run-e2e

Run SkyWalking E2E tests locally

1.58x

Quality

59%

Does it follow best practices?

Impact

79%

1.58x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

78%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.

The body is a high-quality, deeply actionable runbook: executable commands, explicit validation/recovery loops, and concrete triage procedures. It loses points only on conciseness (dense prose in the traps section) and progressive disclosure (large reference-style sections inlined rather than split into bundle files), both of which are efficiency rather than correctness issues.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (e.g. terse bash snippets, no padding about what Go or docker is), but several sections are dense with hard-won 'learned the hard way' prose (steps 6, 7, 9) that could be tightened; it fits the 'Mostly efficient but includes some unnecessary explanation or could be tightened' anchor rather than the lean 4.	3 / 5
Actionability	Nearly every step ships copy-paste-ready bash (find -newer rebuild checks, e2e run/verify/cleanup, swctl queries with port discovery, docker rm -f) plus concrete tables of broken-vs-working flag forms; the guidance is fully executable and covers common cases, matching the score-5 anchor.	5 / 5
Workflow Clarity	The 9-step workflow is explicitly sequenced with validation/recovery checkpoints: rebuild detection (step 2), user-confirmed rebuild (step 3), separate debug-then-cleanup ordering (step 5), manual verify triage before editing (step 6), and expected-file iteration against live containers (step 8), matching the 'Clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	5 / 5
Progressive Disclosure	Structure is good with well-labeled sections and inline pointers to real external locations (test/e2e-v2/CLAUDE.md, .github/workflows/, test/e2e-v2/script/...); however no bundle files exist and the body inlines substantial reference-style material (the full trap catalog in step 9, tool install tables) that could live in separate files, so it is above the 3 anchor but not fully one-level-deep at 5.	4 / 5
	Total	17 / 20 Passed

Description

40%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 accurate and project-specific but terse: it states the what without a 'Use when...' clause and without enumerating concrete capabilities or trigger synonyms. Per the rubric's missing-trigger cap, completeness is held to 2 and specificity to 2 for minimal concrete actions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to run or debug SkyWalking E2E test cases locally, mentions e2e.yaml or e2e-v2, or asks to reproduce a CI E2E failure.'

Enumerate concrete actions to lift specificity, e.g. 'Run an E2E case, rebuild OAP/test services when sources changed, and triage failing verify queries against the live OAP.'

Include natural synonyms and file cues (e2e.yaml, e2e-v2, swctl, verify cases) so users' phrasings match the description.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Run SkyWalking E2E tests locally') but states only a single high-level action with no concrete sub-actions or tools enumerated, matching the 'Names the domain but actions are minimal or generic' anchor; it is below the score-3 anchor which requires 1-2 concrete actions.	2 / 5
Completeness	It gives a clear 'what' (run SkyWalking E2E tests locally) but has no explicit 'Use when...' trigger clause and only a weak argument-hint in frontmatter; the judging guidelines cap completeness at 3 when trigger guidance is missing, and the absence of any 'when' phrasing places it at the 'Has a vague what and no when' boundary at 2.	2 / 5
Trigger Term Quality	It includes the natural term 'E2E tests' plus the recognizable product keyword 'SkyWalking', but lacks synonyms or file/extension cues (e.g. 'e2e.yaml', 'e2e-v2', 'verify cases') that a user might actually say, fitting the 'Some relevant keywords but missing common variations or synonyms' anchor.	3 / 5
Distinctiveness Conflict Risk	'SkyWalking E2E tests' carves a clear niche tied to a specific project's E2E harness, with only minor overlap risk against generic test-running skills, matching the 'Mostly distinct; minor overlap risk' anchor; it is not a 5 because the description omits distinguishing trigger phrases that would fully separate it.	4 / 5
	Total	11 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: apache/skywalking
Path: .claude/skills/run-e2e/SKILL.md
Commit: 521b2ab

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.