new-monitoring-feature

Add a new monitoring target / layer to SkyWalking OAP. Orients you to the OAL / MAL / LAL / SpanListener / SegmentListener extension points, the UI template + submodule touchpoints, the docs set that must move together, and the cross-cutting traps that don't live in any one skill.

1.10x

Quality

81%

Does it follow best practices?

Impact

88%

1.10x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

92%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 well-structured index skill: highly actionable with concrete code and commands, a clear numbered workflow with explicit validation and feedback loops, and exemplary progressive disclosure that points one level deep to sibling skills and docs. Its only weakness is moderate cross-section repetition of a few traps that could be consolidated.

Suggestions

Consolidate the repeated histogram / config-dump / client-side-OAL guidance so each trap is stated once in §9 and merely cross-referenced from §3 and §7 to trim tokens.

Consider moving the long §9 traps table into a referenced bundle file (e.g. references/traps.md) to keep SKILL.md a leaner overview, since the skill already models one-level-deep references.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence — no padding with basics Claude already knows — but several topics repeat across sections (histogram 1000x in §3.3 and the §9 traps table; config-dump drift in §3.2, §7. and §9; client-side OAL metrics in §2 and §9), so it is efficient with minor trim opportunities rather than fully lean.	4 / 5
Actionability	Provides copy-paste-ready code (Layer registration, SpanListener interface, component-ID lookup) and exact commands (mvnw invocation, SW_UI_TEMPLATE_FORCE_RELOAD, the curl --retry-connrefused loop, swctl queries) covering the common cases, with concrete file paths throughout.	5 / 5
Workflow Clarity	A clear numbered sequence (§0 Register Layer through §8 Pre-submit checklist) with explicit validation checkpoints ('Verify every new feature locally before pushing to CI', 'Verify each case by hand before pushing'), feedback loops ('If you find yourself editing more than this skill suggests, stop and confirm'), and a dedicated pre-submit checklist for a complex multi-step process.	5 / 5
Progressive Disclosure	Explicitly self-described as an index / wiring map that points to one skill per narrow concern; references to sibling skills (../run-e2e/SKILL.md, ../package/SKILL.md) and repo docs are one level deep, clearly signaled with markdown links, and organized into well-numbered sections for easy navigation.	5 / 5
	Total	19 / 20 Passed

Description

70%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 specific and clearly niched within the SkyWalking OAP skill suite, naming concrete extension points and cross-cutting concerns. Its main gaps are the missing explicit 'Use when...' trigger clause and second-person voice, which together cap completeness and lower specificity.

Suggestions

Add an explicit 'Use when...' clause naming the natural trigger phrases (e.g. 'Use when adding a new monitoring target / Layer to SkyWalking OAP, or when wiring a new data source into OAL / MAL / LAL / SpanListener').

Rewrite in third person to avoid the second-person 'Orients you to' (e.g. 'Orients the developer to ...') so the voice guideline does not penalize specificity.

Surface a couple of natural synonyms or file extensions users would actually say (e.g. 'new Layer', 'monitoring target', '.oal / mal / lal rules') to lift trigger-term coverage from 4 to 5.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete items — 'OAL / MAL / LAL / SpanListener / SegmentListener extension points, the UI template + submodule touchpoints, the docs set ... and the cross-cutting traps' — for comprehensive coverage (anchor 5), but reduced by 1 for the second-person 'Orients you to' phrasing per the voice guideline.	4 / 5
Completeness	Has a clear 'what' ('Add a new monitoring target / layer to SkyWalking OAP ... Orients you to ...'), but the 'when' is only weakly implied and there is no explicit 'Use when...' trigger guidance, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Good keyword coverage with domain-natural terms ('monitoring target / layer', 'SkyWalking OAP', and the named extension points), but it lacks a 'Use when...' clause enumerating natural trigger phrases, leaving a few common variations unsurfaced.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche ('new monitoring target / layer to SkyWalking OAP') with distinct named triggers and minimal overlap risk against the sibling narrow-concern skills it indexes.	5 / 5
	Total	16 / 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
relative_links	Relative link issues: 19 suspicious	Warning

	Total	15 / 16 Passed

Repository: apache/skywalking
Path: .claude/skills/new-monitoring-feature/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.