agent-send
Send messages to AI agents in Discord, Telegram, Slack. Use when: delegating tasks conversationally or multi-agent collaboration.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
Agents & models
25,573 results
aieos-identity
Portable AI identity system using AIEOS (AI Entity Object Specification) - import, export, and manage agent personas in a standardized JSON format.
gitlab-claude
Interact with GitLab via the glab CLI. Supports six MR workflows — Create (create MR), Read (summarize), Review (full code/security/QA review), Fix (review +…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
skills-cli
Use when users ask to discover, install, list, check, update, remove, back up, restore, sync, or initialize Agent Skills, mention `bunx skills`, `npx skills`,…
naval-perspective
Naval Ravikant's thinking operating system. Based on in-depth research of his works, podcasts, tweets, decision records, and external criticism, distilling 5 core mental models, 8 decision heuristics, and a complete expression DNA. Once activated, immersively role-play as Naval, responding to questions directly from the "I" perspective. When the user mentions "from Naval's perspective," "what would Naval think," "Naval mode," "Naval…
kiroku-memory
AI Agent long-term memory system with cross-session, cross-project persistence. Triggers: - /remember - Store memories - /recall - Search memories - /forget -…
afk-impl
Used for AFK execution of planned and completed long tasks
browser-use-expert
Senior Web Automation Engineer. Expert in browser-use CLI, Python library, and agentic web orchestration (v0.11.4+).
aile-using-superpowers
Use at the start of any conversation - determine how to find and use skills, and require the skill tool to be invoked before any response (including clarifying questions)
open-tag-admin
Admin/control console for an Open Tag Slack tag-in workflow backed by MFS. Use to set up a new Open Tag bot from scratch, check what is currently running…
deliberation
Structured deliberation support for decisions worth sitting with — ethical questions, architecture choices, trade-offs, decisions where the user wants clarity…
task-execute
Continuous execution framework: keeps Claude running efficiently across long-term tasks spanning multiple conversation turns. Use this skill when the user's task is large in scope and needs to be completed across multiple context windows. Trigger scenarios include: the user mentions "long-term task", "multi-stage project", "cross-session development", "large feature development", "requires multiple conversations to complete", …
task-start
Task kickoff process: requirement alignment + UI prototype confirmation + solution design. Triggered when receiving new features, complex tasks, or large requirements. Includes a decision tree to determine which path to take, an alignment checklist, a UI prototype preview step, solution templates, and examples. Trigger words: new feature, implement xxx, large task, unclear requirement. Workflow position: task-start → task-execute → task-finish
coliseum-dispatch
Dispatches a composed set of assignment envelopes to domain-expert subagents in parallel, in a single message with multiple Agent tool calls. Enforces the…
coliseum-orchestrator
Threads the four-phase grain-to-coliseum transformation — given a dense prompt (the "grain"), autonomously surfaces parallel dimensions, composes…
dimension-surfacing
Surfaces the parallel domain dimensions implicit in a dense or minimal prompt. Use when a user prompt is small on the surface but plainly implies multiple…
governance-evolution-protocol
Phase 5 of the pentaphase structural-overhaul protocol. Codifies operational protocols, onboards the ecosystem of participants, programs behavior monitoring,…
find-loops
Search the agenticloops.dev directory for an existing agentic loop (a recurring, scheduled agent) and install it. Use when someone wants a repeating job run on…
mlx-fine-tuning
Specialized skill for MLX-based LLM fine-tuning on Apple Silicon. This skill should be used when working with LoRA fine-tuning, model conversion from…
model-hierarchy
Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity. Use this skill when: (1) deciding which model to use for a task,…
rightstack
Use RightStack as a read-only Web3 stack advisor for architecture recommendations, workflow inspection, tool comparisons, and package-migration checks. Use for…
agent-telegrambot
Interact with Telegram using bot tokens - send messages, read chats, manage reactions
make-skill
Create a focused workspace Skill from reusable decisions, knowledge, templates, or workflows in the current conversation. Use for /make-skill with a focus…