CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

80

Quality

100%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

A well-structured overview SKILL.md that is lean, actionable, and cleanly routes to real one-level-deep reference files. Its sequenced process includes validation checkpoints and the content is appropriately split across the bundle.

DimensionReasoningScore

Conciseness

Lean and efficient: it assumes Claude's competence (no explanations of what evaluators, CloudWatch, or tracing are) and every section earns its place by routing or setting up, with no padded concept prose.

3 / 3

Actionability

Gives concrete executable guidance — 'Run `agentcore --version`', 'Read `agentcore/agentcore.json`' — and a decision table mapping each intent to a specific reference file path, which is actionable routing for an instruction skill.

3 / 3

Workflow Clarity

Steps 0–3 are clearly sequenced with explicit validation checkpoints: a CLI version gate in Step 0 and a project-file existence guard with a fallback message in Step 1.

3 / 3

Progressive Disclosure

The body is a concise overview that routes to one-level-deep, clearly signaled references (evals.md, observability.md, cost.md), all of which exist as real bundle files, with content appropriately split.

3 / 3

Total

12

/

12

Passed

Description

100%

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 strong, third-person description that names concrete capabilities, provides an extensive natural-language trigger list, and explicitly separates itself from sibling skills. It answers both 'what' and 'when' without fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'set up evaluators, online monitoring, CI/CD quality gates, observability, or cost optimization' — rather than vague language, matching the top anchor.

3 / 3

Completeness

Clearly states what it does (measuring/improving agent quality and performance) and when to use it via 'Use when...' plus an explicit 'Triggers on:' list, answering both what and when.

3 / 3

Trigger Term Quality

An explicit 'Triggers on:' list gives natural phrases users would actually say ('evaluate my agent', 'agent too slow', 'how much does my agent cost', 'logs not showing up'), with strong coverage of variations.

3 / 3

Distinctiveness Conflict Risk

Has a clear niche (quality/observability/cost) and explicitly disambiguates with 'Not for debugging errors or crashes — use agents-debug', making wrong-skill triggering unlikely.

3 / 3

Total

12

/

12

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
aws/agent-toolkit-for-aws
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.