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.
Build a multi-screen NavigationPanel layout in Optix via the live bridge — tabs that switch content, done the ONE-mechanism way that actually renders. Use for "add navigation", "multi-screen HMI", "tabs to switch screens", "nav bar with pages".
Healthcare navigation and medical-information assistant for symptom triage, lab-result explanation, medication side-effect review, visit preparation, post-visit summaries, care-plan checklists, referral handoffs, and structured escalation. Use when the user wants help understanding labs, medications, discharge notes…
You are building an external executive function system for a user with AUDHD (combined ADHD + Autism). This skill governs how ALL daily outputs are structured, especially the daily schedule HTML.
Run a project's engineering decisions as a living log — MADR-lite ADRs (supersede, never delete) for decisions expensive to reverse, issues for the work (and its cheap-to-reverse choices), research artifacts, an optional PRD, a project constitution, and living Mermaid architecture views, where every record has exactly…
Cross-agent repo-local progress checkpoint workflow for any git repository. Use this skill whenever the user says save progress, checkpoint, snapshot the current lane, capture key chat context, write down what matters before closing, or wants the next session to resume immediately from Codex, Claude Code, opencode, or…
Triggers when a user asks to build, create, update, run, test, schedule, deploy, host, upgrade, inspect, open the inspection UI, or delete a saved GTM workflow, its result table, runs, or diagram in a GTM workspace, with phrasings like "build a workflow that scores our inbound companies", "run Score inbound accounts"…
Unofficial WHOOP recovery, sleep, strain and HRV for AI agents. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants WHOOP data or actions through an agent.
Guide for discovering 540+ developer tools, design resources, AI platforms, and agencies using the thetoolforthat MCP server. Use when asked to find tools for a project, recommend tech stack components, discover design agencies, or search for specific tool categories.
Use this skill when the user wants to add in-app purchases (subscriptions, consumables, or non-consumables) to a React Native / Expo mobile app. onesub is the open-source server side of react-native-iap — one line of Express middleware validates Apple StoreKit 2 and Google Play Billing receipts. Pair it with the…
Confluence team wiki and documentation platform - lets an agent search, read, and create pages across internal knowledge bases, runbooks, technical documentation, and policy spaces.
Attack patterns and real-world examples sourced from the HackerBot Claw campaign analysis by StepSecurity (2025): https://www.stepsecurity.io/blog/hackerbot-claw-github-actions-exploitation -->.
Access and operate any database via CLI. Use when exploring schemas, querying data, writing records, running migrations, diagnosing connection issues, or switching between multiple databases. Supports SQLite, PostgreSQL, MySQL, MariaDB, DuckDB, ClickHouse, and SQL Server.
This skill audits a project's existing context files, validates consistency across cascading context layers, and generates missing context files based on the cascading context methodology.
A Korean proofreading and editing skill for short text and academic documents in DOCX, PDF, or Markdown format. It checks spelling, spacing, sentence quality, and, for papers, logic and citations.
Scaffold a complete, production-ready Azure project from scratch for ANY use case: RAG chatbots, multi-agent systems, API backends, data pipelines, Azure Functions, full-stack web apps, ML training/inference, or event-driven microservices. USE FOR: gathering requirements through adaptive questioning, generating…
Debug Linux kernels using bata24/GEF (GDB Enhanced Features) via the GDB MCP. Use when doing kernel debugging, exploit development, slab/heap inspection, task/cred analysis, memory layout investigation, ROP gadget search, or any qemu-system kernel GDB session. Trigger on kernel debugging, GEF commands, slab analysis…
Simulate Google AI Overviews by running prompts through Gemini 3 Flash with Google Search grounding. See which sources get cited, how often, and what snippets get pulled — before checking the real AI Overview. Track a specific domain to measure mention rate, citation rate, and exact excerpts. Use when a user wants to…
Use when creating or modifying a skill: follow SKILL.md rules, define commands and dependencies, validate locally, version correctly, and publish.
★not rated 13 3mo agoA32 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: