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.
Produce AWS architecture diagrams as editable .drawio files using the AWS 2026 shape set (mxgraph.aws4 stencils), with verified stencil names and a validator. Use this whenever an AWS architecture diagram is requested, revised, or reviewed, including when the user only says "draw the architecture", "diagram this"…
Skill "powerbi_integration" from MidOSresearch/midos, covering 📊 power bi sovereignty: the star schema standard, 1. data model, 2. dax formulas for attribution and cpa (cost per acquisition).
Apply design psychology — cognitive biases and behavioral principles — to review UI/UX work and generate ideas, recommendations, and critiques grounded in named principles. Use this skill whenever the user asks for a UX review, design critique, conversion analysis, onboarding/checkout/pricing/paywall feedback, "why…
A visual-design guide for turning articles, PDFs, screenshots, brand materials, or long text into cover images and educational infographics for Chinese social platforms such as WeChat, Xiaohongshu, and Douyin.
A tool for turning authorized application code into installable agent capabilities such as Functions, MCP tools, and Skills. It extracts useful features, interfaces, workflows, and fixes from existing frontend, backend, or full-stack code.
Research-first scouting agent skill that runs BEFORE any build decision, new dependency, new system, or feature request. Search existing solutions (codebase, dependencies, packages, GitHub repos, APIs, SaaS, templates) before writing code. Output a REUSE / USE / FORK / BUY / INTEGRATE / BUILD recommendation with a…
Seed, audit, adopt, and progressively evolve an agent-native repository with risk-triggered specs, durable decisions, resident governance skills, capability state, deterministic gates, and safe upgrades. Use when initializing or upgrading a repository, when an unmanaged repository grows complex, or when delivery…
Use when you want to make something measurably better and let the agent do the trial-and-error for you — for example "make this faster", "how can I improve this?", "reduce cost/memory", "increase test coverage", or "make this search return better results" (also tuning an LLM training run). You don't need to know the…
A Chinese-language guide for creating animated teaching videos with Manim, a program that draws mathematical and technical animations. It covers scripts, storyboards, code, rendering, narration, subtitles, and MP4 output.
Turn any CLI or MCP server into an Agent Skill. Use when you want to replace an MCP server with a zero-overhead CLI skill, or generate a skill from any command-line tool's --help output.
Navigate SAP's AI technology landscape and guide implementation of AI use cases on SAP BTP. Use when someone asks which AI approach to use on SAP, how to build AI apps, agents, or ML models on SAP BTP, or needs guidance on SAP AI Core, Joule, Generative AI Hub, HANA Cloud ML, RPT-1, Document AI, or Joule Skills. Also…
The only Telegram skill your AI agent needs. Read messages, parse channels, download and transcribe voice notes — all via Telethon user API. One session file, zero bots. Use when user says 'read telegram', 'check saved messages', 'fetch from telegram', 'parse channel', 'transcribe voice', 'telegram search', 'check my…
Attach Proof Engine proofs to LLM-wiki claims. Use for ingest (extract claims, look up or commission proofs, rewrite pages with badges) and lint (re-verify citations, detect contradictions, report stale proofs) steps in wiki pipelines. Trigger phrases: "ingest wiki page", "lint wiki", "{{prove:}} markers", "verify…
Use this skill whenever the project uses spec-graph for managing requirements, decisions, phases, changes, interfaces, states, tests, and other semantic entities in a typed graph. Trigger when the user mentions spec-graph, or when the task involves any of: tracking requirements or decisions, planning development…
Interactively walk through every decision log in .ninthwave/decisions/ one at a time. For each log: read it, check whether the choice it describes still matches what shipped, ask the human what to do (ratify / record as ADR / codify into an existing doc / create follow-up work item / revise / merge / skip), execute…
Use for end-to-end website or interface design, redesign, implementation, or major visual polish; orchestrates discovery, references, art direction, systems, build, critique, QA, and release gates.
Expert Google Ads management — campaign analysis, budget optimization, keyword strategy, ad copy, Performance Max advisory, and account auditing. Activate when the user asks about Google Ads, PPC, campaigns, ad spend, ROAS, keywords, bidding strategies, or any advertising-related query.
Senior engineer CLI expertise for AI agents — workflows, safety guardrails, gotchas, and anti-patterns across cloud, IaC, containers, databases, dev tools, and platforms.
★not rated 8 6mo agoA42 tokens
originalMIT
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: