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.

Quality

85%

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%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 exemplary redirect stub: maximally lean, unambiguous, and actionable, correctly instructing Claude to invoke the replacement skill and to update stale references.

Dimension	Reasoning	Score
Conciseness	Five lean lines with zero padding: it assumes Claude's competence, explains nothing the model already knows, and every token earns its place.	5 / 5
Actionability	Fully concrete guidance for an instruction-only skill: exact replacement skill to invoke (configs-create) and the exact rename mapping (aiconfig-create → configs-create), covering the common arrival cases.	5 / 5
Workflow Clarity	A single-task skill under 50 lines whose single action (invoke configs-create) is unambiguous, with no destructive or batch operations requiring validation.	5 / 5
Progressive Disclosure	Under 50 lines with no external references needed (confirmed: no references/, scripts/, or assets/ directories exist), organized with a clear header — well-organized sections suffice for a skill this size.	5 / 5
	Total	20 / 20 Passed

Description

62%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.

A well-executed deprecation-redirect description: it is unambiguous about its purpose and explicitly redirects to the replacement skill, but it omits any natural task trigger phrases and describes no capabilities of the underlying domain.

Suggestions

Add an explicit trigger clause (e.g., 'Use only when an old reference or automation names aiconfig-create') to sharpen the 'when' and raise completeness.

Include a brief mention of what the skill domain covered (e.g., creating aiconfig files) so the redirect carries context and catches natural phrasing like 'create an aiconfig'.

Add common synonyms or variants of the old name that stale references might use to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description states concrete redirect actions ("Do not use this skill; invoke configs-create instead", "Kept only so old references…") but describes no capabilities of the underlying task domain, so coverage is not comprehensive.	3 / 5
Completeness	The "what" is explicit (deprecated redirect stub) and "when" guidance exists ("Do not use this skill; invoke configs-create instead"), but there is no concrete 'Use when…' trigger phrase, capping it below 5.	4 / 5
Trigger Term Quality	Relevant keywords are limited to the proper names "aiconfig-create" and "configs-create" plus deprecation terms; the old name is a natural term for someone with a stale reference, but no natural task phrases, variations, or synonyms are present.	3 / 5
Distinctiveness Conflict Risk	The explicit "Do not use this skill; invoke configs-create instead" unambiguously resolves the naming overlap with the closely related configs-create skill, leaving only minor overlap risk from the similar names.	4 / 5
	Total	14 / 20 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-create/SKILL.md
Commit: ef54971

Reviewed: 6 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.