Claude MarketplacesSubmit
lingzhi227 avatar

Survey Generation

lingzhi227/agent-research-skills

This generates complete academic survey papers by following the AutoSurvey pipeline: collect 50-200 papers from Semantic Scholar, generate multiple outlines in parallel and merge them, then write each subsection using RAG with inline citations. It enforces citation validation using NLI to check claims against sources and won't let you hallucinate references. The local coherence pass smooths transitions between subsections while preserving citations. You get a full LaTeX paper with BibTeX entries. Honestly, this is overkill for a three page related work section, but if you're actually writing a 20-30 page survey paper and need to synthesize hundreds of sources with verified citations, the structured pipeline keeps you from drowning in papers or making stuff up.

skills.sh installs
1.8K
GitHub stars
459
last updated
Aug 21, 2026
View on GitHub

Install

$ npx -y skills add lingzhi227/agent-research-skills --skill survey-generation --agent claude-code

Installs into .claude/skills of the current project.

Files

Survey Generation

Generate complete academic survey papers with structured outline, RAG-based writing, and citation validation.

Input

  • $0 — Survey topic or research area

Scripts

Literature search

python ~/.claude/skills/deep-research/scripts/search_semantic_scholar.py \
  --query "relevant search query" --max-results 50

References

  • Survey prompts (outline, writing, citation, coherence): ~/.claude/skills/survey-generation/references/survey-prompts.md

Workflow (from AutoSurvey)

Step 1: Collect Papers

  1. Search Semantic Scholar / arXiv for papers on the topic
  2. Collect 50-200 relevant papers with titles and abstracts
  3. Filter by relevance and citation count

Step 2: Generate Outline (Multi-LLM Parallel)

  1. Generate N rough outlines independently (parallel)
  2. Merge outlines into a single comprehensive outline
  3. Expand each section into subsections
  4. Edit final outline to remove redundancies
SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/lingzhi227/agent-research-skills
Categories
DevOps & CI/CD, Documentation, AI & Agent Building, Data Science & ML, Automation & Workflows, Sales & Marketing
First seen
Jun 3, 2026

More from lingzhi227/agent-research-skills

All 31

Recommended

More DevOps & CI/CD
1anthropics avatarlead-triageanthropics/knowledge-work-pluginsScores inbound HubSpot leads by engagement signals, company fit, and urgency markers to produce a "call these 5 today" list with talking points, drafts the foll1.7Kskills.sh installs
2alirezarezvani avatarsenior-backendalirezarezvani/claude-skillsDesigns and implements backend systems including REST APIs, microservices, database architectures, authentication flows, and security hardening. Use when the us1.7Kskills.sh installs
3qwencloud avatarqwencloud-audio-ttsqwencloud/qwencloud-ai[QwenCloud] Synthesize speech from text with Qwen TTS models. TRIGGER when: user wants to convert text to speech, create voiceovers, generate audio narration, r1.7Kskills.sh installs
4arize-ai avatarphoenix-tracingarize-ai/phoenixOpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to p1.7Kskills.sh installs
5buildgreatproducts avatarproduct-plannerbuildgreatproducts/builder-osVision intake conversation followed by generation of three product documents — `docs/product-vision.md` (strategy and brand), `docs/prd.md` (technical spec for 1.7Kskills.sh installs
6answerzhao avatarweb-readeranswerzhao/agent-skillsImplement web page content extraction capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to scrape web pages, extract article content, 1.7Kskills.sh installs