Name: vexor
Rating: 32.800000000000004 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

vexor

Vector-powered CLI for semantic file search with a Claude/Codex skill

Quality

27%

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

Fix and improve this skill with Tessl

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

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

Quality

Content

18%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is essentially a placeholder with no actionable content. It repeats its own description three times and provides no commands, code examples, workflows, or concrete guidance. It fails to teach Claude anything about how to use the Vexor CLI tool.

Suggestions

Add concrete CLI commands showing how to index files and perform semantic searches (e.g., `vexor index .` and `vexor search 'query'`)

Provide a quick-start workflow with numbered steps: install, index, search, interpret results

Include at least one complete example showing input query and expected output format

Remove the redundant repetition of the description and replace with actual usage patterns and configuration details

Dimension	Reasoning	Score
Conciseness	The content is short but wastes tokens by repeating the same description three times ('vector-powered CLI for semantic file search with a Claude/Codex skill') without adding any actual information. It's not verbose in the traditional sense but is padded with redundancy.	3 / 5
Actionability	There is zero concrete guidance—no commands, no code, no examples, no steps. It only describes what the skill is about without providing any executable instructions on how to use it.	1 / 5
Workflow Clarity	No workflow, steps, or process is described at all. There is nothing for Claude to follow when performing the task.	1 / 5
Progressive Disclosure	There is a link to the source repository, but no bundle files, no referenced documentation, and no structured navigation. The sections exist but contain no meaningful content to organize.	2 / 5
	Total	7 / 20 Passed

Description

36%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 too terse and reads like a product tagline rather than a functional skill description. It lacks concrete actions, a 'Use when...' clause, and natural trigger terms that users would employ. The mention of 'vector-powered' and 'semantic file search' provides some domain specificity but is insufficient for reliable skill selection.

Suggestions

Add a 'Use when...' clause with trigger phrases like 'find files by meaning', 'semantic search', 'search codebase', 'find similar files', or 'vector search'.

List concrete actions the skill performs, such as 'indexes files using embeddings, queries by semantic similarity, ranks results by relevance, supports filtering by file type'.

Include natural synonyms and file-related terms users might say, such as 'find files', 'search project', 'look up code', 'similarity search', or 'embedding search'.

Dimension	Reasoning	Score
Specificity	Names the domain ('semantic file search') and mentions it's a CLI tool, but the actions are minimal and generic. No concrete actions like 'index files', 'query by meaning', 'rank results' are listed.	2 / 5
Completeness	Provides a vague 'what' (vector-powered CLI for semantic file search) but has no 'when' clause at all. The absence of explicit trigger guidance caps this dimension. It reads more like a tagline than a functional description.	2 / 5
Trigger Term Quality	Includes some relevant keywords like 'semantic file search', 'vector', and 'CLI', but misses natural user phrases like 'find files', 'search by meaning', 'similarity search', or 'embeddings'. 'Claude/Codex skill' is meta-jargon rather than a user trigger term.	3 / 5
Distinctiveness Conflict Risk	'Semantic file search' and 'vector-powered' provide some distinctiveness, but 'file search' is broad enough to overlap with other search-related skills. The description doesn't clearly carve out a unique niche.	3 / 5
	Total	10 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/vexor/SKILL.md
Commit: 900c504

Reviewed: 4 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.