research

Systematic technical investigation—evidence gathering, option comparison, and actionable recommendations. Use when the user asks to "research X", "investigate Y", "look into Z", "compare X vs Y", "how does X work", or needs analysis of libraries, APIs, frameworks, or architectural approaches.

Quality

91%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

100%

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

This is an excellent skill file that provides comprehensive, actionable guidance for technical research without unnecessary verbosity. The structured workflow, concrete tool usage examples, and domain-specific investigation checklists (library evaluation, API comparison, architectural decisions) make it immediately useful. The output template ensures consistent, decision-ready deliverables.

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient, assuming Claude's competence as a staff-level engineer. No unnecessary explanations of basic concepts; every section provides actionable guidance without padding.	3 / 3
Actionability	Provides concrete tool commands (WebSearch, Context7, Grep/Glob), specific investigation checklists for different research types, and a complete markdown template for output structure. Highly executable guidance.	3 / 3
Workflow Clarity	Clear 5-step workflow with explicit sequencing (Scope → Gather → Evaluate → Synthesize → Cite). Each step has concrete substeps and the source evaluation hierarchy provides a validation framework for research quality.	3 / 3
Progressive Disclosure	Well-structured overview with clear sections. References to external files (references/patterns.md, skills/FRAMEWORKS.md, RECIPE.md) are one level deep and clearly signaled in dedicated 'Reference Material' and 'See Also' sections.	3 / 3
	Total	12 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a solid description with excellent trigger term coverage and complete what/when guidance. The main weakness is that the capability description uses somewhat abstract terms ('evidence gathering', 'option comparison') rather than concrete actions, and the broad trigger terms like 'research' could potentially conflict with other skills.

Suggestions

Make capabilities more concrete by specifying actions like 'analyze documentation, benchmark alternatives, evaluate trade-offs, summarize findings'

Add distinguishing qualifiers to reduce conflict risk, such as specifying this is for 'technical/engineering research' vs general research or documentation lookup

Dimension	Reasoning	Score
Specificity	Names the domain (technical investigation) and lists some actions (evidence gathering, option comparison, actionable recommendations), but these are somewhat abstract rather than concrete specific actions like 'analyze API documentation' or 'benchmark performance'.	2 / 3
Completeness	Clearly answers both what (systematic technical investigation with evidence gathering, option comparison, recommendations) AND when (explicit 'Use when...' clause with multiple trigger phrases and specific use cases).	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'research X', 'investigate Y', 'look into Z', 'compare X vs Y', 'how does X work', plus domain terms like 'libraries, APIs, frameworks, architectural approaches'.	3 / 3
Distinctiveness Conflict Risk	While it specifies 'technical investigation' and lists specific domains (libraries, APIs, frameworks), terms like 'research' and 'how does X work' could overlap with documentation skills or general Q&A skills.	2 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: tslateman/duet
Commit: c3b1fc2

Reviewed: 3 months 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.