aiconfig-agent-graphs

DEPRECATED redirect — this skill was renamed to agent-graphs. Do not use this skill; invoke agent-graphs instead. Kept only so old references to aiconfig-agent-graphs 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 concise, fully actionable, and unambiguous about both what not to do and what to do instead. It also closes the loop by telling the reader to update stale references, covering the only realistic failure mode.

Dimension	Reasoning	Score
Conciseness	The body is six lean lines ('This skill has been renamed.' / 'Invoke the agent-graphs skill instead') with zero padding and nothing Claude already knows explained. Every token earns its place, matching the anchor 'Lean and efficient; assumes Claude's competence'.	5 / 5
Actionability	The guidance is fully executable for an instruction-only skill: 'Invoke the agent-graphs skill instead — it contains the current, complete instructions' and 'update it from aiconfig-agent-graphs to agent-graphs'. Per the scoring notes, absence of code is not penalized when guidance is this actionable, so it fits the top anchor rather than 4.	5 / 5
Workflow Clarity	It is a single-purpose skill whose one action is unambiguous, guarded by an explicit warning ('Do not follow any instructions here and do not perform the task from this skill'), with a remediation step for old references. The simple-skill exception applies and no destructive/batch cap does, so 5 rather than 4.	5 / 5
Progressive Disclosure	The skill is under 50 lines, has no bundle files (references/, scripts/, assets/ are absent), and needs no external references; a clear heading plus three short paragraphs is well-organized for a stub. The rubric's under-50-lines guideline allows 5 with just well-organized sections.	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.

The description is clear, third-person, and effective for a deprecation stub: it states what happened (rename), what to do (invoke agent-graphs), and why the file still exists. Its weakness is conventional trigger phrasing — no 'Use when...' style clause and no keyword variations — which leaves trigger quality and completeness in the mid range.

Suggestions

Add an explicit trigger clause such as 'Applies only when an old reference mentions aiconfig-agent-graphs' to make the 'when' as direct as the 'what'.

Include natural keyword variations of the old name users might type (e.g., 'aiconfig agent graphs', 'agent graph') so the redirect matches more real-world phrasings.

State concretely what the successor skill covers in one short phrase so readers of the old name know the redirect target is the same capability.

Dimension	Reasoning	Score
Specificity	The description names its role ('DEPRECATED redirect — this skill was renamed to agent-graphs') plus 1-2 concrete actions ('invoke agent-graphs instead', 'Do not use this skill'), matching the anchor for a named domain with 1-2 concrete actions. It is not generic (rules out 2) but does not list several specific actions (rules out 4).	3 / 5
Completeness	The 'what' is explicit (deprecated redirect to agent-graphs) and a 'when' is present via 'Kept only so old references to aiconfig-agent-graphs still point users to the new name' plus the explicit 'Do not use this skill'. The when could be phrased as a direct trigger clause, so it fits anchor 4 rather than 5, and it is more than weakly implied, ruling out 3.	4 / 5
Trigger Term Quality	It contains the relevant terms for its niche ('aiconfig-agent-graphs', 'agent-graphs', 'renamed') but no natural variations or synonyms a user might say. This matches 'Some relevant keywords but missing common variations or synonyms' rather than the good-coverage anchor 4.	3 / 5
Distinctiveness Conflict Risk	It has a clear niche (old references to the specific old name) with distinct triggers, but it repeatedly names 'agent-graphs', creating minor overlap with the live skill's triggers — matching 'Mostly distinct; minor overlap risk with closely related skills'. The overlap is intentional and resolves correctly, so it does not drop to 3.	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-agent-graphs/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.