skilld
All skills
agents365-ai avatar

/scholar-deep-research

@72ee04b
by Agents365.aiagents365-ai/365-skills57 stars
12

Use when the user asks for a literature review, academic deep dive, research report, state-of-the-art survey, topic scoping, comparative analysis of methods/papers, grant background, or any request that needs multi-source scholarly evidence with citations. Also trigger proactively when a user question clearly requires academic grounding (e.g. "what's known about X", "compare approach A vs B in the literature", "summarize the field of Y"). Runs an 8-phase (Phase 0..7), script-driven research workflow across 7 federated sources (OpenAlex, arXiv, Crossref, PubMed, DBLP, bioRxiv, Exa) with optional Semantic Scholar / Brave MCP enrichment, with deduplication, transparent ranking, dual-backend citation chasing (OpenAlex + Semantic Scholar), self-critique, and structured report output with verifiable citations.

Ask your Agent

Use this Skill: https://skilld.dev/gh/agents365-ai/365-skills/scholar-deep-research

This session only. Nothing lands on disk.

changelog.dREADME.md

≈476 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Changelog fragments

Each pull request that affects observable behavior drops a small markdown file here describing the change. At release time, towncrier build --version X.Y.Z aggregates the fragments into ../CHANGELOG.md and deletes them.

This sidesteps the merge-conflict + diff-noise problem you get when every PR hand-edits CHANGELOG.md directly.

Fragment file naming

<short-kebab-slug>.<type>.md
  • <short-kebab-slug> — anything unique to your PR. Convention: ssrf-guard, docling-engine, rapidocr-lang. No PR/issue numbers (we keep history in git, not in fragment filenames).
  • <type> — one of: feature, bugfix, doc, refactor, removal. See ../towncrier.toml for the canonical list.

Examples:

changelog.d/safe-get-ssrf-guard.feature.md
changelog.d/docling-num-pages-method.bugfix.md
changelog.d/agent-native-rubric-pass.refactor.md

Fragment file body

One short sentence per fragment. Lead with the user-visible effect (what changed for the agent calling the skill), not the implementation detail. Compare:

  • ✅ extract_pdf.py now defaults to docling for scanned PDFs.
  • ❌ Refactored _do_extract to thread engine kwarg through helper.

For a bigger feature, multi-sentence is OK but keep it tight — readers of CHANGELOG.md skim, they don't study.

Release flow

# Dry-run to see what the next CHANGELOG.md will look like:
towncrier build --draft --version 0.15.0

# Write it for real (deletes fragments, edits CHANGELOG.md, no commit):
towncrier build --version 0.15.0

# Then bump metadata.version in SKILL.md and _common.py, commit, tag.

When NOT to write a fragment

  • Pure typo fixes in comments / docstrings
  • Internal helper renames with no behavior change
  • Test-only changes that don't change observable surface

For everything else — write the fragment. It costs 30 seconds.

Source: SKILL.md on GitHub

Third-party checks

1 warning4mo3 checks · Risk SAFE
  • Gen Agent Trust Hub4mo

    This skill is a robust academic research tool that automates literature reviews across multiple scholarly databases. It uses strict input validation for paper identifiers and handles sensitive API keys through environment variables. While the skill executes a local script from a companion 'paper-fetch' skill to download PDFs, this is a standard design pattern within the author's ecosystem. It also processes external PDF text, which carries a minor risk of indirect prompt injection common to all document-reading agents.

  • Socket4mo

    No alerts

  • Snyk4mo

    Risk: MEDIUM · 1 issue

Provenance

Signed by skilld at 72ee04b. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 11 hours ago.

Activeupdated 3 weeks ago

Capability

homepage
https://github.com/Agents365-ai/365-skills
platforms
[macos, linux, windows]
Other metadata
compatibility
Requires Python 3.9+ with httpx and pypdf (see requirements.txt). Optional: `pip install docling` to enable layout-aware markdown PDF extraction (`extract_pdf.py --engine docling`); auto-used as a fallback for scanned/sparse PDFs. Works offline-first (no MCP required) but enriches with Semantic Scholar / Brave MCP tools when available.
metadata
{
  "openclaw": {
    "requires": {
      "bins": [
        "python3"
      ]
    },
    "emoji": "🔬"
  },
  "hermes": {
    "tags": [
      "research",
      "literature-review",
      "academic",
      "papers",
      "citations",
      "survey"
    ],
    "category": "research"
  },
  "pimo": {
    "tags": [
      "research",
      "literature-review",
      "academic"
    ],
    "category": "research"
  },
  "author": "Agents365-ai",
  "version": "0.17.0"
}

README badge

README badge for agents365-ai/365-skills/scholar-deep-research