Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Install and self-host deco Studio (the open-source control plane) on the user's own infrastructure. Use when the user wants to install, run, self-host, or deploy Studio locally (Docker, Rancher Desktop, kind, minikube) or on Kubernetes (managed or self-managed), or asks to "install Studio", "self-host decocms"…
Use when the user asks about their WeChat messages, contacts, conversations, chat history, or needs to decrypt/search WeChat data. Provides structured CLI commands for querying encrypted WeChat macOS databases.
Diagnose and resolve Elasticsearch security errors: 401/403 failures, TLS problems, expired API keys, role mapping mismatches, and Kibana login issues. Use when the user reports a security error.
Builds AI-native products using OpenAI's development philosophy and modern AI UX patterns. Use when integrating AI features, designing for model improvements, implementing evals as product specs, or creating AI-first experiences. Based on Kevin Weil (OpenAI CPO) on building for future models, hybrid approaches, and…
A multi-file workflow for auditing PHP web applications for security issues. The description does not specify enough detail about its exact checks beyond coordinating other PHP audit tools.
A control system for planning and continuing long Chinese fiction with recurring characters, multiple plotlines, and persistent world rules. It keeps project facts, chapter plans, style requirements, and changing story state in organized files.
A writing guide for creating and revising vertical short-drama scripts, where episodes are designed for phone screens and usually last one or two minutes.
A Chinese-language writing guide for creating and reviewing headlines for WeChat public-account articles. WeChat public accounts are channels used to publish articles to followers.
Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Use when asked to "create a skill", "write a skill", "synthesize sources into a skill", "improve a skill from positive/negative examples", "update a skill", or "maintain skill docs and registration". Handles source…
A media downloader that searches for and downloads images or video clips from a description, with support for automatically trimming videos. It can be triggered with media-download requests or the /media command.
Use the One CLI (one) to interact with 3rd-party platforms — Gmail, Slack, Stripe, Notion, etc. through their APIs. One handles auth, request building, and execution. TRIGGER when: Interact with ANY 3rd-party platform or external service (e.g., "send an email", "create a Shopify order", "find a HubSpot contact", "post…
Run registered ComfyUI workflows through the fast comfyui-skill CLI, and use the official local Comfy MCP for live template, node, model, validation, and orchestration capabilities. Use this Skill when: (1) The user requests to "generate an image", "draw a picture", or "execute a ComfyUI workflow". (2) The user has…
Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…
Thinking partner for humanities scholars — history, philosophy, literature, art history, religious studies, classics, and adjacent fields where prose IS the argument. Covers the full arc of a paper: research-question sharpening, literature mapping, plan-only outlining, conception and drafting, four-layer chapter…
A role-playing guide that examines social situations, life choices, and human behavior through the perspective of Chinese documentarian Zhou Lifeng, known online as “Feng Ge.” It uses his stated ideas and public materials as its basis.
Use after the napkinmath pipeline has produced parameters/bounds/scenarios/montecarlo JSON to generate a plan assessment (assessment.md) — a thin interpretation layer over the intermediary artifacts. Emits a JSON manifest, a provenance map, gate verdicts (Critical / Fragile / Marginal / Robust), failure drivers…
Reverse engineer native, managed, Electron/JavaScript, packaged, and browser applications with REA. Use shipped-artifact or approved runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.
Backward-compatible alias for a visible Chat consultation with the Pro intelligence setting; prefer chatgpt-delegate for new Chat or Work delegation workflows.
A prompt generator for vertical Xiaohongshu covers in the Atutun style. Xiaohongshu is a Chinese social platform for lifestyle and product-sharing posts; the style uses large Chinese titles, a person cutout, checklists, stickers, arrows, and high-contrast layouts.
Ultra-compressed communication mode. Cuts token usage 75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or…
A method for finding overlooked companies that supply a hard-to-replace part of an investment trend's supply chain. A supply-chain bottleneck is a limited upstream resource or supplier that can hold back the rest of the market.
A daily news digest for popular short-drama articles on WeChat public accounts. WeChat public accounts are channels that publish articles; the digest groups topics and includes cover images, engagement data, and writing insights.
★not rated 399▲
+5 2d agoA269 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: