Name: optimize-triage
Rating: 63.2 (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

76%

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

77%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 skill body is a well-sequenced, actionable, validation-rich multi-agent workflow, but it is a monolithic single file with no progressive disclosure into reference files, and the read-only framing is stated redundantly.

Suggestions

Split the per-resource-type cloud-provider command catalog (Check D) and the Phase 6 report-file template into separate reference files referenced one level deep from SKILL.md.

Consolidate the repeated read-only / research-only warnings into a single prominent statement near the top instead of restating them across Phase 3 and the closing line.

Move the detailed category-specific checks (Check E) into a referenced CHEATSHEET or checks file to reduce inline length while keeping SKILL.md as an overview.

Dimension	Reasoning	Score
Conciseness	The body is long but the length is mostly justified domain-specific process detail rather than concepts Claude already knows; the main over-explanation is the read-only / research-only warning repeated at the top, mid-body, and end, which could be consolidated.	4 / 5
Actionability	Concrete, mostly executable commands throughout (grep/git-log snippets, per-resource-type cloud CLI calls such as `aws s3api get-bucket-lifecycle-configuration`), with only minor gaps where commands are templated around `[resource-id]` placeholders.	4 / 5
Workflow Clarity	A clear six-phase sequence with explicit validation checkpoints — Phase 3 silent internal validation, HIGH/MEDIUM/LOW/SKIP verdicts, mixed-group splitting, and 'stop and ask' blocker handling — plus decision branches and feedback loops for a batch multi-agent operation.	5 / 5
Progressive Disclosure	Good internal section structure (phases, Checks A–E), but no bundle files exist and everything is inlined in one ~250-line document; content that would benefit from separate reference files (the per-resource cloud-command catalog and the Phase 6 report template) is inline with no outbound references.	3 / 5
	Total	16 / 20 Passed

Description

75%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 specific, distinctive, and rich in domain trigger terms, but it omits any explicit 'Use when...' trigger guidance, leaving the 'when to invoke' question unanswered.

Suggestions

Add a 'Use when...' clause naming natural trigger phrases (e.g. 'Use when triaging CloudZero Optimize recommendations, investigating unaddressed cost savings, or running a parallel cost-optimization research sweep').

Include a few synonyms / colloquial terms a user might actually say ('cost recommendations', 'savings opportunities', 'optimize triage') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Fetch top unaddressed CloudZero Optimize recommendations', 'dispatch parallel research agents per item', 'apply SRE critique', 'surface actionable findings with confidence verdicts and per-resource report files' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The 'what' is clearly and comprehensively stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance; per the judging guidelines this caps completeness at 3.	3 / 5
Trigger Term Quality	Strong domain keywords ('CloudZero Optimize recommendations', 'research agents', 'SRE critique', 'confidence verdicts') that a CloudZero user would naturally say, but missing common synonyms or variations beyond the core product terms.	4 / 5
Distinctiveness Conflict Risk	A clear niche tied to CloudZero Optimize with parallel-agent research and SRE critique — distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 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: 62c27f3

Reviewed: 1 day 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.