agent-sona-learning-optimizer

Agent skill for sona-learning-optimizer - invoke with $agent-sona-learning-optimizer

Quality

25%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-sona-learning-optimizer/SKILL.md

Quality

Content

50%

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

The body is organized into clear sections but is dominated by marketing-style benchmark claims and descriptive capability lists rather than executable guidance, with the only actionable content being two hook commands. Its references are dangling or malformed because no bundle files exist.

Suggestions

Cut the unverifiable benchmark statistics and per-domain deltas; replace with concise operational guidance on how to actually drive a learning cycle.

Provide a concrete, sequenced pre-task → post-task workflow with a verification step that the recorded outcome was applied, rather than two isolated hook commands.

Fix the malformed package reference ("@ruvector$sona" should likely be "@ruvector/sona") and either supply the referenced docs/RUVECTOR_SONA_INTEGRATION.md as a real reference file or remove the dangling link.

Dimension	Reasoning	Score
Conciseness	The body is padded with unverifiable benchmark claims ("+55% quality improvement", "2211 ops$sec", per-domain deltas) and surface marketing of LoRA/EWC++/routing that Claude cannot act on, fitting the anchor for mostly-efficient but unnecessarily padded content.	2 / 3
Actionability	Only the two `npx claude-flow@alpha hooks` commands are executable; the rest is descriptive ("Automatic model selection", "Learn from every task execution") with no callable API, matching the anchor for some concrete guidance but incomplete.	2 / 3
Workflow Clarity	The pre-task/post-task hooks are presented as isolated commands with no sequence, checkpoint, or validation step, fitting the anchor for steps present but checkpoints missing or implicit.	2 / 3
Progressive Disclosure	Sections are reasonably organized, but the References point to a malformed package name ("@ruvector$sona@0.1.1") and a docs path with no corresponding bundle file present, fitting the anchor for structure present but references not clearly signaled or real.	2 / 3
	Total	8 / 12 Passed

Description

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 boilerplate that fails to convey any concrete capability, natural trigger, or use context, leaving it indistinguishable from any other auto-generated skill description. It would not help a user or Claude decide when to invoke it.

Suggestions

Replace the boilerplate with concrete actions the skill performs (e.g., what 'learning optimization' actually does to task execution).

Add an explicit 'Use when...' trigger clause listing natural terms a user would say (e.g., 'Use when improving repeated task quality' or the domains it optimizes).

State the distinct niche clearly so it does not read as a generic wrapper around the sona-learning-optimizer package.

Dimension	Reasoning	Score
Specificity	The description only states "Agent skill for sona-learning-optimizer - invoke with $agent-sona-learning-optimizer", naming no concrete actions, matching the anchor for vague or absent actions.	1 / 3
Completeness	It answers neither what (the phrase "Agent skill for X" is circular) nor when to use it, with no "Use when..." trigger, matching the anchor for missing what AND when.	1 / 3
Trigger Term Quality	It contains only the invocation token "$agent-sona-learning-optimizer" rather than natural keywords a user would say, matching the anchor for technical jargon / no natural keywords.	1 / 3
Distinctiveness Conflict Risk	"Agent skill for sona-learning-optimizer" is generic boilerplate applicable to any skill and establishes no distinct niche, matching the very-generic / high-conflict anchor.	1 / 3
	Total	4 / 12 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: ruvnet/claude-flow
Path: .agents/skills/agent-sona-learning-optimizer/SKILL.md
Commit: 26c35b5

Reviewed: about 6 hours 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.