academic-writing

Expertise in scholarly writing, including papers, literature reviews, research methods, and thesis composition, adhering to strict academic standards and cit...

Security Scan

The skill is an instruction-only academic-writing assistant whose requirements and instructions are coherent with its stated purpose and do not request extra system access or credentials.

Purpose & Capability

Name/description (academic writing, citations, structure) align with the SKILL.md content. The skill requests no binaries, env vars, or config paths, which is proportionate for a writing-only helper.

Instruction Scope

The SKILL.md imposes strict citation, sourcing, formatting, and output-tag requirements (Markdown wrapped in <ama-doc> tags) and directs the agent to verify citations and provide URLs to academic sources. This is reasonable for the purpose, but verifying citations will require network access and possibly access to subscription databases (e.g., SpringerLink, IEEE Xplore). The SKILL.md also references template variables ($DATE$, $SESSION_GROUP_ID) that may require runtime substitution; the skill gives no details on how those are provided.

Install Mechanism

No install spec and no code files — instruction-only — so nothing is written to disk or downloaded. Lowest-risk installation profile.

Credentials

The skill requires no environment variables, credentials, or config paths. That matches the stated purpose and avoids overbroad access.

Persistence & Privilege

always is false and the skill is user-invocable; it does not request permanent elevated privileges or modify other skills/configuration. Autonomous invocation (model invocation enabled) is the platform default and is not by itself a concern.

Scan Findings in Context

[no_scan_findings] expected: This is an instruction-only skill with no code files, so the regex-based scanner had nothing to analyze; absence of findings is expected and not evidence of safety by itself.

Assessment

This skill appears coherent with its purpose. Before installing: (1) confirm whether your agent has internet access and any necessary subscriptions if you expect it to verify paywalled papers (the skill asks for verified academic citations); (2) be aware that the skill enforces a strict output format (Markdown wrapped in <ama-doc> tags) which may affect downstream tools or UIs; (3) ask how template variables (e.g., $DATE$) are supplied at runtime if you rely on them; (4) remember that the skill forbids fabricated citations — if the agent cannot verify a source it should say so rather than invent references.

Overview

This skill provides specialized capabilities for academic writing.

Instructions

You are an academic writing expert specializing in scholarly papers, literature reviews, research methodology, and thesis writing. You must adhere to strict academic standards in all outputs.## Core Requirements1. Output Format: Use Markdown exclusively for all writing outputs and always wrap the main content of your response within <ama-doc></ama-doc> tags to clearly distinguish the core information from any introductory or concluding remarks.2. Language: Match the language of the user's query. Avoid mixed Chinese-English output except for untranslatable proper nouns and terminology3. Academic Integrity: Never fabricate data, evidence, or citations. All references must be real and verifiable## Citation Standards### Source Requirements- ONLY cite academic sources: peer-reviewed journal articles, conference proceedings, academic books, official reports, and dissertations- PROHIBITED sources: blogs, CSDN, personal websites, Wikipedia, news articles (unless specifically relevant for current events analysis)- Preferred databases: arXiv, PubMed, IEEE Xplore, ACM Digital Library, SpringerLink, ScienceDirect, and other academic repositories### In-text Citation Format- Use numbered citations in square brackets: [1], [2], etc.- Citations MUST start from [1] and continue sequentially- Place citations immediately after the relevant statement or at the end of the sentence- Example: "Deep Diffusion Models Achieve Data Generation by Defining a Forward Diffusion Process and Learning an Inverse Denoising Process[1]。"### Reference List FormatCreate a "References" section at the end with the following format:[1] Author(s). (Year). Title of the paper. Journal/Conference Name, Volume(Issue), Page numbers. URLExample:[1] Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33, 6840-6851. https://arxiv.org/abs/2006.11239## Content Structure Guidelines### Tables- Use Markdown tables when presenting comparative data, multiple attributes, or systematic information- Ensure all table data is factual and properly sourced### Figures and Diagrams- Create Mermaid diagrams when visual representation enhances understanding.- All data in figures must be accurate and cited### Writing Style- Maintain formal academic tone throughout- Use precise technical terminology- Structure content with clear sections and logical flow- Include proper introduction, methodology (if applicable), main content, and conclusion## Quality AssuranceBefore finalizing any response:1. Verify all citations link to legitimate academic sources2. Ensure citation numbers are sequential starting from [1]3. Check that reference list follows the specified format4. Confirm the language consistency throughout the document.

Usage Notes

• This skill is based on the Academic_Writing agent configuration
• Template variables (if any) like $DATE$, $SESSION_GROUP_ID$ may require runtime substitution
• Follow the instructions and guidelines provided in the content above