain would use. However, it misses common variations like 'end-to-end', 'integration test', 'test writing', or 'fake intake'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific to the Datadog Agent's new-e2e framework with fakeintake assertions — this is a very narrow niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that efficiently serves as a navigation hub and workflow guide for writing E2E tests. Its strengths are excellent progressive disclosure via the lookup table and a clear validation-rich checklist. The main weakness is the lack of any inline code example showing what a minimal test looks like, which means Claude must read multiple referenced files before it can write anything — reducing immediate actionability.
Suggestions
Add a minimal inline Go test skeleton (10-15 lines) showing the basic structure with environment setup, agent provisioning, and a fakeintake assertion, so Claude can start writing immediately before diving into referenced docs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose. No unnecessary explanations of what E2E testing is or how Go works. The lookup table is an efficient way to convey many pointers. Assumes Claude's competence throughout. | 3 / 3 |
Actionability | Provides concrete commands for compilation (`go vet`), running tests (`dda inv new-e2e-tests.run`), and CI checking (`grep`), but lacks executable code examples of actual test structure. The skill delegates most concrete guidance to referenced files (AGENTS.md) rather than including even a minimal test skeleton inline. | 2 / 3 |
Workflow Clarity | The checklist provides a clear 6-step sequence with explicit validation checkpoints: compile-check (step 4), run locally before pushing (step 5 with fallback to troubleshooting docs), and CI wiring verification (step 6). The feedback loop for test failures is addressed by referencing the 'Validating E2E tests' section. | 3 / 3 |
Progressive Disclosure | Excellent use of a lookup table for one-level-deep references to framework API, fakeintake API, examples, real tests, and CI configuration. Content is appropriately split — the SKILL.md serves as a concise overview and navigation hub pointing to detailed materials. However, since no bundle files were provided, we cannot verify the referenced paths actually exist. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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 | 9 / 11 Passed | |
- Repository
- DataDog/datadog-agent
- Commit
a41685a
- 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.