CtrlK
BlogDocsLog inGet started
Tessl Logo

analyze-costs

Analyze cloud costs, find optimization opportunities, and track anomalies using Harness CCM via MCP. Use when user says "cloud costs", "analyze costs", "cost optimization", "reduce spending", "cost report", or asks about cloud bills.

68

Quality

81%

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

76%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 concise, actionable MCP skill body with strong structure and a useful reference table. The main weakness is the absence of explicit validation/verification checkpoints in a workflow that includes a destructive execute action.

Suggestions

Add an explicit validation checkpoint before destructive/batch actions (e.g., 'Confirm the anomaly ID and feedback value with the user before calling harness_execute with report_feedback').

Insert a verify step between data gathering and reporting (e.g., 'Verify recommendations and anomaly data are complete before drafting the report; re-query if a perspective returns empty'), turning the Performance Notes into an explicit workflow checkpoint.

Consider moving the Cost Resource Types Reference table into a references/ file and linking to it, keeping the main body as a lean overview.

DimensionReasoningScore

Conciseness

Lean and efficient with no padding or explanation of concepts Claude already knows; every section (steps, report format, reference table, examples, troubleshooting) earns its place.

5 / 5

Actionability

Concrete MCP call blocks with specific resource_type values and parameters, plus a full resource-types reference table and worked examples; placeholders like '<perspective_id>' require runtime substitution, leaving minor gaps from fully copy-paste-ready.

4 / 5

Workflow Clarity

Seven clearly sequenced steps are present, but there are no explicit validation checkpoints, and the destructive harness_execute 'report_feedback' action proceeds without confirm-before-execute; the destructive/batch cap therefore limits this to 3.

3 / 5

Progressive Disclosure

Well-organized into clearly labeled sections with no nested references and an appropriately inline resource-types table for an MCP skill; no bundle files exist, and the bulk reference table could arguably be split out, leaving a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

87%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 strong description that clearly states capabilities and provides explicit trigger guidance tied to a distinct niche. Minor gains are possible by sharpening the most abstract action verb and broadening trigger synonyms.

DimensionReasoningScore

Specificity

Names the domain and three concrete actions ('Analyze cloud costs, find optimization opportunities, and track anomalies') tied to a specific system (Harness CCM via MCP), but 'find optimization opportunities' is somewhat abstract compared to the fully granular score-5 example.

4 / 5

Completeness

Explicitly answers both 'what' (analyze/find/track) and 'when' via a clear 'Use when user says...' clause with concrete trigger phrases, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Six natural trigger phrases ('cloud costs', 'analyze costs', 'cost optimization', 'reduce spending', 'cost report', 'asks about cloud bills') give good coverage, though common synonyms like 'spend', 'FinOps', or 'AWS/GCP bill' are missing.

4 / 5

Distinctiveness Conflict Risk

Scoped to Harness CCM via MCP with niche-specific triggers, giving a clear niche and minimal conflict risk with other skills.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
harness/harness-ai
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.