exa-cost-tuning

Optimize Exa costs through search type selection, caching, and usage monitoring. Use when analyzing Exa billing, reducing API costs, or implementing budget controls and usage alerts. Trigger with phrases like "exa cost", "exa billing", "reduce exa costs", "exa pricing", "exa expensive", "exa budget".

Quality

96%

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

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 content is highly actionable and lean, with a clear sequenced workflow and error-recovery guidance, but it keeps all detail inline in a single long file with no progressive disclosure to bundle references, capping that dimension at 2.

Suggestions

Move the longer worked examples (e.g., the SEARCH_PROFILES map and ExaBudgetTracker class) into a references/ file such as examples.md and link to it from SKILL.md so the main file stays a concise overview.

Add a brief validation checkpoint in the workflow (e.g., "after applying a technique, re-run the usage check in Step 5 to confirm cost dropped") to make the cost-reduction feedback loop explicit.

Consolidate the overlapping search-type guidance in Step 1 (predefined profiles) and Step 4 (selectCostEffectiveType) into a single reference, or clearly state when to use each, to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is lean and code-forward with a one-sentence overview and no explanations of concepts Claude already knows; every section delivers a concrete cost-reduction technique with minimal prose padding.	3 / 3
Actionability	It provides fully executable TypeScript against the real Exa SDK (exa.search/searchAndContents), an LRU cache, a bash/Python usage check, and an ExaBudgetTracker class — copy-paste ready with real API patterns.	3 / 3
Workflow Clarity	Five clearly numbered steps are sequenced, supported by a Cost Optimization Checklist and an Error Handling table mapping issue→cause→solution, which together provide the checklist and error-recovery feedback the 3-anchor calls for.	3 / 3
Progressive Disclosure	Sections are well organized, but the entire ~190-line body is inline in one file with no bundle files (references/scripts/assets absent) and no one-level-deep references to offload the detailed code, so it is not split across files as the 3-anchor expects.	2 / 3
	Total	11 / 12 Passed

Description

100%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.

A strong, specific description that covers concrete actions, natural trigger phrases, both the what and when, and occupies a clear niche with low conflict risk. The only cosmetic issue is choppy embedded blank lines in the YAML value, which does not affect the scored content.

Dimension	Reasoning	Score
Specificity	"Optimize Exa costs through search type selection, caching, and usage monitoring" plus "budget controls and usage alerts" lists multiple concrete, distinct actions rather than vague language, matching the 3-anchor.	3 / 3
Completeness	It explicitly states what the skill does ("Optimize Exa costs through…") and when to use it ("Use when analyzing Exa billing, reducing API costs, or implementing budget controls and usage alerts"), clearly answering both what and when.	3 / 3
Trigger Term Quality	"exa cost", "exa billing", "reduce exa costs", "exa pricing", "exa expensive", "exa budget" are natural phrases a user would actually say, giving good coverage with common variations.	3 / 3
Distinctiveness Conflict Risk	The Exa-specific niche and dedicated trigger phrases (all prefixed with "exa") make it clearly distinguishable and unlikely to fire for an unrelated skill.	3 / 3
	Total	12 / 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: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/exa-pack/skills/exa-cost-tuning/SKILL.md
Commit: 4c47e33

Reviewed: 3 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.