searxng-search

Enhanced web and package repository search using local SearXNG instance

3.80x

Quality

52%

Does it follow best practices?

Impact

95%

3.80x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./searxng-search/SKILL.md

Quality

Discovery

32%

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 identifies the tool (SearXNG) and general domain (web and package repository search) but is too terse to be effective for skill selection. It lacks explicit trigger guidance ('Use when...'), specific concrete actions, and natural user-facing keywords that would help Claude reliably choose this skill over alternatives.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to search the web, look up packages, find library documentation, or query online resources.'

List specific concrete actions such as 'search the web for documentation, look up package versions on npm/pypi/crates.io, find code examples online.'

Include natural trigger terms users would say, such as 'search online', 'look up', 'find a package', 'google', 'search for', along with specific package registry names.

Dimension	Reasoning	Score
Specificity	Names the domain (web and package repository search) and the tool (SearXNG), but does not list specific concrete actions like 'search for packages', 'query documentation', 'find library versions', etc.	2 / 3
Completeness	Describes what it does at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also weak, so this scores a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'web search', 'package repository search', and 'SearXNG', but misses common user-facing variations like 'look up', 'find online', 'search the web', 'npm', 'pypi', or other package manager names users might mention.	2 / 3
Distinctiveness Conflict Risk	The mention of 'SearXNG' and 'package repository' adds some distinctiveness, but 'web search' is quite generic and could overlap with any general search or browsing skill.	2 / 3
	Total	7 / 12 Passed

Implementation

72%

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

This is a solid, highly actionable skill with excellent concrete examples and good progressive disclosure. Its main weaknesses are moderate verbosity (the PyPI workaround and manual config sections could be moved to reference files) and the lack of explicit validation checkpoints in the start-then-search workflow. The quick reference table and usage patterns are particularly strong.

Suggestions

Move the PyPI workaround and manual container start sections to reference files to reduce the main skill's token footprint

Add an explicit validation step after `start-searxng --detach` (e.g., `curl -s http://localhost:8888/config | jq '.instance_name'` to confirm it's running before proceeding to searches)

Remove the opening paragraph explaining what SearXNG is - Claude doesn't need this context

Dimension	Reasoning	Score
Conciseness	The skill is fairly comprehensive but includes some unnecessary verbosity - the PyPI workaround section is extensive, the manual container start section duplicates what the helper script does, and some explanatory text could be trimmed. The introductory sentence explaining what SearXNG is is unnecessary context for Claude.	2 / 3
Actionability	Excellent actionability throughout - every section provides concrete, copy-paste ready commands with curl, jq, and bash. The quick reference table, usage patterns, and debugging commands are all fully executable with specific URLs and parameters.	3 / 3
Workflow Clarity	The start/stop workflow is clear, and individual search patterns are well-documented. However, there's no explicit validation step after starting SearXNG (e.g., verify it's running before searching), and the overall workflow of start → search → process results lacks explicit sequencing with checkpoints.	2 / 3
Progressive Disclosure	Well-structured with a quick start, quick reference table, then progressively more detailed sections. References to external files (package-engine-status.md, pypi-direct-search.md) are one level deep and clearly signaled. Content is logically organized from basic to advanced.	3 / 3
	Total	10 / 12 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: YPares/agent-skills
Commit: aed1afb

Reviewed: 2 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.