CtrlK
BlogDocsLog inGet started
Tessl Logo

aiconfig-create

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

62

Quality

73%

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-create/SKILL.md
SKILL.md
Quality
Evals
Security

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 an exceptionally clean, concise redirect notice that gives unambiguous direction (do not follow these instructions, invoke configs-create, update old references) with no padding, scoring near the top of the rubric.

DimensionReasoningScore

Conciseness

The body is a lean redirect notice where every token earns its place ("Do not follow any instructions here", "Invoke the configs-create skill instead"), assumes Claude's competence, and contains no padding or over-explanation, matching the score-5 anchor of a lean, efficient skill.

5 / 5

Actionability

It gives concrete, executable direction ("Invoke the configs-create skill instead", "update it from aiconfig-create to configs-create") covering the common arrival case, fitting the score-4 anchor of mostly executable guidance with minor gaps; it falls short of score 5 only because there are no copy-paste-ready commands or code examples, though code absence is not penalized for an instruction-only skill.

4 / 5

Workflow Clarity

This is a single-purpose redirect skill under 50 lines with an unambiguous single action (do not execute, invoke configs-create), so per the simple-skill scoring note workflow clarity scores 5; no destructive or batch operation is involved, so the validation cap does not apply.

5 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references, and is organized with a clear heading and well-structured paragraphs, so per the scoring note progressive disclosure scores 5 with just well-organized sections; no bundle files exist to verify.

5 / 5

Total

19

/

20

Passed

Description

53%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 clearly communicates that this is a deprecated redirect pointing to configs-create, with concrete 'do not use / invoke instead' guidance, but it lacks an explicit 'Use when...' trigger clause and natural-language synonyms, so it scores in the mid-range.

Suggestions

Add an explicit trigger clause such as 'Use only when a reference to the old name aiconfig-create is encountered, then redirect to configs-create' to lift completeness above 3.

Include natural-language variations users might say (e.g., 'create AI config', 'aiconfig') alongside the skill identifiers to improve trigger term quality.

State the trigger scenario up front ('Use when old references to aiconfig-create appear') rather than burying it in a rationale clause.

DimensionReasoningScore

Specificity

Names the domain ("DEPRECATED redirect") and one to two concrete actions ("Do not use this skill", "invoke configs-create instead"), but is not a comprehensive capability list, matching the score-3 anchor; it is not as sparse as score 2 ("Names the domain but actions are minimal") and lacks the multiple specific actions needed for score 4.

3 / 5

Completeness

The 'what' is clear (deprecated redirect; invoke configs-create instead), but the 'when' is only weakly implied via "Kept only so old references to aiconfig-create still point users to the new name" with no explicit "Use when..." clause, so per the judging guideline completeness is capped at 3.

3 / 5

Trigger Term Quality

Relevant identifiers are present ("aiconfig-create", "configs-create") that a user or automation referencing the old name would hit, but there are no natural-language synonyms or variations, fitting the score-3 anchor of "some relevant keywords but missing common variations"; it is richer than score 2's single generic keyword yet short of score 4's good coverage.

3 / 5

Distinctiveness Conflict Risk

It is keyed to the specific deprecated name "aiconfig-create" and only triggers for old references to it, giving minimal conflict risk with only minor overlap against the replacement "configs-create" skill, matching the score-4 anchor of "mostly distinct; minor overlap risk".

4 / 5

Total

13

/

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.

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.