aiconfig-custom-metrics

DEPRECATED redirect — this skill was renamed to custom-metrics. Do not use this skill; invoke custom-metrics instead. Kept only so old references to aiconfig-custom-metrics still point users to the new name.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is an exemplary lean redirect notice: concise, fully actionable, with an unambiguous single-step workflow and clean organization appropriate for a skill needing no bundle files. No changes needed.

Dimension	Reasoning	Score
Conciseness	The body is four lean lines with no concept explanations; every token earns its place for a redirect notice, matching the 'lean and efficient' anchor 3.	3 / 3
Actionability	It gives the exact replacement skill to invoke and the exact old-to-new name mapping ('aiconfig-custom-metrics' to 'custom-metrics'), which is complete and actionable for an instruction-only redirect.	3 / 3
Workflow Clarity	This is a simple single-purpose skill under 50 lines with one unambiguous action and no destructive or batch operations, so the simple-skills note permits a 3 for clear workflow.	3 / 3
Progressive Disclosure	Under 50 lines with no need for external bundle references, the body is well-organized with a clear heading and points one level out to the custom-metrics skill, satisfying the simple-skills note.	3 / 3
	Total	12 / 12 Passed

Description

75%

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 well-formed deprecated-skill redirect description: it clearly states both its purpose and the trigger condition (old references to the prior name), and is highly distinctive. It scores lower only on specificity and trigger-term breadth, which are inherently limited for a redirect notice.

Suggestions

For specificity, consider naming the concrete downstream actions the renamed custom-metrics skill performs, so the description conveys capability rather than only redirect mechanics.

For trigger-term quality, add a few natural-language phrases users might say when encountering the old name (e.g., 'aiconfig custom metrics', 'AIConfig metrics') to broaden keyword coverage.

Consider an explicit 'Use when an old reference to aiconfig-custom-metrics is found' clause to make the trigger guidance unmistakable rather than phrased as a retention rationale.

Dimension	Reasoning	Score
Specificity	It names the redirect domain and one concrete action ('invoke custom-metrics instead'), but does not list multiple specific productive actions, matching anchor 2 rather than the multi-action anchor 3.	2 / 3
Completeness	It explicitly states what it does (redirect to custom-metrics) and gives equivalent explicit trigger guidance ('Kept only so old references to aiconfig-custom-metrics still point users to the new name'), so the missing-trigger cap does not apply.	3 / 3
Trigger Term Quality	The actual skill names a user or automation would reference ('aiconfig-custom-metrics', 'custom-metrics') are present, but coverage is narrow with no broader natural-language variations, fitting anchor 2.	2 / 3
Distinctiveness Conflict Risk	It names specific skills and explicitly says 'Do not use this skill', giving it a clear narrow redirect niche unlikely to trigger for the wrong skill, matching anchor 3.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: launchdarkly/ai-tooling
Path: skills/agentcontrol/aiconfig-custom-metrics/SKILL.md
Commit: e6ab09b

Reviewed: 3 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.