exa-multi-env-setup

Configure Exa across development, staging, and production environments. Use when setting up multi-environment search pipelines, managing API key isolation, or configuring per-environment search limits and caching. Trigger with phrases like "exa environments", "exa staging", "exa dev prod", "exa environment setup", "exa multi-env".

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

The body is highly actionable with executable TypeScript and concrete CI/CD guidance, and is well-structured with lean prose. Its main weakness is workflow safety: production deployment lacks an explicit validation/promotion gate even though a health check is defined.

Suggestions

Add a validation checkpoint to the deploy workflow: after deploy-staging, run checkExaHealth() and only promote to production when status is 'healthy' — this turns the existing health check into a gate and lifts workflow_clarity above the destructive-operation cap.

Eliminate the duplicated exa.searchAndContents call by having cachedSearch delegate to search() for the non-cached path, removing the verbatim repeat between Step 2 and Step 3.

Remove the redundant Environment Strategy table (or the inline config values) so per-tier settings live in one place, trimming token cost without losing information.

Dimension	Reasoning	Score
Conciseness	Prose is lean with no over-explanation of concepts Claude already knows, but the exa.searchAndContents invocation is duplicated verbatim in Step 2 and Step 3 (cachedSearch re-implements rather than delegating to search), and the Environment Strategy table restates values already in the config code. Not a 5 because of these duplicated/redundant blocks; not a 3 because the body is mostly efficient rather than noticeably verbose.	4 / 5
Actionability	Provides fully executable, copy-paste-ready TypeScript across config, search service, cache layer, env vars, CI/CD YAML, and a health check, covering the common multi-env cases concretely. Not a 4 because the examples are complete and specific rather than having minor gaps.	5 / 5
Workflow Clarity	Steps 1–6 are clearly sequenced, but production deployment is a destructive/batch operation with no validation gate between staging and production, and the health check (Step 6) is defined but not wired as a 'only proceed when healthy' checkpoint in the deploy flow. Per the destructive-operation cap, this cannot exceed 3; it is not a 2 because a real sequence with a health check is present.	3 / 5
Progressive Disclosure	Sections are well-organized with clear headers and a clearly signaled one-level-deep reference ('see exa-deploy-integration') plus external doc links, with no nested references. Not a 5 because all six code blocks are inlined in a single ~220-line file rather than split into reference files; not a 3 because structure and navigation are genuinely good.	4 / 5
	Total	16 / 20 Passed

Description

100%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, complete, and well-triggered: it states concrete capabilities, gives explicit 'Use when' guidance plus natural trigger phrases, and occupies a distinct niche. It uses appropriate third-person voice with no fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'setting up multi-environment search pipelines, managing API key isolation, or configuring per-environment search limits and caching' — giving comprehensive coverage of the skill's capabilities. It is not a level-4 case because coverage is broad and each action is distinct rather than having minor gaps.	5 / 5
Completeness	Explicitly answers both 'what' (configure Exa across dev/staging/prod with key isolation, limits, caching) and 'when' ('Use when setting up...' plus explicit trigger phrases), in third person. Not a 4 because the 'when' is concrete and specific rather than merely present.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger phrases including synonyms — 'exa environments', 'exa staging', 'exa dev prod', 'exa environment setup', 'exa multi-env' — the kind a user would actually say. Not a 4 because it goes beyond good coverage to enumerate multiple natural variations.	5 / 5
Distinctiveness Conflict Risk	'Exa multi-environment setup' is a clear niche with distinct Exa-scoped triggers, minimizing conflict with other skills. Not a 4 because the triggers are uniquely Exa-specific with no meaningful overlap risk.	5 / 5
	Total	20 / 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: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/exa-pack/skills/exa-multi-env-setup/SKILL.md
Commit: 0540a62

Reviewed: 43 minutes 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.