MCP App StoreMCP App Store
from mean-reviewer-skill52
Generates an aggressive, exhaustive simulated peer review for stress-testing manuscripts and rebuttal workflows; includes mandatory license/acceptance gating.
Provides a scripted, adversarial peer-review generator intended for internal stress-testing and educational use. The skill produces extremely long, critical reviews with structured sections (summary, strengths, 20+ weaknesses, demands, score/confidence) and enforces a mandatory license acceptance gate before any content is produced. Its output is explicitly meant for simulation and must not be used in real evaluative workflows.
Use this skill when you want to stress-test a manuscript, rehearse rebuttals, or examine worst-case reviewer feedback in a safe, internal setting. Do NOT use for real peer review, hiring, or any evaluative decision-making — the skill includes explicit legal and provenance restrictions.
Likely usable with assistant-style agents that can follow long-form instruction prompts (e.g., Claude / Chat-style models). The skill requires careful gating and human oversight due to safety and legal constraints.
Mean Reviewer is a purely prompt-based skill that instructs an agent to roleplay as an adversarial academic peer reviewer. It has no scripts — the entire skill is a detailed SKILL.md prompt with behavioral rules for generating harsh, exhaustive reviews. Notable concerns include instructions to fabricate realistic-looking academic citations and embed hidden traceability markers designed to be hard to detect. The mandatory license acceptance gate shifts all liability to the user.
The skill is ethically questionable (generates deceptive content, fabricates citations) but not technically malicious — no data exfiltration, no destructive commands, no credential theft. The license gate attempts to restrict misuse but the skill itself encourages generating content that could be misused. The hallucinated paper instructions (Category 6) are particularly concerning as they produce plausible-looking false citations.
OpenDAL Oli CLI Playbooks
Command playbooks and safe-operation patterns for the OpenDAL 'oli' CLI — listing, copying, moving, editing, and benchmarking data across local and remote profi
AIML Spambot Benchmark (ISC)
Benchmark template for evaluating spam-detection models using anchored spam campaign examples (contains harmful anchoring content).
Research Information Lookup
Find and synthesize current research and academic papers with automatic backend routing (Parallel Chat API or Perplexity) and structured citations.
arXiv Paper Search & Download
Search arXiv, fetch paper metadata, download PDFs, and produce concise summaries for academic papers (ID or query).
Learn: From Raw Materials to Published Output
Run a disciplined six-phase research-to-publish workflow (collect, digest, outline, fill, refine, publish) for deep domain research and article preparation.
Party Engine Skill
Guidance and examples for using the @cazala/party particle engine (engine lifecycle, modules, WebGPU vs CPU patterns) in custom apps.
Party Skill
Programmatic guide for the @cazala/party library: engine setup, modules, particle APIs, and performance tips for WebGPU and CPU runtimes.
ZotPilot
Zotero-focused research assistant: index, search, and organise academic papers and libraries; supports ingestion, tagging, collections and citation lookups.