SuperAPI AI DirectoryFind an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
25,657 results
The 5-part method for writing cinematic AI video prompts (works for Seedance / Xiaoyunque / Sora / Kling / Jimeng), including 14 rules for avoiding failures. Attach it to the steps for writing video prompts, storyboards, and short drama scripts.
Eliminate overthinking: act on intent, cache decisions, stay in scope. Trigger: When agent hesitates, over-analyzes, or re-litigates.
Synchronization across model directories. Trigger: After creating or modifying skills, agents, or prompts to sync across directories.
Portable credential management for AI agents using age encryption, session-scoped leases, auto-rotation, and killswitch. Use this skill when agents need…
Scan recent agent sessions for repeated friction, corrections, approvals, workflow patterns, and packaging candidates. Use when asked to find signals,…
Reference template for creating new Loom agent personas. Use when adding a new role to the org chart, defining a new agent's responsibilities, or bootstrapping…
Generate a visual spec-to-code coverage map showing which code files are covered by which specifications. Creates ASCII diagrams, reverse indexes, and coverage…
Create or update Codex custom subagent TOML files under `.codex/agents/` or `~/.codex/agents/`. Use when the user asks to create, design, review, or refine a…
Route desktop and browser work across an isolated browser, the harness's own Chrome extension (Claude in Chrome, the Codex Chrome plugin, or the bundled Agent…
Multi-agent orchestration patterns: delegation, context passing, workflow gates, and role-based coordination. Activate when coordinating multiple specialized…
Turn a confirmed software mission into a coordinated five-role Codex engineering workflow with visible named SubAgents that plan, review, implement, test,…
Lindy is an AI agent creation and management platform focused on business process automation. It enables organizations to build sophisticated AI-powered…
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
Upgrade a plugin's skills, hooks, and patterns to align with latest Claude Code capabilities and best practices. Use when a plugin needs modernization, after…
Prefer @kodycodes/cli execute --local over hosted MCP execute when the agent has shell + Node. Use when running Kody execute / calling Kody from an agent that…
Use when working with the Peekaboo CLI or MCP server to capture macOS screens, inspect UI elements, and automate GUI interactions…
A skill for managing an AI agent's memory across sessions. Operate a five-layer memory architecture with the openclaw-mem CLI, handle memory tasks throughout the session lifecycle (start/middle/end), manage project Brains, and maintain memory hygiene. memory, context, handoff, working memory,…
MacBook MLX local LLM orchestration skill for running lightweight on-device models via command line. Use when you need local inference, private/offline…
Local-first RAG memory system for AI agents. Progressive Disclosure search, Auto-Capture from sessions, Brain directories for per-project context, injection…
Dispatch multiple subagents for independent tasks simultaneously. Use when facing 2+ unrelated tasks that can proceed without shared state or sequential…
Guide for creating effective SKILL.md files that extend agent capabilities. Use when creating new skills, updating existing ones, or teaching the agent…
Execute implementation plans using fresh subagents per task with two-stage review (spec compliance + code quality). Use when executing multi-task plans with…
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or…