CtrlK
BlogDocsLog inGet started
Tessl Logo

exa-search

Semantic search, similar content discovery, and structured research using Exa API. Use when you need semantic/embeddings-based search, finding similar content, or searching by category (company, people, research papers, etc.).

55

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/exa-search/SKILL.md

The canonical home for this skill is exa-search in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

47%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 concise and neatly sectioned but largely superficial: it provides an install command and otherwise points the reader to an external repo, with no concrete Exa API usage examples or defined workflow.

Suggestions

Add a concrete, copy-paste-ready Exa API call example (e.g. a curl or Python snippet) under Examples instead of only linking to the GitHub repo.

Replace vague steps like 'Configure Exa API key' and 'Use naturally in Claude Code conversations' with the specific commands or code a user must run.

Specify the API key configuration (the exact environment variable name) in Best Practices rather than the generic 'via environment variables' guidance.

DimensionReasoningScore

Conciseness

The body is lean with no concept over-explanation, but some tokens are redundant (the When-to-Use list echoes the description) or trivial ('Use naturally in Claude Code conversations').

4 / 5

Actionability

Only the install command is executable; usage guidance is high-level ('Configure Exa API key', 'Use naturally') with no concrete API call examples or specific steps to execute a search.

2 / 5

Workflow Clarity

A rough three-step sequence is present but steps are poorly defined and lack any validation or concrete commands beyond installation.

2 / 5

Progressive Disclosure

Sections are well-organized for a short skill, but detail is offloaded to an external GitHub repo rather than one-level-deep bundled reference files.

4 / 5

Total

12

/

20

Passed

Description

78%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 well-structured description that clearly states capabilities and provides an explicit 'Use when' trigger clause with natural keywords. Its main weakness is moderate action specificity and some overlap with sibling search skills.

DimensionReasoningScore

Specificity

Names the domain (Exa API) and a few concrete actions ('semantic search, similar content discovery, and structured research') but the actions are not comprehensive and 'structured research' is somewhat abstract.

3 / 5

Completeness

Explicitly answers both 'what' (semantic search, similar content discovery, structured research via Exa API) and 'when' with a concrete 'Use when you need...' trigger clause.

5 / 5

Trigger Term Quality

Includes natural user phrases ('semantic/embeddings-based search', 'finding similar content', 'searching by category', 'research papers') with some synonyms, but lacks file extensions or a fuller synonym set.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (Exa semantic search) with distinct triggers, but overlaps with related web/search skills such as tavily-web and firecrawl-scraper listed in the body.

4 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.