CtrlK
BlogDocsLog inGet started
Tessl Logo

wigolo-research

Local-first multi-step research with question decomposition, parallel search, structured briefs, cross-references, and gap analysis. Use when the user needs comprehensive analysis, comparison reports, literature reviews, or says "research", "compare X vs Y", "deep dive", "thorough analysis", "find everything about". Returns a structured `brief` with `topics`, `highlights`, `key_findings`, `sections.overview.cross_references`, `sections.comparison`, `sections.gaps`.

73

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, highly actionable body: executable invocation examples for every mode, a concrete depth/source table, and a clean pointer to synthesis rules. The main issues are the redundant split between 'Anti-Patterns' and 'When NOT to use', and the unexplained MCP-sampling-available output branch.

Suggestions

Merge the 'Anti-Patterns' and 'When NOT to use wigolo-research' sections into one section — both cover the same single-shot/simple-lookup exclusion and the duplication wastes tokens.

Briefly state what the output looks like when MCP sampling IS available, since 'When MCP sampling is unavailable (common case)' implies an alternative result shape that is never described.

Clarify the relationship between the 'highlights' and 'key_findings' brief fields (both appear in the output schema and the description) so the report-writing steps map unambiguously onto the brief.

DimensionReasoningScore

Conciseness

The body is lean — JSON quick-reference examples, a compact depth table, a commented output schema, and terse numbered steps — with no re-teaching of concepts Claude knows. However, the 'Anti-Patterns' bullet 'DON'T use for single-URL lookups — use fetch instead' and the 'When NOT to use' section 'You want a single-shot search result... use search' redundantly cover the same not-for-this guidance and could be merged into one section.

4 / 5

Actionability

Provides copy-ready invocations for all depth levels plus domain-scoped and schema-output variants, a concrete 'max_sources' cap of 50, a 6-step report-writing procedure keyed to specific brief fields, and explicit alternative tools (fetch, agent, search) for each anti-pattern.

5 / 5

Workflow Clarity

The report-writing sequence is clearly ordered and the guarantee that gaps are 'never silently dropped' acts as a completeness check. But 'When MCP sampling is unavailable (common case)' implies an alternative output shape that is never described, leaving an unaddressed branch in the workflow.

4 / 5

Progressive Disclosure

A short (~80 line), well-sectioned overview that keeps detail in one-level-deep, clearly signaled references (wigolo/rules/synthesis.md and the sibling skill docs) while inlining only the 'Quick version' of the report procedure — easy to navigate with no buried or nested references.

5 / 5

Total

18

/

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 that concretely states capabilities, enumerates the output structure, and provides a rich set of natural trigger phrases covering both what and when. Its only weakness is that broad trigger terms leave minor conflict risk with closely related single-query search skills.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'question decomposition, parallel search, structured briefs, cross-references, and gap analysis' — and concretely enumerates the returned structure ('topics', 'highlights', 'key_findings', 'sections.overview.cross_references', 'sections.comparison', 'sections.gaps'), giving comprehensive coverage rather than minor gaps.

5 / 5

Completeness

Explicitly answers both what ('Local-first multi-step research with question decomposition, parallel search, structured briefs, cross-references, and gap analysis' plus the returned brief structure) and when ('Use when the user needs comprehensive analysis, comparison reports, literature reviews, or says...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes eight natural user phrasings — "research", "compare X vs Y", "deep dive", "thorough analysis", "find everything about", plus 'comprehensive analysis', 'comparison reports', 'literature reviews' — which comprehensively cover how users naturally request research work.

5 / 5

Distinctiveness Conflict Risk

The 'multi-step research' + structured-brief framing carves a clear niche, but broad triggers like 'thorough analysis' and 'find everything about' carry minor overlap risk with the closely related wigolo-search/wigolo-agent sibling skills; the description itself (unlike the body) does not disambiguate against them.

4 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 4 suspicious

Warning

Total

15

/

16

Passed

Repository
KnockOutEZ/wigolo
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.