Name: optimize-triage
Rating: 65.60000000000001 (1 reviews)
Author: Cloudzero

optimize-triage

Fetch top unaddressed CloudZero Optimize recommendations, dispatch parallel research agents per item, apply SRE critique, and surface actionable findings with confidence verdicts and per-resource report files. Read-only research only.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/cost-analyst/skills/optimize-triage/SKILL.md

Quality

Content

92%Weight 40%Scale 1-3

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

The body is highly actionable, concise, and exceptionally well-sequenced with validation checkpoints and feedback loops. Its main weakness is progressive disclosure: a large, complex skill is delivered as a single monolithic file with no reference files to offload detail.

Suggestions

Extract the Phase 6 report-file template and the Check A–E command catalogs into one-level-deep reference files (e.g. REPORT-TEMPLATE.md, CHECKS.md) referenced from SKILL.md to shorten the overview.

Move the per-resource-type provider command lists (Check D) into a separate quick-reference file so the core workflow stays scannable.

Add a short 'Quick start' overview at the top summarizing the six phases before the detailed per-phase instructions.

Dimension	Reasoning	Score
Conciseness	Lean and actionable throughout — it assumes Claude's competence, never explains basic cloud/IaC concepts, and every section (checks, verdicts, report structure) earns its tokens rather than padding.	3 / 3
Actionability	Provides concrete, copy-paste-ready commands (grep -r '[resource-id]' ..., git log --all -S ..., aws s3api get-bucket-lifecycle-configuration, kubectl top pods) and exact output formats rather than abstract descriptions.	3 / 3
Workflow Clarity	Phases 1–6 are explicitly sequenced with validation checkpoints: Phase 3 silent internal validation, HIGH/MEDIUM/LOW/SKIP verdicts, 'Stop if nothing qualifies', and feedback loops ('check errors → stop that check, note the failure, continue').	3 / 3
Progressive Disclosure	A ~320-line monolithic SKILL.md with no bundle files and no external references; the report-file template and per-resource check details are candidates for one-level-deep reference files but are all inline, so it is not fully split for navigation.	2 / 3
	Total	11 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 specific and distinctively scoped to CloudZero Optimize, but omits an explicit 'Use when...' trigger clause and leans on product jargon over natural user phrasing. Adding explicit invocation triggers and common-language keywords would raise completeness and trigger-term quality.

Suggestions

Append an explicit 'Use when...' clause stating the user situations that should trigger this skill (e.g. reviewing CloudZero Optimize recommendations, triaging cost-savings recs).

Add natural-language trigger terms users actually say ('cost optimization', 'cloud waste', 'save on cloud spend') alongside the product-specific jargon.

Reframe the trailing 'Read-only research only' as a constraint within a full what-and-when sentence rather than as the only 'when' signal.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Fetch top unaddressed CloudZero Optimize recommendations, dispatch parallel research agents per item, apply SRE critique, and surface actionable findings with confidence verdicts and per-resource report files' — matching the score-3 anchor.	3 / 3
Completeness	Clearly answers 'what' but lacks an explicit 'Use when...' trigger clause; 'Read-only research only' describes a constraint, not when to invoke, so completeness is capped at 2 per the guidelines.	2 / 3
Trigger Term Quality	Relevant terms ('CloudZero Optimize recommendations', 'research agents', 'SRE critique') are present but specialized; missing common natural variations a user might say ('cost optimization', 'cloud waste', 'save money').	2 / 3
Distinctiveness Conflict Risk	Tightly scoped to CloudZero Optimize with distinct triggers ('CloudZero Optimize recommendations', 'confidence verdicts'), making it unlikely to fire for an unrelated skill.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Cloudzero/cloudzero-claude-marketplace
Path: plugins/cost-analyst/skills/optimize-triage/SKILL.md
Commit: b9c7c16

Reviewed: 13 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.