CtrlK
BlogDocsLog inGet started
Tessl Logo

searxng-search

Enhanced web and package repository search using local SearXNG instance

65

3.80x
Quality

48%

Does it follow best practices?

Impact

95%

3.80x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./searxng-search/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

64%

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

This is a highly actionable skill with excellent concrete examples and copy-paste-ready commands covering a wide range of search use cases. Its main weaknesses are length and organization — the manual container configuration, PyPI workarounds, and Nushell integration could be moved to reference files to keep the main skill lean. The workflow could benefit from explicit validation checkpoints after starting the service.

Suggestions

Move the 'Manual Container Start', 'PyPI Workaround', and 'Nushell Integration' sections to separate reference files to reduce the main skill's token footprint

Add an explicit validation step after `start-searxng --detach`, e.g., 'Verify: `curl -s http://localhost:8888/config | jq .brand.name`' to confirm the service is ready

Remove the introductory sentence explaining what SearXNG is — Claude doesn't need this context

DimensionReasoningScore

Conciseness

The skill is fairly comprehensive but includes some unnecessary verbosity — the introductory sentence explaining what SearXNG is, the manual container start section duplicating what the helper script does, and the extensive PyPI workaround section add bulk. The Nushell integration section is nice but niche. Overall it could be tightened significantly.

2 / 3

Actionability

Excellent actionability throughout — every section provides concrete, copy-paste-ready curl commands with jq filters, executable bash scripts, and specific examples with real package names (tokio, express, flask). The quick reference table is immediately usable.

3 / 3

Workflow Clarity

The start/stop lifecycle is clear, and the quick reference table provides good sequencing. However, there are no explicit validation checkpoints — for example, after starting SearXNG there's no step to verify it's actually running and responsive before proceeding to queries. The debugging section exists but isn't integrated into the workflow as validation steps.

2 / 3

Progressive Disclosure

References to `references/package-engine-status.md` and `references/pypi-direct-search.md` show some progressive disclosure, but the main file is quite long (~200+ lines) with configuration details, manual container setup, and Nushell integration that could be split into reference files. The inline PyPI workaround and manual config sections bloat the main skill.

2 / 3

Total

9

/

12

Passed

Description

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 lacks concrete actions, explicit trigger guidance, and natural user-facing keywords. It would benefit significantly from a 'Use when...' clause and more specific capability listing to help Claude distinguish it from other search-related skills.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to search the web, look up packages, find libraries, or needs online search results.'

List specific concrete actions such as 'search the web for information, query package repositories (npm, PyPI, crates.io), aggregate results from multiple search engines.'

Include natural trigger terms users would say, such as 'search online', 'find a package', 'look up', 'search for', and specific package manager names.

DimensionReasoningScore

Specificity

Names the domain (web and package repository search) and the tool (SearXNG), but does not list specific concrete actions like 'query packages', 'filter results', or 'aggregate search results'.

2 / 3

Completeness

Provides a partial 'what' (enhanced search using SearXNG) 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 1.

1 / 3

Trigger Term Quality

Includes relevant terms like 'web search', 'package repository search', and 'SearXNG', but misses common user-facing variations such as 'search the web', 'find packages', 'look up', 'npm', 'pypi', or 'search online'.

2 / 3

Distinctiveness Conflict Risk

Mentioning 'SearXNG' and 'local instance' adds some distinctiveness, but 'web search' is very broad and could easily overlap with other search-related skills. The 'package repository search' aspect helps somewhat but isn't strongly delineated.

2 / 3

Total

7

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
YPares/agent-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.