Name: research-summarizer
Rating: 72 (1 reviews)
Author: alirezarezvani

research-summarizer

Structured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and documentation. Extracts key findings, generates comparative analyses, and produces properly formatted citations. Use when: user wants to summarize a research paper, compare multiple sources, extract citations from documents, or create structured research briefs. Plugin for Claude Code, Codex, Gemini CLI, and OpenClaw.

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

The canonical home for this skill is research-summarizer in alirezarezvani/claude-skills

Quality

Content

88%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 well-organized, highly actionable skill body with clear multi-step workflows and a strong verification loop. The main weakness is progressive disclosure: the body references scripts and reference files that are not bundled, and template content is duplicated between inline scaffolds and the cited reference.

Suggestions

Bundle the referenced files (scripts/extract_citations.py, scripts/format_summary.py, references/summary-templates.md, references/citation-formats.md, scripts/convert.sh) or remove the references if the inline scaffolds already cover the content.

De-duplicate the quality assessment guidance — keep it in one place (either Workflow 1 step 3 or the Quality Assessment Framework table) rather than restating it twice.

Trim the opening marketing prose ('Read less. Understand more. Cite correctly.' and 'Built for product managers...') to reduce tokens that do not aid execution.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no explanations of what citations or IMRAD are), but quality assessment appears twice (Workflow 1 step 3 and the Quality Assessment Framework table) and the marketing tagline/opening prose could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready CLI commands ('python3 scripts/extract_citations.py document.txt --output json', 'python3 scripts/format_summary.py --template academic') and fully specified scaffold templates covering all three workflows and common cases.	5 / 5
Workflow Clarity	Three workflows are clearly sequenced with numbered steps, and a dedicated Verification Loop provides an explicit checklist with feedback loops (e.g., citation total must match bibliography count; investigate any gap) satisfying the batch-operation validation requirement.	5 / 5
Progressive Disclosure	Good section structure with clearly signaled one-level-deep references ('See references/summary-templates.md', 'See references/citation-formats.md'), but those referenced files and the cited scripts are not present in the bundle, and summary templates are duplicated inline and in the reference.	4 / 5
	Total	18 / 20 Passed

Description

88%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, third-person description that clearly states capabilities and provides explicit, natural trigger phrases for when to activate. Minor gaps in synonym/extension coverage and disambiguation keep trigger quality and distinctiveness just below full marks.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Extracts key findings, generates comparative analyses, and produces properly formatted citations' — across a named domain set (papers, articles, reports, documentation), giving comprehensive coverage of the summarization capability.	5 / 5
Completeness	Explicitly answers both 'what' (handles source types, extracts findings, generates comparisons, formats citations) and 'when' via a 'Use when:' clause with four concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger phrases ('summarize a research paper', 'compare multiple sources', 'extract citations from documents', 'create structured research briefs') but omits synonyms and file extensions like .pdf, so a few natural terms are missing.	4 / 5
Distinctiveness Conflict Risk	The research-brief/citation-comparison niche is mostly distinct, but 'summarize a research paper' could overlap with a generic summarizer skill and the description does not actively disambiguate from related research skills.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 15 missing	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/research-summarizer/SKILL.md
Commit: 19392f7

Reviewed: ~3 hours 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.