searxng-search

Enhanced web and package repository search using local SearXNG instance

3.80x

Quality

62%

Does it follow best practices?

Impact

95%

3.80x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./searxng-search/SKILL.md

Quality

Content

71%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 highly actionable with ready-to-run commands and a clear start/stop workflow, but it carries some redundancy around the PyPI workaround and inlines container-config detail that belongs in a reference. Two existing reference files are also orphaned from the body.

Suggestions

Consolidate the PyPI guidance: state the workaround once and link to references/pypi-direct-search.md instead of re-explaining it in Common Usage, the Workaround section, and Known Issues.

Move the Manual Container Start and Advanced Config blocks into a reference file (e.g., references/container-config.md) and link from the Configuration section.

Link the orphaned reference files from the body — add pointers to references/agent-usage.md and references/category-guide.md in the relevant sections so they are discoverable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but the opening 'SearXNG is a privacy-respecting metasearch engine...' is mild over-explanation, and the PyPI situation is re-explained across Common Usage, a dedicated Workaround section, and Known Issues.	3 / 5
Actionability	Abundant copy-paste-ready curl + jq commands organized by task cover the common cases (web, cargo, npm, repos, IT) with concrete URLs, filters, and parsing examples.	5 / 5
Workflow Clarity	Quick Start sequences start -> ready-check (built into start-searxng) -> stop clearly, and a Debugging section supports error recovery; the search step itself is single-action, though an explicit 'verify the instance is up before searching' checkpoint is only implicit.	4 / 5
Progressive Disclosure	Sections are well-organized and two references are clearly linked, but a substantial Manual Container Start / Advanced Config block is inlined that could live in a reference, and two bundle files (agent-usage.md, category-guide.md) are present but never linked from the body.	3 / 5
	Total	15 / 20 Passed

Description

53%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.

The description clearly states what the skill does and names a specific tool, but it lacks any explicit 'when to use' trigger guidance and its action vocabulary is thin. Adding a 'Use when...' clause with natural trigger phrases would raise completeness and trigger-term quality.

Suggestions

Add a 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when the user wants to search the web or package registries via a local, privacy-respecting metasearch engine').

Broaden trigger terms to include natural phrasings like 'search packages', 'npm search', 'PyPI search', 'find Rust crates', or 'search code repos'.

Replace the filler word 'Enhanced' with a concrete capability to improve specificity (e.g., 'Run a local SearXNG instance to aggregate web and package-registry search results as JSON').

Dimension	Reasoning	Score
Specificity	Names the domain ('web and package repository search') and the concrete mechanism ('using local SearXNG instance'), but the action 'search' is generic and coverage is not comprehensive — it stops short of listing the kinds of searches supported.	3 / 5
Completeness	Has a clear 'what' (enhanced web and package repository search via local SearXNG) but no 'when' clause or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant natural keywords ('web search', 'package repository search', 'SearXNG') but misses common variations users would say such as 'find packages', 'npm search', 'PyPI search', or specific registry names.	3 / 5
Distinctiveness Conflict Risk	The 'local SearXNG instance' framing carves a fairly distinct niche away from generic search skills, with only minor overlap risk with closely related web-search tools.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: YPares/agent-skills
Path: searxng-search/SKILL.md
Commit: e9d2149

Reviewed: 3 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.