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.
Analyze repository evidence to bootstrap, migrate, update, or audit project documentation covering architecture, flows, APIs, schemas, security, configuration, and delivery. Use when creating a complete documentation system, synchronizing existing docs with Git or code changes, adopting unmanaged documentation…
Utiliza este skill cuando el usuario pida dibujar pizarras, diagramas de arquitectura, bocetos UI o esquemas de cajas libres que requieran geometría manual 2D y un alto grado de personalización posterior. Genera el código fuente JSON de Excalidraw (.excalidraw) para importación directa.
Teaches Claude Code how to write a production-safe PII redaction service for any project handling sensitive personal data — medical bills, insurance forms, financial documents, HR records, etc.
Use whenever the conversation involves the user's projects, systems, infrastructure, people, past decisions, or recurring problems — even when memory is not explicitly mentioned. Trigger on possessives and project references ("my project", "our server", "remember when we", "last time"), named systems and services in…
Triage and review OSSM Jira CVE issues for the Kiali component. Two features - triage (find new CVEs, close inapplicable issues, create fix PRs for master and supported branches) and review (review fix PRs across branches, verify consistency and CI, approve, merge, update Jira). Use when the user mentions CVE triage…
A product-management workflow engine that combines eight planning modules into one process. It supports tasks such as market research, competitor analysis, requirements documents, architecture, interface planning, and technical plans.
Activate when the user wants SEO for a Next.js app — implementing, auditing, or fixing on-page and technical SEO to a top ("Neil Patel standard", "score 100", "rank", "Core Web Vitals", "metadata", "sitemap", "structured data", "Open Graph") bar. Trigger phrases include "add SEO to my Next.js site", "audit my Next…
QQ MCP bot — auto-wake on message, manage pending to prevent duplicate wakes, reply via sendmessage/sendimage/sendvoice then unlock. Use when interacting with QQ MCP, managing wake rules, or debugging QQ bot workflows.
A collection of commands for reducing token usage in OpenClaw or Claude Code. It includes model routing, context compression, heartbeat and loop tuning, usage reports, configuration generation, and related audits.
Unified security suite for agent workspaces. Installs, configures, and orchestrates all 11 OpenClaw security tools in one command — integrity, secrets, permissions, network, audit trail, signing, supply chain, credentials, injection defense, compliance, and incident response.
Starts and structures Raycast extension work: locate the extension folder, sync git, create a feature branch, install deps, and run dev from the extension directory (ray develop or npm run dev). Use when beginning work on a Raycast extension, after the user names an extension or says to start development, or when…
Apply or audit the Frontend Stack Blueprint in an existing or new frontend repository. Use when an agent must inspect a project, select capability-gated profiles, create a blueprint.config.json contract, plan safe changes, run conformance, or verify that implementation evidence matches the blueprint without…
Integrate with or answer questions about the Qapla' shipping & tracking REST API (public v1.3). Use this when working with Qapla' to push shipments or raw orders, generate and confirm carrier labels, track parcels, get real-time multi-carrier quotes, look up pickup points (PUDO), verify addresses, list couriers and…
Guide for creating WordPress Playground Blueprint JSON files and executing WP-CLI commands. Use when building Blueprint files, automating WordPress/WooCommerce management via CLI, configuring WordPress Playground environments, or troubleshooting. Covers blueprint creation, WP-CLI commands, and WooCommerce CLI…
Structured approach to diagnosing and fixing bugs. Use when a bug is reported, a test fails unexpectedly, behavior doesn't match expectations, or when "something is wrong" but the cause isn't clear. Triggers on "debug this", "why is this broken", "this doesn't work", "investigate this failure", unexpected test…
A structured tutor for learning academic concepts, definitions, formulas, and theorems. It offers short explanations for review and longer explanations for new or difficult material.
A role-based workflow for planning, building, and reviewing AI features with several agents. Role-based means each agent takes a defined part in the work.
Combine two AI agent skills into one. Trigger phrases: /fuse, "fuse these skills", "combine skills", "merge these two skills", "create a fusion skill".
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice…
Create, edit, compile, and review rigorous mathematical Beamer/LaTeX slides for papers, lectures, seminars, reading groups, and defenses. Use for .tex decks involving theorems, proofs, definitions, notation, TikZ diagrams, or mathematical correctness. Not for PowerPoint/PPTX workflows.
Use when the user asks for a Godot practice exercise, drill, or "give me something to build" — e.g. "/godot-exercise signals", "give me a Godot drill", "something to practice CharacterBody2D with". Generates one small self-contained exercise scoped to a topic, never the solution.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
★not rated 3 7d agoA77 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: