Skill reviews

Automated literature retrieval and Feishu Bitable management. Use when user requests to create a literature database, search PubMed for specific topics, or manage research papers i

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Microsoft Outlook/Live.com email and calendar client via Microsoft Graph API. List, search, read, send emails. View and create calendar events. Supports device code auth for server

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Maxxit trading powered by 0G decentralized AI compute for portfolio-aware trade decisions and 0G decentralized storage for censorship-resistant alpha listings. Includes all DEX tra

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Monthly health check for your agent stack — hunts for zombie crons, dead scripts, unused API keys, superseded tools, and stale subscriptions. Classifies each finding as delete/repl

• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill
• Does not say what the process needs to start

Discord Bot (discord.com). Use this skill for ANY Discord Bot request — reading, creating, updating, and deleting data. Whenever a task involves Discord Bot, use this skill instead

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Use this skill when the user wants to clean up, back up, or optimize their 126.com (NetEase) email account. Covers local backup, spam/subscription bulk deletion, and large attachme

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

AI image creation skill supporting text-to-image, image editing, image understanding, and more. Uses qwen-image-2.0-pro, wan2.7-image, qwen3.5-plus and other models. Use this skill

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (3 tags): a typed call is more reliable

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Populates investment banking pitch deck templates with data from source files. Use when: user provides a PowerPoint template to fill in, user has source data (Excel/CSV) to populat

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Screen incoming NDAs and classify them as GREEN (standard), YELLOW (needs review), or RED (significant issues). Use when a new NDA comes in from sales or business development, when

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Create natural, high-retention hooks and opening text for TikTok, Instagram Reels, YouTube Shorts, and slideshow/carousel-style short-form content in English and German.

• 22 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• 14 mutating operations with no state check

Cross-platform shopping risk and after-sales decision skill for mainland China that evaluates merchant credibility, hidden post-purchase friction, refund difficulty, and evidence-r

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 17 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Keeps a dated record of how an agent's work has been going — an evening journal, free thinking at night, and a way to read it back. Use when asked to run the inner-life evening or

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

This skill helps users migrate their local machine learning scripts to run on TensorPool GPU clusters using the interactive cluster workflow (tp ssh). Use this when a user has a wo

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

A first aid learning assistant. Activate when the user mentions learning first aid, CPR, bleeding control, wound care, fractures, bandaging, building a first aid kit, or practicing

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Close the agent's context session and consolidate what was learned. Self-triggering — fires when the agent finishes a task, wraps up work, or is about to go idle. Handles the keep/

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Sync Mailchimp newsletter posts to a Ghost blog. Fetches newsletter content from RSS, converts HTML to clean markdown with horizontal rules, uploads images to Ghost, and publishes

• References files that are not bundled: ../ghst/SKILL.md, url
• 10 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Build throwaway code to answer a design question fast. Routes between two modes: Logic (interactive terminal app for state machines and data models) or UI (multiple radically diffe

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

AI content signature detector for social media posts. Measures 8 linguistic dimensions that LinkedIn's 360Brew and other platforms use to detect AI-generated content — lexical dive

• 12 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Use when the user wants to convert MP4 video files to GIF format, or asks about video-to-GIF conversion with quality/size control

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Linear process with no failure handling

Thin orchestrator for the end-to-end video localization pipeline. Routes to the four focused sub-skills — /wjs-transcribing-audio, /wjs-translating-subtitles, /wjs-dubbing-video, /

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (4 tags): a typed call is more reliable
• Does not say what the result is

Update multilingual customer support reply templates in markdown files, then sync the updated content to Feishu Wiki, log the change in a GitHub issue, and package/publish the repe

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Design a public-safe 7-day Skool challenge. Use when the user wants to invite member action, collect comments, produce visible proof, test demand, or turn repeated tasks into free

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Linear process with no failure handling

Create, modify, generate, and deploy websites, web apps, dashboards, SaaS products, internal tools, interactive web pages, Weixin mini program , games on the Baidu Medo platform us

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 27 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval