CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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`.

Quality

84%

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

78%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, dense body with excellent token efficiency and copy-paste invocations, and a clear report-writing sequence. The main weakness is structural: the skill's essential synthesis rules live in an unbundled file referenced via a fragile cross-directory path, and one referenced output field (`citations`) is never shown.

Suggestions

Bundle the report-writing rules inside the skill (e.g., references/synthesis.md) and reference it with a path relative to SKILL.md, so the core workflow doesn't depend on sibling-directory layout.

Add the `citations` field to the output example so step 6 ('Cite with [N] format from citations') is grounded in the documented schema.

Add a brief finishing check to the report workflow (e.g., confirm every sub-query and named entity is either covered or listed in sections.gaps before completing).

DimensionReasoningScore

Conciseness

Lean and dense throughout: a compact invocation quick-reference, a depth table instead of prose, a skeletal output schema with inline comments, and terse anti-pattern bullets. Nothing re-teaches concepts Claude already knows; every section earns its place.

5 / 5

Actionability

The Quick Reference gives copy-paste-ready invocations covering standard, comprehensive, quick, domain-scoped, and schema-constrained cases, plus a concrete depth/max_sources tuning knob. Not a 5: step 6 says 'Cite with [N] format from `citations`' but a `citations` field never appears in the output example, and the actual synthesis instructions are delegated elsewhere.

4 / 5

Workflow Clarity

'Writing the Report' gives a clear numbered 6-step sequence with each step mapped to its source field, and the gaps guarantee ('never silently dropped') acts as a soft completeness check. Not a 5: there are no explicit validation checkpoints (e.g., verifying every sub-query is covered before finishing), though the non-destructive nature means the missing-validation cap does not apply.

4 / 5

Progressive Disclosure

The body is short and well-sectioned with clearly signaled references, but the bundle contains no reference files at all, and the core report-writing rules are delegated to '../wigolo/rules/synthesis.md' — a relative path outside the skill's own directory that does not resolve within this bundle. Navigation therefore depends on unverifiable sibling layout rather than a bundled references/ file, which is more than a minor organization gap.

3 / 5

Total

16

/

20

Passed

Description

83%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 states concrete capabilities, explicit 'Use when' triggers with natural phrases, and a precise output contract. It sits just below top marks on specificity and trigger coverage due to a few abstract terms and missing common synonyms.

DimensionReasoningScore

Specificity

Lists several concrete capabilities ('question decomposition, parallel search, structured briefs, cross-references, and gap analysis') plus concrete output fields ('key_findings', 'sections.comparison', 'sections.gaps'). Not a 5 because 'local-first' and 'cross-references' are somewhat abstract, and the back half of the description is output-schema detail rather than additional actions.

4 / 5

Completeness

Explicitly answers both: what ('multi-step research with question decomposition, parallel search, structured briefs...') and when ('Use when the user needs comprehensive analysis... or says "research", "compare X vs Y"...') with concrete trigger phrases, matching the anchor-5 example shape. A 4 would require the 'when' clause to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Good natural-language coverage: 'research', 'compare X vs Y', 'deep dive', 'thorough analysis', 'find everything about', plus use cases like 'comparison reports' and 'literature reviews'. Not a 5 because common variations such as 'investigate', 'look into', 'survey', or 'background on' are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche (multi-source synthesis into structured briefs) with distinct triggers that differ from single-shot search terms. Only minor overlap risk with generic search/report skills; the description itself doesn't disambiguate against plain search, keeping it just below a 5.

4 / 5

Total

17

/

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

Path

skills/wigolo-research/SKILL.md

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.