CtrlK
BlogDocsLog inGet started
Tessl Logo

aiconfig-online-evals

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

76

Quality

95%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

An appropriately minimal redirect body: concise, unambiguous, and well-organized with no unnecessary explanation or nested references. It does exactly what a deprecation shim should and nothing more.

DimensionReasoningScore

Conciseness

Eight lean lines with no concept-explaining fluff and no padding; every token earns its place and it assumes Claude's competence rather than explaining what a redirect is.

3 / 3

Actionability

Gives concrete, executable guidance naming the exact skill to invoke (online-evals) and the exact action for callers (update references from aiconfig-online-evals to online-evals), leaving no ambiguity.

3 / 3

Workflow Clarity

A single unambiguous redirect action with an explicit instruction not to follow the old instructions; per the simple-skills note, a clear single action can score 3.

3 / 3

Progressive Disclosure

Under 50 lines with no need for external references, organized with a clear heading and bolded skill name; no bundle files exist so there is nothing to split out, satisfying the well-organized-sections bar.

3 / 3

Total

12

/

12

Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-written deprecation redirect: third-person, concise, and explicit about both the action (invoke online-evals) and the trigger (old references to aiconfig-online-evals). It lacks multiple concrete capabilities only because a redirect legitimately has a single action.

DimensionReasoningScore

Specificity

Names one concrete action ('invoke online-evals instead') but does not list multiple specific capabilities, matching the 'names domain and some actions' anchor rather than the 'lists multiple specific concrete actions' level above.

2 / 3

Completeness

Explicitly answers both what (redirect users to the new name) and when ('old references to aiconfig-online-evals still point users to the new name'), with explicit trigger guidance, so it is not capped at 2.

3 / 3

Trigger Term Quality

Uses natural terms a user would actually say ('DEPRECATED redirect', 'renamed to online-evals', 'old references to aiconfig-online-evals'), giving good coverage of the redirect's trigger vocabulary.

3 / 3

Distinctiveness Conflict Risk

Names the specific old and new skill identifiers, giving it a clear niche that is unlikely to trigger for the wrong skill; it would not conflict with other skills.

3 / 3

Total

11

/

12

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.

Validation16 / 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.