prompt-dsl
Domain-specific language for categorical prompt composition with functor combinators and natural transformation operators. Use when building composable prompt…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-12 00:15
Agents & models
26,126 results
quality-enriched-prompting
[0,1]-enriched category implementation for gradient-based prompt quality optimization. Use when implementing quality-aware prompt systems, building enriched…
recursive-meta-prompting
Recursive Meta-Prompting (RMP) implementation with unified categorical syntax. Supports @mode:iterative, @quality: thresholds, >=> Kleisli composition, and…
git-guardrails-claude-code
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent…
multi-turn-runtime-adapters
Adapt AI agent runtimes (Claude Code SDK, Codex CLI app-server) into multi-turn conversational systems. Covers session lifecycle, resume/fork, event…
coordinate-agents
Drive another Sidecar-managed agent from a shell — discover targets, create the layout, start a provider, prompt and wait, read before sending keys, broadcast…
create-adapter
Create conversation adapters for importing AI chat history from different tools (Claude Code, Cursor, Warp, Codex, etc.). Covers the adapter.Adapter interface,…
create-prompt
Create prompts for sidecar workspaces. Covers prompt structure (name, ticketMode, body), template variables (ticket with fallbacks), config file locations…
drag-pane
Drag-and-drop pane resizing implementation for two-pane plugin layouts. Covers mouse event handling via the internal/mouse package, hit region registration,…
port-herdr-integration
Port one Herdr provider integration into Sidecar: read the sync report to see which provider moved, pick the port shape, keep the provider half verbatim and…
methodology
AgentOS 3-layer context, orchestrated delegation, and OpenSpec living specifications. Use when explaining how context flows through layers, how agents…
oracle-thinkdeep
Extended reasoning analysis using sequential thinking. Use for deep exploration, comprehensive analysis, complex decisions, or when you need fresh perspectives…
ops-automation-agent
Authoring playbook for building agents that automate recurring internal tasks — running scheduled workflows, syncing data between systems, posting…
sokosumi
Use when connecting existing agents to a private Sokosumi Workspace, setting up Coworkers, or working with Tasks and Jobs through the CLI.
Contradiction Lift
This skill should be used when the user wants to "synthesize two competing solutions without averaging", "resolve a design/value disagreement by lifting to a…
parallel-workload
This skill should be used when the user wants to extend the parallel-workload test framework, add a new action, modify existing actions, or add SQL coverage to…
project-init
Project initialization skill (three-tier automatic detection). When the user says "initialize project", "project initialization", "help initialize this project", "start a new project", "create a project blueprint", "help me init the project", etc., requests to establish project infrastructure for the current folder, be sure to use this skill. This skill automatically builds to the highest available tier based on this computer's toolchain: L1 local (AGENTS.md +…
startup
Start-work continuation assistant (three-tier automatic detection). When the user says "start work", "begin working", "I'm here", "where did we leave off", "let's continue", "what's next", "continue the work", "let's go", or any other request to continue the previous work, this skill must be used. This skill reads the AGENTS.md project blueprint and the handoff.md handoff file, checks git status (including remote…
notebooklm-mcp-setup
Install and connect NotebookLM MCP in AntiGravity (or another AI Agent). Load this skill when the user says "connect NotebookLM", "set up NotebookLM", "install NotebookLM MCP", or "let you operate my NotebookLM".
prompt
Use when asked to create, review, split, or save task prompts under `./prompts/`. Recreates the old /prompt command as a Codex skill for writing explicit,…
run-prompt
Use when asked to execute one or more saved prompts from `./prompts/`, including the old /run-prompt command syntax. Supports sequential execution by default…
context
Create or revise repository instructions using verified commands, paths, architecture constraints, and review expectations. Use when creating AGENTS.md or…
software-factory
software-factory — an installable skill for AI agents, published by mattpocock/skills.
neovim
Neovim remote control and socket management for tmux environments. Use this skill when you need to control Neovim instances from agents, open files in existing…