SuperAPI AI DirectoryFind an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
26,316 results
Use the native tmux CLI to hand a set of tickets from the map/spec to the auto-detected CodeBuddy Code or Claude Code for strictly serial execution; each worker invokes /implement, and the main window only consumes terminal-state messages and independently verifies Git.
Concurrent exploration orchestration for map.md and the issues in the same directory: AgentTeam concurrently dispatches /wayfinder to speed things up, and context hygiene prevents the main Agent from bloating and losing quality; after user confirmation, start and verify Answer and status.
AgentHansa Alliance War quest workflow only. Use only when explicitly selected by agenthansa-router-copilot or the user for an Alliance War quest, New Quest,…
Ground self-referential answers in the agent's actual filesystem. Use when the user asks who the agent is, what it can do, what it knows, what it remembers,…
Create or update a workspace skill: its description, structure, instructions, and supporting files.
Choose or design a new speaking voice when the user asks for a new, different, custom, invented, or generated voice.
Provides the static system voice catalog used by Jarvis. It does not define a user-facing workflow.
Use when the user asks to discover, inspect, or invoke an agentic capability dynamically published by a paired phone or wearable, including device controls,…
Use when the user needs broad parallel research across many independent inputs with a shared output schema.
Persistent memory system for the AiTer Agent. File formats, read/write patterns, search techniques, and maintenance rules for tasks, knowledge, contacts,…
Guide for creating production-ready Agent Skills. Use when creating new skills, improving existing skills, or diagnosing why a skill isn't working effectively.…
Evaluate Agent Skills against official specifications and 8-dimensional scoring framework. Use when: (1) Reviewing SKILL.md files for quality, (2) Auditing…
Iteratively improve any output until a clear finish-line condition holds — autonomous loop modeled on Claude Code's `/goal` command. Establish ONE measurable…
Multi-agent research conference that spawns parallel autoresearchers with symposium sharing, adversarial peer review, and insight synthesis. Reads a conference.md, orchestrates N researchers in structured rounds, and produces a synthesized result combining the best findings. TRIGGER when: user mentions "autoconference" or "conference" with research context; user wants multiple researchers competing or collaborating; user wants parallel autoresearch with peer review; user mentions "conference.md"; user wants research synthesis from multiple approaches; user wants adversarial evaluation of research results. DO NOT TRIGGER when: user wants a single autoresearch loop (use autoresearch-skill); user wants a simple one-shot answer; user wants to read a single paper.
Socratic deep-interview loop that turns a vague idea into an execution-ready spec, using a quantitative ambiguity score to gate when requirements are clear…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
Run World Labs Atlas API tasks from a terminal with the worldlabs CLI. Covers install and sign-in, uploading files, running a task from a JSON request, waiting…
Use when generating LocalizeASO screenshot or field-review proposals with a BYO coding/AI agent. Pulls an agent bundle, writes structured proposals, and never…
Keep repository-level Claude and Codex agent instructions compatible by creating safe symlinks between CLAUDE.md and AGENTS.md, and between .claude/skills/*…
Route Claude 5 tiers (Haiku/Sonnet 5/Opus 5/Fable 5), effort, and subagents for cost-effective accepted results, and handle Claude 5 prompting, long-running…
Create new Claude Code skills with best practices. Use when user wants to create, extract, or build a new skill. Provides templates and GitHub automation.…
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
Use when an instruction or skill asks you to interview, grill, or clarify with the user before generating — the structured-question mechanics for ask_question…
The organization's settled decisions. Consult before asking the user any policy question, and before naming a provider or technology at design time.