Skip to content
Agentmart
Submit a tool

evidence-synthesis

Lightweight systematic literature synthesis (~20 papers max) using arXiv search and sequential summarization.

Skill by azerothl

IndexedMIT★ 2
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/azerothl-evidence-synthesis

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Lightweight systematic literature synthesis (~20 papers max) using arXiv search and sequential summarization. Use for research surveys; paper-critique handles single-paper review.

Use cases: research

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/evidence-synthesis

What's inside

Skill name
evidence-synthesis
Description
Lightweight systematic literature synthesis (~20 papers max) using arXiv search and sequential summarization. Use for research surveys; paper-critique handles single-paper review.
License
MIT
Compatibility
arxiv_search tool or scripts/arxiv_search.py; Python 3.10+ stdlib for script.
Metadata
version: 1.0
Instructions
35 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (3)

  • SKILL.md
  • arxiv_search.py · scripts/
  • skill.json

SKILL.md (first lines)

# Evidence Synthesis

Small-scale **literature synthesis** — not a full academic SLR pipeline with subagents.

## When to Use

- User wants overview of research on a topic
- Survey arXiv/preprints for a technology area
- Build reading list with 1-paragraph summaries per paper

## Tools

- **arxiv_search** — Native when available
- **run_command** — `python scripts/arxiv_search.py "<query>" [max]`
- **web_fetch** — Abstract pages if needed

## Execution

1. Define research question (PICO-style if clinical)
2. Run 2–3 search queries; cap **~20 papers**
3. For each: title, authors, year, 3-bullet summary, link
4. Synthesis section: themes, gaps, conflicting findings
5. Limitations: not exhaustive, English/arXiv bias

## Provenance

Inspired by deer-flow systematic-literature-review; simplified for Akasha.

## Installation

```
Install the evidence-synthesis skill from https://github.com/azerothl/Akasha_skills/tree/main/skills/evidence-synthesis
```

From azerothl/Akasha_skills, MIT.

More from azerothl/Akasha_skills

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Jun 8, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.0
License
MIT
Repository
github.com/azerothl/Akasha_skills
Website
azerothl.github.io/Akasha_skills/
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from azerothl

Cite this page

evidence-synthesis skill. Agent Mart. https://agentmart.dev/skills/azerothl-evidence-synthesis (last updated 2026-10-24)