research

Researches a topic by breaking it into subtopics, gathering factual information with reasoning, and producing a structured summary with key findings and open questions. Use when the user asks to research, investigate, look up, summarize a topic, or says 'what is known about...' or 'learn about...'

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

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

A compact, well-organized instruction skill with a clear sequenced workflow, a reusable output template, and a worked example that make it readily actionable. The only real weakness is the example's embedded dated facts and vendor specifics, which add tokens and will go stale over time.

Suggestions

Replace the dated/factual specifics in the example (e.g., 'since 2017', '1.1-1.5x native speed', vendor names) with placeholder-style content so the example illustrates format without going stale and consuming tokens on time-sensitive detail.

If real-world grounding is desired for the example, move such specifics to a separate references file so the main body stays lean and evergreen.

Dimension	Reasoning	Score
Conciseness	The instructions and output template are lean and avoid explaining concepts Claude already knows, but the worked WebAssembly example embeds time-sensitive specifics ('since 2017', '1.1-1.5x native speed', named vendors) that can go stale and add tokens, matching the level-2 'mostly efficient but could be tightened' anchor rather than a fully lean level-3.	2 / 3
Actionability	Provides a concrete sequenced process with a specific subtopic count (3-5) plus a copy-paste-ready output template and a filled-in example, giving actionable guidance for an instruction-only skill; not below 3 because the guidance is specific and immediately usable.	3 / 3
Workflow Clarity	The five numbered steps form a clear, ordered sequence that flows directly into the structured output format; research is not a destructive or batch operation so the missing-validation cap does not apply, and for a simple skill this clear sequencing earns the top anchor.	3 / 3
Progressive Disclosure	This is a simple, under-50-line skill with no bundle files and no need for external references; content is organized into clearly labeled sections (Instructions, Output Format, Example Output), which per the rubric's simple-skills note earns the top score on well-organized sections alone.	3 / 3
	Total	11 / 12 Passed

Description

92%

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 well-constructed description with concrete actions, strong natural trigger phrasing, and explicit what-and-when guidance written in correct third-person voice. Its main weakness is the breadth of the research domain, which leaves some overlap risk with related summarization or lookup skills.

Suggestions

Narrow the trigger scope or add a distinguishing qualifier (e.g., 'when the user wants a structured, multi-subtopic synthesis rather than a quick fact lookup') to reduce overlap with general search/summarize skills.

Consider signaling the deliverable format (a structured summary with TL;DR, findings, and open questions) more explicitly in the description so it is distinguishable from simple lookups.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'breaking it into subtopics, gathering factual information with reasoning, and producing a structured summary with key findings and open questions' — matching the level-3 anchor of several specific concrete actions; it goes beyond naming a domain.	3 / 3
Completeness	Explicitly answers both what (the research/summary process) and when via a clear 'Use when...' clause with concrete triggers, satisfying the level-3 anchor; it is not 2 because the trigger guidance is explicit rather than implied.	3 / 3
Trigger Term Quality	Natural user phrasings are well covered: 'research, investigate, look up, summarize a topic, or says what is known about... or learn about...', which are terms a user would naturally say; not below 3 because common variations are present, not above since the scale tops at 3.	3 / 3
Distinctiveness Conflict Risk	Triggers are distinct enough to avoid most confusion, but 'research/summarize/look up/learn about' is a broad domain that could overlap with general summarization or web-search skills, matching the level-2 'somewhat specific but could still overlap' anchor rather than a clear niche.	2 / 3
	Total	11 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: open-gitagent/opengap
Path: examples/lyzr-agent/skills/research/SKILL.md
Commit: d7a8e2e

Reviewed: 4 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.