CtrlK
BlogDocsLog inGet started
Tessl Logo

aiconfig-ai-metrics

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

60

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/agentcontrol/aiconfig-ai-metrics/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%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 model deprecation stub: it warns against following any instructions here, names the replacement skill unambiguously, and tells readers arriving from old references to update them. It is maximally lean, fully actionable for its single purpose, and correctly avoids inlining or referencing any stale content. There is nothing to add or trim without violating its purpose.

DimensionReasoningScore

Conciseness

The body is roughly six lines with zero padding: 'This skill has been renamed. Do not follow any instructions here...' plus the redirect target and the old-reference migration note. It explains nothing Claude already knows and every token earns its place, matching anchor 5 exactly.

5 / 5

Actionability

For an instruction-only redirect skill the guidance is fully executable: 'Invoke the built-in-metrics skill instead' and 'update it from aiconfig-ai-metrics to built-in-metrics' cover both the immediate action and the follow-up migration. Per the scoring notes, absence of code is not penalized in an instruction-only skill when the guidance is actionable — and it is unambiguously so.

5 / 5

Workflow Clarity

This is a simple single-task skill under 50 lines with no multi-step process; the single action (invoke built-in-metrics) is unambiguous, and the simple-skill exception applies. There are no destructive or batch operations, so the validation cap does not apply.

5 / 5

Progressive Disclosure

The body is well under 50 lines with no need for external references; the heading ('Deprecated — renamed to built-in-metrics') and short organized paragraphs satisfy the simple-skill exception, and there are no nested or buried references to navigate.

5 / 5

Total

20

/

20

Passed

Description

41%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 honest and functional as a deprecation notice: it clearly states what happened (rename to built-in-metrics), instructs the reader to invoke the replacement, and explains why the stub is kept. However, as a skill description it names no capabilities of the underlying skill and contains no natural trigger terms, so a user or model searching by task language would not find it — which is partly inherent to a deprecated redirect. Completeness is capped by the missing 'Use when...' guidance, and trigger coverage is limited to the two skill names.

Suggestions

Add explicit trigger guidance for the redirect case, e.g. 'Use only when an old reference (documentation, saved prompt, or automation) names aiconfig-ai-metrics; otherwise invoke built-in-metrics directly.'

Include one or two natural task-language terms (e.g. 'metrics', 'telemetry', 'evaluation metrics') so the description matches how users would actually refer to the skill's domain when deciding where to redirect.

Briefly state the skill's domain of capability (e.g. 'AI metrics collection/evaluation') so the redirect is self-explanatory even to readers who never saw the old skill.

DimensionReasoningScore

Specificity

The description states 'DEPRECATED redirect — this skill was renamed to built-in-metrics. Do not use this skill; invoke built-in-metrics instead.' It conveys one concrete action (the redirect) and identifies the domain only via skill names, but describes zero capabilities of the skill itself. It is above anchor 1 (pure abstract language with no concrete action) yet well below anchor 3 (which expects 1-2 concrete domain actions), so anchor 2 is the closest fit.

2 / 5

Completeness

The 'what' is clear (a deprecated redirect to built-in-metrics), but the 'when' is only weakly implied via 'Kept only so old references to aiconfig-ai-metrics still point users to the new name' — there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

The only keywords are the skill names 'aiconfig-ai-metrics' and 'built-in-metrics' plus 'deprecated'/'redirect' — none are natural phrases a user would say when needing the skill's capability. It sits above anchor 1 (technical jargon only, e.g. 'Handles document object model manipulation') but lacks the relevant keywords and common variations of anchor 3.

2 / 5

Distinctiveness Conflict Risk

The explicit disclaimers ('Do not use this skill; invoke built-in-metrics instead') and the unique skill names make it largely self-disqualifying with minimal conflict risk. It falls just below anchor 5 because the description contains no positive trigger language, so generic metrics-related queries could still surface it alongside the similarly named built-in-metrics.

4 / 5

Total

11

/

20

Passed

Validation

100%

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
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.