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.

63

Quality

73%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/agentcontrol/aiconfig-online-evals/SKILL.md
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.

This is a well-crafted deprecation redirect skill. It is maximally concise, clearly actionable, and leaves no ambiguity about what Claude should do. The content perfectly serves its purpose of redirecting from a deprecated name to the current skill name.

DimensionReasoningScore

Conciseness

The content is extremely lean and efficient. Every sentence serves a purpose: it states the deprecation, tells Claude not to follow instructions here, redirects to the correct skill, and explains how to update old references. No unnecessary explanation.

3 / 3

Actionability

For a redirect/deprecation skill, the guidance is fully concrete and actionable: invoke `online-evals` instead, and update references from `aiconfig-online-evals` to `online-evals`. There is no ambiguity about what to do.

3 / 3

Workflow Clarity

This is a simple single-purpose skill (redirect). The single action is unambiguous: do not use this skill, use `online-evals` instead. No multi-step process is needed, and the instruction is crystal clear.

3 / 3

Progressive Disclosure

For a deprecation redirect with no bundle files, the content is appropriately minimal and well-organized. It correctly points to the replacement skill in a single, clear reference without unnecessary nesting or structure.

3 / 3

Total

12

/

12

Passed

Description

47%

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 deprecation redirect stub rather than a functional skill description. While it serves its narrow purpose of pointing users to the renamed 'online-evals' skill effectively and has low conflict risk, it completely lacks any description of actual capabilities or natural trigger terms that would help Claude understand the underlying functionality.

Suggestions

Add a brief summary of what online-evals actually does (e.g., 'Previously handled online evaluation configuration for AI models') so Claude can understand the domain even when encountering old references.

Include natural trigger terms related to the skill's actual functionality (e.g., 'online evaluations', 'eval config', 'AI evaluation') to help Claude route correctly if users reference the old skill by capability rather than name.

DimensionReasoningScore

Specificity

The description does not describe any concrete actions or capabilities. It only states that the skill is deprecated and redirects to another skill name, with no information about what the skill actually does.

1 / 3

Completeness

It answers 'when' clearly (do not use this skill, invoke online-evals instead), but completely fails to answer 'what does this do' in terms of actual capability. The redirect purpose is explicit, but there's no functional description.

2 / 3

Trigger Term Quality

It includes the old name 'aiconfig-online-evals' and the new name 'online-evals', which are relevant keywords for redirect purposes. However, it contains no natural user-facing trigger terms describing the actual functionality.

2 / 3

Distinctiveness Conflict Risk

The description is very clear about its narrow purpose as a deprecated redirect. It explicitly says 'Do not use this skill' and names the replacement, making it unlikely to conflict with or be mistakenly selected over other skills.

3 / 3

Total

8

/

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.

Validation11 / 11 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.