Use a research report summarizer to turn supplied papers and market reports into a decision-focused brief. Tell your assistant what question the team needs to answer; this Skill organizes findings, methods, evidence quality and limitations, helping operators compare sources and keep the reasons behind each conclusion visible.
Long reports often contain useful findings alongside assumptions that are easy to lose in a short summary. This Skill uses structured templates to keep the result, method and limitations together, with room to compare several documents against the same decision question.
Use it after collecting the source material. It does not search the web for missing reports, and citation candidates must be checked against the original document. If a PDF cannot be read directly, extract its text with a suitable tool before asking for the summary.
Findings, methods and limitations have separate places in the summary. That makes it easier to distinguish a conclusion supported by the supplied study from an interpretation that may not apply to your product category or market.
Comparison templates and citation candidates make follow-up review easier. Keep the original documents available so important numbers and quoted claims can be verified before they appear in a strategy deck, public article or commercial proposal.
Papers, reports, or extracted document text, the decision question, desired detail, and citation style.
Use a Skill-capable agent with file access. Python 3 is required for the bundled Python helpers; inspect their sample schemas before supplying data.
It does not discover sources on the web. Citation extraction uses patterns and needs verification against the original document; PDF text extraction may require another tool.
Copy this request into Codex or Claude Code. The assistant downloads the original repository at the specified commit, installs the complete files and checks required dependencies.
Install research-summarizer in the app I am using and carry out the file installation, not just explain it.
Original repository: https://github.com/alirezarezvani/claude-skills.git
Commit: 6d2f02ea077eead1bee5411a31bcc6db5a11a70c
Skill folder: product-team/research-summarizer/skills/research-summarizer
1. Download this exact source into a new directory. Read SKILL.md and its setup references before running any bundled scripts. Do not substitute another author’s package.
2. For Codex, use ~/.agents/skills/research-summarizer; for Claude Code, use ~/.claude/skills/research-summarizer. Install only for my current app. Install the complete Skill folder, including scripts, references, assets and bundled notices. Keep any root license with the installed folder. Check all destination folders first; if any already exist, report differences before replacing them.
3. Compare the source and installed file lists and hashes. Inspect documented runtimes, dependencies and required connections. Configure only the local dependencies needed for this Skill; use an isolated environment when appropriate. Ask me to complete any account login locally, without putting credentials in chat.
4. Report the source commit, actual installation path, file-check results and any remaining runtime setup. Explain how to invoke research-summarizer in this app. Check discovery separately from file copying; start a new session if needed. Do not run production tasks or claim a successful business outcome from installation alone.This is the unchanged source SKILL.md for the reviewed version. Install the complete package to retain referenced scripts, assets, and instructions. Starter prompts below are EcomAgentTools examples.
---
name: "research-summarizer"
description: "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."
license: MIT
metadata:
version: 1.0.0
author: Alireza Rezvani
category: product
updated: 2026-03-16
---
# Research Summarizer
> Read less. Understand more. Cite correctly.
Structured research summarization workflow that turns dense source material into actionable briefs. Built for product managers, analysts, founders, and anyone who reads more than they should have to.
Not a generic "summarize this" — a repeatable framework that extracts what matters, compares across sources, and formats citations properly.
---
## Scope — Distinct From the research/ Domain
This skill summarizes **documents the user already has** (papers, articles, reports pasted or attached). It performs no web search and needs no MCP server. It is NOT:
- `research/litreview` — academic literature *discovery* and review-guide generation (finds papers via Consensus/academic APIs)
- `research/dossier` — entity due-diligence built from live web research
- `research/notebooklm` — drives Google's NotebookLM product UI
- `research/research` — the router for open-ended "research [topic]" requests that require searching
If the user asks you to *find* sources rather than digest supplied ones, route to the research/ domain instead.
---
## When This Skill Activates
Recognize these patterns from the user:
- "Summarize this paper / article / report"
- "What are the key findings in this document?"
- "Compare these sources"
- "Extract citations from this PDF"
- "Give me a research brief on [topic]"
- "Break down this whitepaper"
- Any request involving: summarize, research brief, literature review, citation, source comparison
If the user has a document and wants structured understanding → this skill applies.
---
## Workflow
### Workflow 1 — Single Source Summary
1. **Identify source type**
- Academic paper → use IMRAD structure (Introduction, Methods, Results, Analysis, Discussion)
- Web article → use claim-evidence-implication structure
- Technical report → use executive summary structure
- Documentation → use reference summary structure
2. **Scaffold the brief** — `python3 scripts/format_summary.py --template academic` (or `article`/`report`/`executive` per source type), then fill in every section from the source:
```
Title: [exact title]
Author(s): [names]
Date: [publication date]
Source Type: [paper | article | report | documentation]
## Key Thesis
[1-2 sentences: the central argument or finding]
## Key Findings
1. [Finding with supporting evidence]
2. [Finding with supporting evidence]
3. [Finding with supporting evidence]
## Methodology
[How they arrived at these findings — data sources, sample size, approach]
## Limitations
- [What the source doesn't cover or gets wrong]
## Actionable Takeaways
- [What to do with this information]
## Notable Quotes
> "[Direct quote]" (p. X)
```
3. **Assess quality**
- Source credibility (peer-reviewed, reputable outlet, primary vs secondary)
- Evidence strength (data-backed, anecdotal, theoretical)
- Recency (when published, still relevant?)
- Bias indicators (funding source, author affiliation, methodology gaps)
### Workflow 2 — Multi-Source Comparison
1. **Collect sources** (2-5 documents)
2. **Summarize each** using the single-source workflow above
3. **Build comparison matrix**
```
| Dimension | Source A | Source B | Source C |
|------------------|-----------------|-----------------|-----------------|
| Central Thesis | ... | ... | ... |
| Methodology | ... | ... | ... |
| Key Finding | ... | ... | ... |
| Sample/Scope | ... | ... | ... |
| Credibility | High/Med/Low | High/Med/Low | High/Med/Low |
```
4. **Synthesize**
- Where do sources agree? (convergent findings = stronger signal)
- Where do they disagree? (divergent findings = needs investigation)
- What gaps exist across all sources?
- What's the weight of evidence for each position?
5. **Produce synthesis brief**
```
## Consensus Findings
[What most sources agree on]
## Contested Points
[Where sources disagree, with strongest evidence for each side]
## Gaps
[What none of the sources address]
## Recommendation
[Based on weight of evidence, what should the reader believe/do?]
```
### Workflow 3 — Citation Extraction
1. **Run the extractor** — `python3 scripts/extract_citations.py document.txt --output json` detects DOI/URL/author-year/numbered citations and deduplicates them
2. **Review and format** the extracted list in the requested style (APA 7 default); manually catch citations the regex missed
3. **Classify citations** by type:
- Primary sources (original research, data)
- Secondary sources (reviews, meta-analyses, commentary)
- Tertiary sources (textbooks, encyclopedias)
4. **Output** sorted bibliography with classification tags
Supported citation formats:
- **APA 7** (default) — social sciences, business
- **IEEE** — engineering, computer science
- **Chicago** — humanities, history
- **Harvard** — general academic
- **MLA 9** — arts, humanities
---
## Tooling
### `scripts/extract_citations.py`
CLI utility for extracting and formatting citations from text.
**Features:**
- Regex-based citation detection (DOI, URL, author-year, numbered references)
- Multiple output formats (APA, IEEE, Chicago, Harvard, MLA)
- JSON export for integration with reference managers
- Deduplication of repeated citations
**Usage:**
```bash
# Extract citations from a file (APA format, default)
python3 scripts/extract_citations.py document.txt
# Specify format
python3 scripts/extract_citations.py document.txt --format ieee
# JSON output
python3 scripts/extract_citations.py document.txt --format apa --output json
# From stdin
cat paper.txt | python3 scripts/extract_citations.py --stdin
```
### `scripts/format_summary.py`
CLI utility that emits **blank structured summary scaffolds** — you (the model) fill them in from the source. It does not analyze content itself.
**Features:**
- 6 templates: academic, article, report, executive, comparison, literature
- Configurable scaffold depth (brief, standard, detailed)
- Text and JSON output for downstream tooling
**Usage:**
```bash
# Generate structured summary template
python3 scripts/format_summary.py --template academic
# Brief executive summary format
python3 scripts/format_summary.py --template executive --length brief
# All templates listed
python3 scripts/format_summary.py --list-templates
# JSON output
python3 scripts/format_summary.py --template article --output json
```
---
## Quality Assessment Framework
Rate every source on four dimensions:
| Dimension | High | Medium | Low |
|-----------|------|--------|-----|
| **Credibility** | Peer-reviewed, established author | Reputable outlet, known author | Blog, unknown author, no review |
| **Evidence** | Large sample, rigorous method | Moderate data, sound approach | Anecdotal, no data, opinion |
| **Recency** | Published within 2 years | 2-5 years old | 5+ years, may be outdated |
| **Objectivity** | No conflicts, balanced view | Minor affiliations disclosed | Funded by interested party, one-sided |
**Overall Rating:**
- 4 Highs = Strong source — cite with confidence
- 2+ Mediums = Adequate source — cite with caveats
- 2+ Lows = Weak source — verify independently before citing
---
## Summary Templates
See `references/summary-templates.md` for:
- Academic paper summary template (IMRAD)
- Web article summary template (claim-evidence-implication)
- Technical report template (executive summary)
- Comparative analysis template (matrix + synthesis)
- Literature review template (thematic organization)
See `references/citation-formats.md` for:
- APA 7 formatting rules and examples
- IEEE formatting rules and examples
- Chicago, Harvard, MLA quick reference
---
## Proactive Triggers
Flag these without being asked:
- **Source has no date** → Note it. Undated sources lose credibility points.
- **Source contradicts other sources** → Highlight the contradiction explicitly. Don't paper over disagreements.
- **Source is behind a paywall** → Note limited access. Suggest alternatives if known.
- **User provides only one source for a compare** → Ask for at least one more. Comparison needs 2+.
- **Citations are incomplete** → Flag missing fields (year, author, title). Don't invent metadata.
- **Source is 5+ years old in a fast-moving field** → Warn about potential obsolescence.
---
## Installation
### One-liner (any tool)
```bash
git clone https://github.com/alirezarezvani/claude-skills.git
cp -r claude-skills/product-team/research-summarizer ~/.claude/skills/
```
### Multi-tool install (run from the claude-skills repo root)
```bash
./scripts/convert.sh --skill research-summarizer --tool codex|gemini|cursor|windsurf|openclaw
```
### OpenClaw
```bash
clawhub install cs-research-summarizer
```
---
## Verification Loop
Before delivering any brief, check:
1. Every Key Finding cites a location in the source (section, page, or quote) — no unanchored claims.
2. `python3 scripts/extract_citations.py <file> --output json` exits 0 and its `total` matches the bibliography count in your output (investigate any gap).
3. Each source carries a 4-dimension quality rating (table above); weak sources are flagged, not silently included.
4. For comparisons: the matrix has one row per dimension and one column per source — no source skipped.
5. Nothing was invented: missing metadata is marked "not stated", never filled in.
---
## Related Skills
- **product-analytics** — Quantitative analysis. Complementary — use research-summarizer for qualitative sources, product-analytics for metrics.
- **competitive-teardown** — Competitive research. Complementary — use research-summarizer for individual source analysis, competitive-teardown for market landscape.
- **content-production** — Content writing. Research-summarizer feeds content-production — summarize sources first, then write.
- **product-discovery** — Discovery frameworks. Complementary — research-summarizer for desk research, product-discovery for user research.
Starter prompts for the main use cases—copy and use them directly.
Summarize a supplied category-research report Use for: Summarize a supplied category-research report. Prepare: Papers, reports, or extracted document text, the decision question, desired detail, and citation style.
Use the installed research-summarizer Skill. Task: Summarize a supplied category-research report. Inputs: [INPUT]. Constraints: [CONSTRAINTS]. Check missing information first. Produce a reviewable result with evidence, assumptions, and next steps. It does not discover sources on the web. Citation extraction uses patterns and needs verification against the original document; PDF text extraction may require another tool.[INPUT][CONSTRAINTS]Compare findings and limitations across supplied papers Use for: Compare findings and limitations across supplied papers. Prepare: Papers, reports, or extracted document text, the decision question, desired detail, and citation style.
Use the installed research-summarizer Skill. Task: Compare findings and limitations across supplied papers. Inputs: [INPUT]. Constraints: [CONSTRAINTS]. Check missing information first. Produce a reviewable result with evidence, assumptions, and next steps. It does not discover sources on the web. Citation extraction uses patterns and needs verification against the original document; PDF text extraction may require another tool.[INPUT][CONSTRAINTS]Extract and verify citations for a decision brief Use for: Extract and verify citations for a decision brief. Prepare: Papers, reports, or extracted document text, the decision question, desired detail, and citation style.
Use the installed research-summarizer Skill. Task: Extract and verify citations for a decision brief. Inputs: [INPUT]. Constraints: [CONSTRAINTS]. Check missing information first. Produce a reviewable result with evidence, assumptions, and next steps. It does not discover sources on the web. Citation extraction uses patterns and needs verification against the original document; PDF text extraction may require another tool.[INPUT][CONSTRAINTS]A merchant supplies an operating report and support-observations article with differing explanations of growth. The task requires source-located summaries, a comparison matrix and a defensible synthesis.
Case input files: business-inputs.zip
Use the research-summarizer Skill.
Synthesize the supplied research notes for our ecommerce product team. Extract each source's question, method, sample, numerical findings and limitations; compare agreements and conflicts, retain traceable citations and quotations, and recommend the decisions the evidence can support plus the most useful next research step.
The attached business materials are:
- inputs/a.txt
- inputs/b.txt
- inputs/brief.txt
Deliver a complete result.md report that the operations team can read, plus any finished files needed for this task. Keep supporting calculations and evidence with the deliverables. Write the report in English; use the requested target language for customer-facing copy. The business datasets are fictional examples unless the brief explicitly names a live public website.The primary file produced by this prompt is shown below in its original language.
The operating report shows a flat 2.5% orders-to-sessions ratio despite 20% more orders. The support article gives a useful hypothesis about policy clarity, but its four selected conversations cannot establish a causal conversion improvement. Clarify confusing policy information, then measure the outcome with a defined funnel or experiment. Both sources are fictional research materials supplied for this case.
Author: Mia Lane. Organization: HarborMug. Document date: November 3, 2026. Type: internal technical report. Question: what changed between the two trading weeks?
Method and sample: two aggregate weekly rows, 100 orders/4,000 sessions then 120/4,800; no customer-level tracking or controlled experiment (A §2). Gross merchandise revenue increased from $2,400 to $2,880, +20%; refunds increased from $120 to $144; ad spend increased from $300 to $360. Gross excludes shipping revenue and tax.
Recalculation: 100/4,000 and 120/4,800 both equal 2.5%. Gross AOV remains $24. Net revenue after the supplied refund dollars is $2,280 then $2,736, +20%. Refund dollars/gross revenue remains 5%; this is not the percentage of orders returned. No realized profit can be established without the remaining costs and revenue definitions (A §§2–4).
Exact quotation: “Volume grew; conversion did not improve.” (A §3.) Read “conversion” here as the report's aggregate order/session ratio, not a deduplicated shopper purchase probability.
Author: Alex Reed. Date: November 2, 2026. Type: supplied article text; no public URL. Question: could clearer delivery and return terms help shoppers?
Method and sample: four selected support conversations mentioning timing uncertainty, with no control group and no measured before/after conversion (B §2). The article's belief that conversion improved is unsupported by its own evidence and conflicts with Source A's aggregate ratio (B §1 versus A §3).
The policy facts are operationally useful: two-business-day dispatch, another three-to-five-business-day delivery estimate, $5 shipping below $50, free shipping at $50, US-only delivery and unused returns within 30 days requiring merchant refund approval (B §3). They do not prove that clarity caused any sales change.
Exact quotation: “Four conversations are a prompt to investigate, not a conversion study.” (B §2.) Convenience selection may overrepresent dissatisfied shoppers. Funding is not stated, the author is merchant-affiliated and opposing explanations were not tested (B §4).
| Dimension | Source A | Source B |
|---|---|---|
| Main claim | Volume grew; order/session ratio flat | Policy clarity may help; improvement is only a belief |
| Method | Two weekly aggregate rows | Four selected support conversations |
| Numeric scope | 220 orders, 8,800 sessions across both weeks | Four conversations, no population denominator |
| Strength | Arithmetic can be reproduced | Identifies a concrete customer question to investigate |
| Credibility | Medium: internal, not peer-reviewed | Low: supplied opinion/article, no independent review |
| Evidence | Medium for descriptive arithmetic; low for causality | Low for conversion effects |
| Recency | High within the fictional exercise dates | High within the fictional exercise dates |
| Objectivity | Medium: merchant-funded, limitations disclosed | Low: merchant-affiliated convenience sample |
Neither source is independent market evidence. The original extractor labels both citations primary; the operating table is primary descriptive data within the fixture, while the support article mixes primary observations with interpretation. Its interpretation should not acquire stronger status merely because a regex classified the citation.
First, keep dispatch and transit wording separate and show shipping thresholds near the buying decision. This follows the specific uncertainty in B §2 and the policy constraints in B §3. Second, retain the unchanged conversion finding in the weekly review rather than crediting the page for volume growth. Third, instrument unique shopper exposure and paid purchases, then define a comparison window or randomized test for policy presentation.
Before testing, inspect whether acquisition mix, stock or promotions changed; neither source covers those alternatives. Collect a consecutively sampled set of support questions, preserving anonymous record IDs and the denominator. Ask shoppers to explain delivery cost and timing without coaching. Use these observations to refine the intervention, not to manufacture a percentage uplift.
brief.txt concatenates A and B and is not a third independent study. The original extraction tool found two citations, matching these two bibliography entries. Both quotations were checked verbatim against their source sections; the calculation file independently reproduces the numerical findings. No external research discovery or genuine merchant outcome is claimed.
Merchant business data is synthetic. Website observations, when present, come from the public URLs listed in the report.
It does not discover sources on the web. Citation extraction uses patterns and needs verification against the original document; PDF text extraction may require another tool.
Source and package files reviewed: GitHub 6d2f02ea077e. This is a static review, not an installation or business-outcome test.
Use authorized inputs and keep secrets out of prompts. Review customer-facing claims, calculations, code changes, and any proposed external action before applying them.
Summarize supplied documents, compare findings, and extract citation candidates. Structured templates separate findings, methods, evidence quality, limitations, and citations.
Choose the method for your agent and install the complete package, not just the displayed SKILL.md. Papers, reports, or extracted document text, the decision question, desired detail, and citation style. Start a new agent session and explicitly ask to use research-summarizer. Try one use case below with a small sample and review the output.
Summarize a supplied category-research report; Compare findings and limitations across supplied papers; Extract and verify citations for a decision brief
It does not discover sources on the web. Citation extraction uses patterns and needs verification against the original document; PDF text extraction may require another tool.
Source and package files reviewed: GitHub 6d2f02ea077e. This is a static review, not an installation or business-outcome test.
Source and package files reviewed: GitHub 6d2f02ea077e. This is a static review, not an installation or business-outcome test.
Source and package files reviewed: GitHub 6d2f02ea077e. This is a static review, not an installation or business-outcome test.
No reviews yet.