CtrlK
BlogDocsLog inGet started
Tessl Logo

run-e2e

Run SkyWalking E2E tests locally

76

1.58x
Quality

71%

Does it follow best practices?

Impact

79%

1.58x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/run-e2e/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

This is a strong, dense operational skill: executable commands dominate, the workflow is clearly sequenced with validation checkpoints and feedback loops, and the traps section encodes genuinely hard-won knowledge that Claude could not infer. Its main weakness is structure: with no bundle files, the troubleshooting and authoring material is all inlined, making the single SKILL.md long and pushing progressive disclosure down. A few verbose prose passages could also be trimmed without losing substance.

Suggestions

Move steps 6-9 (failure triage, UI template DB behavior, expected-file authoring, traps) into a references/e2e-debugging.md and keep SKILL.md as a run-first overview with clearly signaled one-level-deep pointers.

Tighten the longest prose passages (the nested-contains trap and the sim-payload discussion in step 9) into symptom/fix table rows like the swctl flag table, preserving the rules in fewer tokens.

DimensionReasoningScore

Conciseness

The body is almost entirely non-obvious operational knowledge (random port extraction, addIfNotExist semantics, template quoting traps, retry-flag pitfalls) with no padding about concepts Claude already knows. A few long prose passages — notably the nested-contains trap in step 9 — could be tightened, matching 'Efficient; minor instances of over-explanation that could be trimmed' rather than the lean anchor 5.

4 / 5

Actionability

Copy-paste-ready bash commands throughout, including exact install scripts, the docker ps port-extraction one-liner, symptom-to-fix tables for broken swctl flags, and concrete curl retry flags with set -e. Placeholders like <case-path> are inherent to repo-specific values and each is explained. Matches 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

Nine numbered steps form a clear sequence with explicit validation checkpoints (timestamp-based rebuild check, manual verify-query triage before editing), feedback loops (retry e2e verify with containers still up, iterate on the expected file without rebuilding), and confirmation gates on destructive operations (rebuild only with user confirmation; cleanup only after debugging). Matches 'Clear sequence with explicit validation steps; feedback loops for error recovery'.

5 / 5

Progressive Disclosure

There are no bundle files at all; everything — including roughly half the document of troubleshooting content (steps 6-9) that would fit naturally in a one-level-deep reference like e2e-debugging.md — is inlined in a single 230-line SKILL.md. Section headers and tables give good structure (ruling out 2), but content that should be separate is inline with no references signaled, matching anchor 3 rather than 4.

3 / 5

Total

17

/

20

Passed

Description

57%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.

The description is short, specific to the SkyWalking E2E niche, and unambiguous about what it does, but it is a bare capability statement. It lacks any trigger guidance ("Use when...") and common synonyms such as "end-to-end", which limits both completeness and trigger-term quality. Since the skill sets disable-model-invocation, the description mainly serves a human invoking it explicitly, which the missing "when" clause partly mitigates in practice.

Suggestions

Add an explicit trigger clause, e.g. "Use when asked to run, verify, or debug end-to-end tests for SkyWalking OAP, or when authoring e2e.yaml verify cases under test/e2e-v2/".

Broaden trigger vocabulary with natural synonyms and concrete artifacts users would mention: "end-to-end", "e2e tests", "e2e.yaml", "swctl verify", "test/e2e-v2".

Reflect the fuller scope of the skill body (run, triage failures, fire verify queries manually, author expected YAML) so the description covers more than the single "run" action.

DimensionReasoningScore

Specificity

"Run SkyWalking E2E tests locally" names a specific domain and one concrete action (run), but omits the verify, debug, and expected-file authoring workflows the skill actually covers. This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' — the action is concrete and the domain specific (ruling out 2), but there is no list of several specific actions (ruling out 4).

3 / 5

Completeness

The "what" is clear (run SkyWalking E2E tests locally) but a "Use when..." clause or any trigger guidance is entirely absent, which the rubric explicitly caps at 3. It is not 4 because the "when" is missing outright rather than merely imprecise.

3 / 5

Trigger Term Quality

Keywords "SkyWalking", "E2E", "tests" are relevant and natural, but common variations and synonyms are missing ("end-to-end", "integration tests", "e2e.yaml", "verify"). Fits 'Some relevant keywords but missing common variations or synonyms' rather than anchor 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

"SkyWalking E2E" is a clear niche with distinct, product-specific triggers; virtually no other skill would fire on these terms. Matches 'Clear niche with distinct triggers; minimal conflict risk'.

5 / 5

Total

14

/

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.