research

Deep research into technical solutions by searching the web, examining GitHub repos, and gathering evidence. Use when the user explicitly says "use the research skill", "use a research agent", or asks for deep/thorough research into implementation options or technologies.

2.00x

Quality

79%

Does it follow best practices?

Impact

62%

2.00x

Average score across 3 eval scenarios

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./plugins/toolkit/skills/research/SKILL.md

Evaluation results

38%

12%

Cross-Platform Desktop Framework Evaluation

Structured research output format

Criteria

Without this skill

With this skill

Research heading format

Option sections present

100%

Source field per option

Pros field per option

30%

40%

Cons field per option

30%

40%

Evidence field per option

Recommendation section

100%

Sources cited in recommendation

Sources section

100%

Scratch directory used

64%

44%

Markdown Parser Library Selection

GitHub repo cloning and scratch workspace

Criteria

Without this skill

With this skill

Scratch directory created

Git clone used

70%

Repo structure examined

50%

100%

Research heading

Multiple options covered

100%

Source per option

100%

Pros per option

100%

Cons per option

100%

Evidence per option

Recommendation section

100%

Sources section

100%

Sources cite count

85%

38%

Message Queue Selection for Microservices Migration

Evidence requirements and recommendation format

Criteria

Without this skill

With this skill

Minimum 3 distinct sources

100%

Sources cite count in recommendation

100%

Sources section present

100%

Evidence field per option

70%

100%

Source field per option

100%

Scratch directory used

Research heading

Multiple options compared

100%

Pros field per option

100%

Cons field per option

100%

Recommendation section

100%

Repository: dwmkerr/claude-toolkit
Path: plugins/toolkit/skills/research/SKILL.md
Commit: 4316684

Evaluated: 6 months ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Markdown Parser Library Selection Message Queue Selection for Microservices Migration Cross-Platform Desktop Framework Evaluation

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.