MCP App StoreMCP App Store
from crush-skill8
Predict and simulate how a crush might reply—offers analysis, reply prediction, relationship thermometer, and simulated conversations with safety rules.
This skill helps the agent predict likely replies from someone a user is interested in and simulate conversation with that person. It provides analytical tools (reply prediction, signal reading, relationship "temperature"), persona building from chat data, and a simulator mode to rehearse messages safely. Built-in safety and privacy rules are emphasised.
Use when a user asks about a crush, flirting messages, or how to respond—phrases like "crush", "暧昧", "喜欢的人", or requests to predict a reply or interpret signals should trigger this skill. It's also useful when the user wants to rehearse messages by simulating the other person's tone.
Best suited for conversational assistants with access to text parsing, short-term user data storage, and safe-content controls (e.g., chat-oriented agents like Claude/Copilot-style assistants).
A relationship/crush simulation skill offering reply prediction, signal reading, a relationship thermometer, and simulated conversations. The SKILL.md is well-structured with clear safety rules (Layer 0 hard rules against manipulation/harassment, privacy protection, uncertainty labeling). No bundled scripts were present, so all functionality relies on the agent interpreting prompt files (prompts/*.md, references/*.md, tools/*.py) that aren't included. The concept is creative but niche and depends heavily on referenced files not in the bundle.
Strong safety-first design with explicit hard rules against manipulation, harassment, and stalking. Confidence labeling on all predictions is commendable. However, the skill is largely incomplete without its referenced prompt/reference/tool files. The concept (crush reply prediction) is niche — a specific audience but not broad. Bilingual (Chinese/English) which adds accessibility. Architecture is decent with clear mode separation and command routing, but relies on external files not present in the skill bundle.
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
Skill Retro
Analyze a session's skill invocations to surface performance issues and recommend or apply improvements using the skill-creator workflow.
AI News Daily
Generate a structured, bilingual daily briefing of the latest AI industry news, model updates, papers, and open-source tools with in-depth technical analysis an
AIML Spambot Benchmark (ISC)
Benchmark template for evaluating spam-detection models using anchored spam campaign examples (contains harmful anchoring content).
Analyzing Ransomware Leak Site Intelligence
Collect and analyze ransomware data-leak site (DLS) posts to extract victim, group, sector and geographic trends for threat intelligence and proactive defense.
Analyzing Ransomware Leak Site Intelligence
Collect and analyze ransomware data-leak site (DLS) postings to extract victim, group, sector, and timeline intelligence for threat hunting and risk assessment.
Cashu Wallet
Privacy-focused Bitcoin wallet skill enabling sending/receiving via Lightning and Cashu ecash tokens, with multi-mint support and basic wallet management comman
CLS-Certify — Skill Security Auditor
Enterprise-grade multi-dimensional security scanner for Agent Skills that produces S+/S/A/B/C/D ratings and structured HTML/PDF reports.