exa-migration-deep-dive

Migrate from other search APIs (Google, Bing, Tavily, Serper) to Exa neural search. Use when switching to Exa from another search provider, migrating search pipelines, or evaluating Exa as a replacement for traditional search APIs. Trigger with phrases like "migrate to exa", "switch to exa", "replace google search with exa", "exa vs tavily", "exa migration", "move to exa".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

80%

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 token-efficient, with complete executable code and Exa-specific guidance throughout. It loses points on workflow clarity (no explicit validation gate before ramping traffic) and progressive disclosure (everything inline, no detail files to offload to).

Suggestions

Add an explicit validation checkpoint before each traffic-percentage increase in Step 3 — e.g. 'compare overlap/relevance metrics; only raise EXA_TRAFFIC_PERCENTAGE when error rate is below threshold'.

Move the API comparison table and/or the adapter code into a referenced file (e.g. references/api-comparison.md) and link to it from SKILL.md so the main file stays a lean overview.

Expand the 'what' in the description with concrete actions (e.g. install the Exa SDK, build a provider-agnostic adapter, shift traffic via feature flag) to raise specificity.

Dimension	Reasoning	Score
Conciseness	The body is lean — a comparison table plus focused, commented code blocks — and the explanatory comments convey Exa-specific migration knowledge (e.g. "Exa doesn't use" boolean operators, use includeDomains instead of site:) rather than generic padding Claude already knows.	3 / 3
Actionability	Provides fully executable, copy-paste-ready TypeScript (adapter, traffic router, query translator, comparison function) alongside a concrete `npm install exa-js` command, matching the score-3 anchor.	3 / 3
Workflow Clarity	Steps 1–5 are clearly sequenced and Step 5 provides a comparison/validation routine, but the risky batch traffic-shift (0%→10%→50%→100%) lacks an explicit validation checkpoint gating each increase, so per the feedback-loop guidance workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	Sections are well organized and there is a single one-level reference to another skill (exa-advanced-troubleshooting) plus external doc links, but no bundle files exist and the full API comparison plus all code lives inline in one ~190-line file rather than being split into referenced materials.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 well-constructed: it states the migration purpose, gives explicit 'Use when' guidance, and lists natural trigger phrases with strong distinctiveness. Its only weak spot is specificity, where a single 'migrate' verb stands in for a richer set of concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and a primary action ("Migrate from other search APIs (Google, Bing, Tavily, Serper) to Exa neural search") but does not enumerate multiple distinct concrete actions the way the score-3 anchor does (e.g. extract/fill/merge), so it sits at 'names domain and some actions'.	2 / 3
Completeness	Clearly answers both what (migrate from Google/Bing/Tavily/Serper to Exa neural search) and when ("Use when switching to Exa from another search provider, migrating search pipelines, or evaluating Exa as a replacement"), with explicit triggers, matching the score-3 anchor.	3 / 3
Trigger Term Quality	Provides good natural-language coverage users would actually say — "migrate to exa", "switch to exa", "replace google search with exa", "exa vs tavily", "exa migration", "move to exa" — matching the score-3 anchor's breadth.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Exa migration from named competitors) with distinct, provider-specific triggers, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	11 / 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
Commit: 3022dd3

Reviewed: about 3 hours 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.