Academic Paper Summarizer

Academic paper summarization with dynamic SOP selection based on paper topic classification. Supports method, dataset, multimodal, and other paper types with...

Security Scan

The skill is internally consistent with an academic summarizer: it only writes local files and contains SOP templates; there are minor documentation mismatches but no signs of credential requests, external downloads, or exfiltration behavior.

Purpose & Capability

The name/description (academic paper summarization with dynamic SOP selection) matches what the skill provides: instruction-driven behavior and topic-specific SOP templates (templates/sop_templates.ts). Required capabilities (local summary writing, prompt tracking, batch processing) are consistent with the stated purpose. The only mismatch is that SKILL.md references SOP locations (src/lib/agents/topic-sops.ts and summarization_prompt.ts) that do not exist in the provided file manifest; the actual template file is templates/sop_templates.ts. This appears to be a documentation/path mismatch rather than a functional or malicious inconsistency.

Instruction Scope

Runtime instructions instruct the agent to generate structured analysis and save summaries and prompts to local directories (research/{domain}/ai_summaries/ and research/{domain}/prompts/). That is within scope for a summarizer. There are no instructions to read unrelated system files, access environment variables, or send data to external endpoints. Minor inconsistencies: the SKILL.md and README list different minimum lengths/word-vs-character constraints in places, and the system prompt requires output to be valid JSON while also asking for Markdown-style formatting inside text fields (this is feasible because Markdown can be embedded as JSON strings but is a subtle constraint the implementer must handle).

Install Mechanism

No install spec (instruction-only skill with a small template file). This is low-risk: nothing is downloaded or executed on install, and no package managers or external URLs are used.

Credentials

The skill declares no required environment variables, no primary credential, and no required config paths. The declared behavior (local file writes) is consistent with lacking external credentials. There are no unexplained credential requests.

Persistence & Privilege

The skill does not request always:true and uses the default agent invocation model. It writes only to its own output directories as described; there is no evidence it modifies other skills or global agent configuration.

Assessment

This skill appears coherent and low-risk, but review a few things before installing: 1) Confirm you are comfortable that summaries and the raw prompts will be saved to local disk (research/{domain}/...) — if you process confidential papers, those files may contain sensitive text. 2) Inspect templates/sop_templates.ts (the included system prompt) to ensure the behavior and output format (strict JSON with embedded Markdown/LaTeX) match how you plan to consume results. 3) Note documentation inconsistencies (SKILL.md references different file paths; length requirements vary across files). These are not security issues but could cause runtime mismatches. 4) Because the skill enforces long, detailed outputs, check resource/time expectations when batch-processing many papers. If you want extra assurance, run the skill in a sandboxed environment, examine the files it writes, and confirm no unexpected network activity occurs during use.

Paper Summarize Skill

This skill provides academic-grade paper summarization with dynamic Standard Operating Procedure (SOP) selection based on paper topic classification.

Capabilities

• Dynamic SOP Selection: Automatically selects appropriate analysis template based on paper type (method, dataset, multimodal, etc.)
• Rigorous Analysis: Follows top-tier conference review criteria (NeurIPS/ICML/ICLR/ACL)
• Structured Output: Generates comprehensive summaries with methodology critique, experimental assessment, strengths/weaknesses
• Local File Storage: Saves summaries to organized directory structure with proper naming
• Prompt Tracking: Maintains record of actual prompts used for reproducibility
• Dataset Focus: Explicit attention to training/evaluation datasets used in experiments

Supported Paper Types

• method: Algorithm/architecture papers
• dataset: Dataset/benchmark papers
• multimodal: Cross-modal learning papers
• tech_report: System/model release papers
• application: Applied AI papers
• survey: Survey/review papers
• rl_alignment: RL/Alignment/Safety papers
• speech_audio: Speech/audio processing papers
• benchmark: Evaluation/benchmark papers
• analysis: Empirical analysis papers

Usage

Input Requirements

• Paper title, authors, abstract
• Topic classification (one of supported types)
• Research context (keywords, subtopics)

Output Format

• Local file: {paper_title}.md in research/{domain}/ai_summaries/
• Content structure:
  • Paper information (title, authors, venue, links)
  • Core contribution summary
  • Methodology critique (2000+ words)
  • Experimental assessment (1000+ words, with dataset focus)
  • Strengths and weaknesses
  • Critical questions for authors
  • Impact assessment

Quality Standards

• Methodology Critique: 2000+ characters, deep technical analysis including pipeline, novelty, mathematical principles, assumptions, prior art comparison, computational cost, and failure modes
• Experimental Assessment: 1000+ characters, rigorous evaluation with explicit focus on datasets used for training and testing, protocol rigor, baseline fairness, ablation completeness, and statistical significance
• Overall Analysis: 3000+ characters, critical perspective
• Technical Precision: Correct terminology, specific method names, exact metrics

Workflow Integration

This skill integrates with the broader research workflow:

1. Paper Discovery: Works with arXiv search results
2. Quality Filtering: Processes papers that pass relevance screening
3. Batch Processing: Can be called repeatedly for multiple papers
4. Report Generation: Outputs feed into final research report

Configuration

SOP templates are defined in:

• src/lib/agents/topic-sops.ts (primary location)
• summarization_prompt.ts (backup/reference)

Both files contain identical SOP definitions with shared output format requirements.

Examples

# Summarize a method paper
paper_summarize --title "SongEcho: Cover Song Generation" --topic "method" --abstract "..." --authors "..."

# Summarize a dataset paper  
paper_summarize --title "MusicSem: Language-Audio Dataset" --topic "dataset" --abstract "..." --authors "..."

Files Created

• research/{domain}/ai_summaries/{paper_title}.md
• research/{domain}/prompts/{paper_title}_prompt.txt
• Directory structure automatically created if missing