ci-e2e-debug
Download and inspect CI e2e test logs from GitHub Actions artifacts. Use when investigating e2e test failures in CI.
67
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid, focused description that clearly communicates both what the skill does and when to use it. The trigger terms are natural and the scope is narrow enough to avoid conflicts. The main weakness is that the specific capabilities beyond 'download and inspect' could be more detailed.
Suggestions
Expand the specific actions beyond 'download and inspect' — e.g., 'Download CI e2e test logs from GitHub Actions artifacts, parse error messages, identify failing test cases, and surface root causes.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (CI e2e test logs, GitHub Actions artifacts) and two actions (download and inspect), but doesn't elaborate on what 'inspect' entails or list more specific capabilities like parsing errors, identifying flaky tests, etc. | 2 / 3 |
Completeness | Clearly answers both what ('Download and inspect CI e2e test logs from GitHub Actions artifacts') and when ('Use when investigating e2e test failures in CI') with an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'CI', 'e2e test', 'test logs', 'GitHub Actions', 'artifacts', 'test failures' — these are terms a user would naturally use when dealing with failing CI tests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific niche — CI e2e test logs from GitHub Actions artifacts is a very distinct domain unlikely to conflict with other skills. The combination of GitHub Actions, artifacts, and e2e test logs creates a clear, narrow scope. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill for debugging CI e2e test failures. Its main strengths are concrete, executable commands and valuable domain-specific knowledge in the Notes section (especially the profile exporter gotcha). The main weakness is the lack of validation checkpoints in the workflow — e.g., verifying the download succeeded or handling cases where no artifacts exist.
Suggestions
Add a validation step after downloading the artifact (e.g., check file size or unzip exit code) to catch download failures early.
Add a brief error-handling note for when no artifacts are found for a given run ID (common scenario worth addressing).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with concrete commands, but the Notes section includes some explanatory context that could be tightened. The profile exporter note is valuable domain knowledge but slightly verbose. Overall reasonable but not maximally lean. | 2 / 3 |
Actionability | Provides fully executable bash commands with specific gh API endpoints, jq filters, grep patterns, and find commands. Each step is copy-paste ready with clear placeholders for variable values like RUN_ID and ARTIFACT_ID. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced (find artifact → download → inspect → report), but there are no validation checkpoints or error recovery steps. For example, no check that the zip downloaded successfully, no handling of missing artifacts, and no verification that extraction succeeded. | 2 / 3 |
Progressive Disclosure | For a single-purpose skill under 50 lines with no bundle files, the content is well-organized with clear sections (Steps and Notes). The structure is appropriate for the scope — no need for external references given the focused nature of the task. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- apache/skywalking
- Commit
bf0fe4b
- 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.