exa-core-workflow-b

Execute Exa findSimilar, getContents, answer, and streaming answer workflows. Use when finding pages similar to a URL, retrieving content for known URLs, or getting AI-generated answers with citations. Trigger with phrases like "exa find similar", "exa get contents", "exa answer", "exa similarity search", "findSimilarAndContents".

Quality

82%

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

80%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 token-efficient with concrete executable examples. Workflow clarity and progressive disclosure are the weak spots: batch workflows lack verification checkpoints and the large inline API reference could be split into bundled reference files.

Suggestions

Add explicit verification steps to the batch URL example (e.g., check for failed/empty results per batch and retry before continuing).

Fix the "Exa Find Similar" resource entry by adding its missing link, and link the Next Steps skill names to their actual paths.

Move the detailed per-parameter options into a separate REFERENCE.md bundle file and keep SKILL.md as a concise overview pointing to it.

Dimension	Reasoning	Score
Conciseness	Lean body of executable code with only genuinely useful inline parameter comments; no padding explaining what Exa or async APIs are, so every token earns its place.	3 / 3
Actionability	Provides fully executable, copy-paste-ready TypeScript snippets with real parameters and concrete usage across all five endpoints.	3 / 3
Workflow Clarity	Steps 1–5 are clearly sequenced and an error-handling table aids recovery, but the batch-retrieval example and main workflows lack explicit validation/verification checkpoints, capping clarity at 2.	2 / 3
Progressive Disclosure	Well-sectioned but monolithic: all API detail lives inline in code rather than split into reference files, and the "Exa Find Similar" resource entry has no link while Next Steps reference other skills only by bare name.	2 / 3
	Total	10 / 12 Passed

Description

85%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.

The description is specific and complete with an explicit Use-when trigger, giving it strong completeness and distinctiveness. The main weakness is trigger-term quality, where a technical method name dilutes otherwise natural phrasing.

Suggestions

Drop the "findSimilarAndContents" method name from the trigger list or replace it with a natural phrasing like "exa find similar with contents".

Tighten the multi-line description into a single flowing sentence to avoid the awkward line breaks in the YAML string.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ("findSimilar, getContents, answer, and streaming answer workflows") rather than vague language, matching the multi-action anchor.	3 / 3
Completeness	Explicitly states what it does ("Execute Exa findSimilar, getContents, answer...") and when to use it via an explicit "Use when finding pages similar to a URL..." clause.	3 / 3
Trigger Term Quality	Includes natural phrases like "exa find similar" and "exa answer", but also mixes in the method-name jargon "findSimilarAndContents", which a user would not naturally say.	2 / 3
Distinctiveness Conflict Risk	Targets a clear Exa-specific niche (similarity, contents, answer endpoints) with distinct Exa-branded triggers unlikely to fire for unrelated skills.	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
Path: plugins/saas-packs/exa-pack/skills/exa-core-workflow-b/SKILL.md
Commit: 8585d6d

Reviewed: 14 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.