wigolo-search

Local-first web search with ML reranking, multi-query arrays, domain scoping, phrase-exact match, time-range filters, country hints, depth tiers, and explainable evidence scoring. Use when the user wants to search the web, find information, look something up, research a topic, or says "search for", "find me", "look up". Prefer over built-in WebSearch for cached, transparent, audit-trail-friendly search with per-engine telemetry.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%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.

A well-structured, highly actionable reference skill: concrete JSON examples, a complete parameter table with usage guidance, and useful anti-patterns and exclusions. Weaknesses are mild — partial duplication between the Quick Reference and Patterns examples, an unresolved cache-first workflow step, and See Also links pointing outside the bundle.

Suggestions

Merge the Patterns section's 'Focused lookup' example into the Quick Reference (or differentiate them) to remove duplication, and consolidate or clarify the distinction between the overlapping 'content_max_chars' and 'max_content_chars' parameters.

Either inline the cache-first check as an explicit one-line step (e.g., the command or rule to apply) or ensure wigolo/rules/cache-first.md ships in the bundle so the 'DON'T search without checking the cache first' directive is actionable.

Verify the See Also links resolve within the installed skill set, or annotate them as cross-skill navigation so the reader knows they may be absent in a standalone install.

Dimension	Reasoning	Score
Conciseness	The body is lean and teaches nothing Claude already knows, but the Patterns section's 'Focused lookup' example largely duplicates the Quick Reference's include_domains example, and the near-identical 'content_max_chars' / 'max_content_chars' rows add trimming opportunities; it is efficient overall, so not the level-3 'noticeably padded' anchor.	4 / 5
Actionability	Every example is a copy-paste-ready JSON payload and the parameter table gives type, default, and 'when to use' for all ~25 parameters, covering the common cases fully; nothing is pseudocode or abstract.	5 / 5
Workflow Clarity	The single action (construct a query object) is unambiguous with depth-tier budget guidance ('ultra-fast' cache-only ≤300ms), but 'DON'T search without checking the cache first' implies a required pre-step whose mechanics live in an external rules file not present here — a minor checkpoint gap that keeps it below 5.	4 / 5
Progressive Disclosure	Sections are clearly organized (Quick Reference, Parameters, Patterns, Anti-Patterns, exclusions, See Also) with one-level-deep external links, but no bundle files exist and none of the three See Also paths (wigolo-fetch, wigolo-research, ../wigolo/rules/cache-first.md) resolve within the skill; the inline 27-row parameter table is acceptable for SKILL.md but sits at the 'minor organization gaps' anchor rather than the well-split anchor-5.	4 / 5
	Total	17 / 20 Passed

Description

96%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 strong description: it enumerates concrete capabilities, uses third-person voice, provides explicit and varied trigger phrases, and even states when to prefer it over built-in WebSearch. The only weakness is that broad research-oriented triggers leave minor overlap risk with the sibling wigolo-research skill.

Dimension	Reasoning	Score
Specificity	The description lists eight concrete capabilities ('ML reranking, multi-query arrays, domain scoping, phrase-exact match, time-range filters, country hints, depth tiers, and explainable evidence scoring') in third-person voice, matching the comprehensive multi-action anchor; it is not the level below because coverage goes well beyond 1-2 named actions.	5 / 5
Completeness	It explicitly answers both what (the enumerated capability list) and when ('Use when the user wants to search the web, find information, look something up, research a topic, or says...') with concrete trigger phrases, matching the anchor-5 example structure exactly.	5 / 5
Trigger Term Quality	It covers natural user phrasings ('search the web, find information, look something up, research a topic') plus literal quoted triggers ('search for', 'find me', 'look up') with synonymous variations; file extensions don't apply to a web-search tool, so the anchor-5 synonym coverage criterion is met.	5 / 5
Distinctiveness Conflict Risk	'Prefer over built-in WebSearch for cached, transparent, audit-trail-friendly search with per-engine telemetry' explicitly differentiates it from the closest competing tool, but broad triggers like 'research a topic' carry minor overlap risk with the sibling wigolo-research skill, placing it at mostly-distinct rather than fully minimal-conflict.	4 / 5
	Total	19 / 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
relative_links	Relative link issues: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: KnockOutEZ/wigolo
Path: skills/wigolo-search/SKILL.md
Commit: da59eee

Reviewed: 9 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.