CtrlK
BlogDocsLog inGet started
Tessl Logo

ci-e2e-debug

Download and inspect CI e2e test logs from GitHub Actions artifacts. Use when investigating e2e test failures in CI.

68

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

An efficient, highly actionable debugging skill: real commands, a sensible sequence, and genuinely expert Notes that anticipate the non-obvious failure modes (mock-provider exporter crashes masquerading as clean OAP logs). Adding a post-download validation checkpoint and making steps 3–4 fully concrete would lift it further.

DimensionReasoningScore

Conciseness

The body is lean and command-driven with zero padding — it never explains what GitHub Actions or grep are. The Notes section carries only non-obvious project knowledge (e.g. the profile-exporter subprocess failing independently of a healthy OAP), so every token earns its place. Anchor 5.

5 / 5

Actionability

Steps 1–3 give copy-paste-ready `gh api`, `unzip`, `find`, and `grep` commands, but step 3 leaves `<log_file>` as an unfilled placeholder and step 4 ("Check BanyanDB, UI, and other pod logs as needed") is only a high-level hint. Mostly executable with minor gaps — anchor 4, not 5.

4 / 5

Workflow Clarity

A clear five-step sequence with implicit verification (grepping error signatures) and an explicit error-recovery branch ("When OAP logs are clean but tests fail: look at which specific test step failed"). Missing an explicit checkpoint that the artifact download/unzip succeeded or that the artifact list was non-empty, so it fits anchor 4 rather than 5. The destructive/batch cap does not apply: this is a read-only inspection workflow, and the only `rm -rf` clears a /tmp scratch directory.

4 / 5

Progressive Disclosure

A 44-line, single-purpose skill with no need for external references: the body has well-organized Steps and Notes sections and no bundle files exist, so there are no dangling references to verify. Per the simple-skill guideline this is anchor 5.

5 / 5

Total

18

/

20

Passed

Description

82%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 strong description: concrete, correctly voiced, with an explicit and well-matched 'Use when' clause. The only weakness is breadth — it names just two actions and doesn't hint at the multi-component log triage or root-cause reporting the skill actually performs.

Suggestions

Add one or two more concrete actions to the what-clause, e.g. "Download and inspect CI e2e test logs (OAP, BanyanDB, UI) from GitHub Actions artifacts and summarize the root cause".

Include a couple of natural trigger variants users might say, such as "failed e2e tests" or "CI test failures", to widen keyword coverage.

DimensionReasoningScore

Specificity

"Download and inspect CI e2e test logs from GitHub Actions artifacts" names the domain plus exactly two concrete actions, but omits the root-cause reporting step and which components' logs to inspect. This matches anchor 3 (domain and 1-2 concrete actions, not comprehensive) rather than 4, which requires several specific actions with only minor gaps.

3 / 5

Completeness

It explicitly 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 concrete trigger phrases, matching the anchor-5 example structure. Voice is third-person imperative, so no person-voice penalty applies.

5 / 5

Trigger Term Quality

"CI e2e test logs", "GitHub Actions artifacts", "e2e test failures in CI", and "CI" are phrases a developer would naturally say when a pipeline breaks. Not 5 because common variants like "failed tests", "flaky tests", "test logs", or "workflow run" are missing.

4 / 5

Distinctiveness Conflict Risk

The niche is narrow — triaging e2e failures specifically via GitHub Actions run artifacts — with triggers unlikely to fire for general GitHub, log-reading, or test-writing skills. Minimal conflict risk, matching anchor 5.

5 / 5

Total

17

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
apache/skywalking
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.