CtrlK
BlogDocsLog inGet started
Tessl Logo

cx-cost-optimization

Use this skill when the user asks to "check data usage", "list TCO policies", "reduce Coralogix costs", "optimize observability spend", "lower our logging bill", "data budget exceeded", "TCO policy", "retention tier", "archive storage", "ingestion costs", "frequent search vs archive", "why is our bill so high", "spending too much on logs", "data retention settings", "cost analysis", "usage breakdown", "optimize log volume", "control data ingestion", "archive cold data", "billing units", "plan consumption", "daily plan", "overage", "PAYG", "usage anomaly", "usage trend", "cx_data_usage_units", or wants to investigate, analyze, or reduce Coralogix data costs.

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

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 operational guide with strong safety gates and verification loops. Its main weaknesses are redundancy — the mandatory two-step workflow is repeated three times — and inline detail (the PromQL/bucketing section) that could be moved to a second reference file.

Suggestions

State the mandatory capabilities-then-query workflow once (in the 'Authoritative Billable Usage Queries' section) and have Step 1 and the key-flags list reference it in one line instead of restating it.

Move the Metrics-Based Cost Analysis detail (key-metrics table, UTC-day bucketing rules, anomaly-detection steps, breakdown labels) into a second reference file, keeping a short concept-to-metric mapping inline.

Trim the jq Examples section so it shows the jq pipelines without re-listing the full cx commands already demonstrated in the workflow steps.

DimensionReasoningScore

Conciseness

The body is dominated by lean command tables and executable examples with no explanation of concepts Claude already knows, but the mandatory capabilities-then-query workflow is stated three times (the key-flags list, the 'Authoritative Billable Usage Queries' section, and Step 1), and the jq Examples section re-lists commands already shown in the workflow. That is noticeable redundancy that could be tightened, matching 'mostly efficient but could be tightened' rather than the minor-trims anchor.

3 / 5

Actionability

Everything is copy-paste executable: exact `cx` invocations with flags, complete jq pipelines for each analysis, ready PromQL queries (e.g. `100 * sum(cx_data_usage_units) / cx_data_plan_units_per_day`), and a concrete JSON request body example. The common cost-analysis cases are covered specifically.

5 / 5

Workflow Clarity

The five-step investigation workflow is clearly sequenced with explicit validation checkpoints: 'Verify after changes: Re-run the diagnosis commands to confirm the change took effect', approval gates before any `--yes` write, and read-only mode for safe exploration. The destructive-operation validation cap does not apply because feedback loops are present.

5 / 5

Progressive Disclosure

The reference file (references/data-usage-query-api.md, verified to exist) is well signaled, loaded on demand ('Load ... before creating the query body'), and one level deep. However the detailed Metrics-Based Cost Analysis material (metric tables, UTC-day bucketing rules, anomaly-detection ladder, breakdown labels) is inline in an already long body and would fit a second reference file, so structure is good but not fully split — anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

81%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.

An unusually rich trigger-phrase list with an explicit 'use when' clause and a tightly bounded niche. Its one weakness is that the capability statement ('investigate, analyze, or reduce Coralogix data costs') is thin relative to the extensive trigger coverage, leaving the 'what' under-specified.

DimensionReasoningScore

Specificity

The closing clause 'investigate, analyze, or reduce Coralogix data costs' names the domain plus three actions, but the rest of the description is trigger phrases (e.g. 'retention tier', 'archive storage', 'ingestion costs') rather than statements of what the skill does. It matches 'names domain and 1-2 concrete actions, but not comprehensive' rather than the several-distinct-actions anchor.

3 / 5

Completeness

The 'when' is explicit and thorough ('Use this skill when the user asks to...'), and a 'what' exists ('investigate, analyze, or reduce Coralogix data costs'), but the what is thin — it never states the skill's concrete capabilities (measure spend, manage TCO policies, adjust retention, configure archive). Both present, what could be more explicit, so anchor 4 rather than 5.

4 / 5

Trigger Term Quality

Comprehensive natural-language coverage including synonyms and technical identifiers: 'why is our bill so high', 'lower our logging bill', 'spending too on logs' phrasing, 'optimize observability spend', 'PAYG', 'overage', 'usage anomaly', and the metric name 'cx_data_usage_units'. Nothing a user would naturally say is missing.

5 / 5

Distinctiveness Conflict Risk

Clearly scoped to 'Coralogix data costs' with cost-specific trigger phrases, giving it a clear niche with minimal conflict risk; only negligible overlap with a sibling telemetry-querying skill, since every trigger is cost/billing-oriented.

5 / 5

Total

17

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
coralogix/cx-cli
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.