CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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.

A highly actionable, well-sequenced multi-agent workflow with concrete commands, explicit validation checkpoints, and disciplined error handling. The only weaknesses are mild — slight repetition of the read-only disclaimer and some inlined bulk (report template, resource-type command lists) that could live in separate reference files.

DimensionReasoningScore

Conciseness

The body is dense and directive with no explanations of concepts Claude already knows, but has minor trimmable redundancy — the read-only constraint is restated three times (header, prerequisites, closing) and the Phase 6 report template is spelled out fully inline.

4 / 5

Actionability

Fully executable guidance throughout: copy-pasteable grep/git log/aws/gcloud/kubectl/gh commands, concrete table schemas, an exact report filename pattern, and a specific documentation URL — the common cases are covered with real commands.

5 / 5

Workflow Clarity

Six clearly sequenced phases with explicit checkpoints and feedback loops: wait-for-user-response gates, 'Stop if nothing qualifies', per-check error recovery ('Check errors or loops → stop that check, note the failure, continue'), and a dedicated validation phase assigning HIGH/MEDIUM/LOW/SKIP verdicts with mixed-group handling.

5 / 5

Progressive Disclosure

Well-organized sections with clear headers and appropriate inline placement for the short per-check content; no bundle files exist so navigation is within one file. Minor gap: the per-resource-type command lists (Check D/E) and the Phase 6 report template are bulk that could be split into reference files.

4 / 5

Total

18

/

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.

A specific, distinctive description that names concrete actions comprehensively, but it omits any explicit 'when to use this skill' trigger clause and under-covers the natural phrasings (cost optimization, cloud waste, savings) a user would most likely say when reaching for it.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks about CloudZero Optimize recommendations, cloud cost optimization, savings opportunities, or idle-resource cleanup.'

Add natural synonyms users would say — 'cost optimization', 'cloud waste', 'idle resources', 'savings' — to improve trigger matching.

Fold the scope note into the when-clause so the description answers what, when, and boundary in one compact sentence.

DimensionReasoningScore

Specificity

The description 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' — with comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

The 'what' is clearly and specifically answered, but there is no 'Use when...' clause or equivalent explicit trigger guidance; 'Read-only research only' is a scope disclaimer, not a 'when'. Per the guidelines, a missing when-clause caps completeness at 3.

3 / 5

Trigger Term Quality

Good natural keyword coverage ('CloudZero Optimize recommendations', 'research agents', 'report files', 'confidence verdicts'), but misses common variations a user might actually say such as 'cost optimization', 'cloud waste', 'savings opportunities', or 'idle resources'.

4 / 5

Distinctiveness Conflict Risk

Highly niche triggers (CloudZero Optimize, SRE critique, confidence verdicts, per-resource report files) make it clearly distinguishable from generic research or cloud skills with minimal conflict risk.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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
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.