agents-optimize

Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI/CD quality gates, observability, or cost optimization. Triggers on: "evaluate my agent", "add evaluator", "measure quality", "quality gate", "run evals", "agent too slow", "why is it slow", "reduce latency", "set up observability", "CloudWatch dashboard", "how much does my agent cost", "cost optimization", "logs not showing up", "logs missing", "spans not found", "eval failing", "eval error", "dev traces", "local traces", "agentcore dev traces", "traces to CloudWatch". Not for debugging errors or crashes — use agents-debug. Slow but correct routes here; broken routes to debug.

Quality

94%

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

88%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 efficient overview that routes to three real reference files via a clear decision table, with concise sequencing and a version prerequisite checkpoint. It is slightly light on inline executable detail, but that is appropriate given the reference-backed design.

Dimension	Reasoning	Score
Conciseness	The body is lean: brief 'When to use' bullets, a compact decision table, and short process steps that defer detail to references without explaining concepts Claude already knows.	5 / 5
Actionability	Provides concrete commands (`agentcore --version`, reading `agentcore/agentcore.json`) and a decision table mapping intents to reference files, but most executable detail lives in the references rather than inline.	4 / 5
Workflow Clarity	Clear sequenced steps (Step 0 through Step 3) with a verification checkpoint at CLI version and a guard for missing project config, though validation of eval/observability outcomes is deferred to the references.	4 / 5
Progressive Disclosure	Well-structured overview with clearly signaled one-level-deep references (evals.md, observability.md, cost.md) that all exist as real files, and a decision table for easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

100%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 exemplary: it specifies concrete capabilities, provides comprehensive natural trigger terms, explicitly answers both what and when, and clearly delineates boundaries against sibling skills. The third-person voice is maintained throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('set up evaluators, online monitoring, CI/CD quality gates, observability, or cost optimization') covering the skill's scope comprehensively.	5 / 5
Completeness	Explicitly answers both what (measure/improve agent quality via evaluators, monitoring, observability, cost) and when (detailed 'Triggers on' clause with concrete phrases), plus explicit 'Not for' boundary guidance.	5 / 5
Trigger Term Quality	Extensive natural trigger phrases users would actually say ('evaluate my agent', 'run evals', 'agent too slow', 'how much does my agent cost', 'logs not showing up') including synonyms and variations.	5 / 5
Distinctiveness Conflict Risk	Clear niche (AgentCore quality/performance) with explicit routing rules ('Slow but correct routes here; broken routes to debug') minimizing overlap with sibling skills like agents-debug.	5 / 5
	Total	20 / 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: aws/agent-toolkit-for-aws
Path: plugins/aws-agents/skills/agents-optimize/SKILL.md
Commit: d6ad2e4

Reviewed: 19 minutes 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.