Loading...
Loading...
Found 504 Skills
Structured memory creation workflow. Converts messy notes, conversations, and unstructured thoughts into well-typed, tagged, confidence-scored memories. Uses 1-question-at-a-time clarification to avoid cognitive overload.
Interactive workflow for creating, configuring, connecting, and publishing AI agents on Agents.Hot using the agent-mesh CLI. Also covers CLI command reference, flags, skill publishing, and troubleshooting. Trigger words: create agent, manage agent, publish agent, agent description, agent setup, list agents, delete agent, connect agent, agent-mesh command, CLI help, agent-mesh flags, connect options, agent-mesh troubleshooting, TUI dashboard, publish skill, skill init, skill pack, skill version, skills list, unpublish skill, install skill, update skill, remove skill, installed skills.
Use when creating new skills, editing existing skills, or verifying the validity of skills before deployment
Documentation and commit specialist. Runs after ralph subagents complete a Priority group. Reviews RALPH_DONE signals, updates progress.md and PRD task checkboxes, and makes one atomic git commit per completed user story. Also writes an implementation summary when the full PRD is done. Use after ralph subagents finish implementing — never during active development.
Design, apply, and maintain SKOS taxonomies for joelclaw agent workflows. Use when defining concept schemes, classifying agent inputs/outputs, mapping to external vocabularies, or integrating taxonomy metadata with Typesense retrieval.
Use this skill when you need to operate the Creem CLI for authentication checks, products, customers, checkouts, subscriptions, transactions, configuration, monitoring, or terminal automation workflows. Prefer it for agent-driven Creem tasks that should use real CLI commands and JSON output instead of dashboard clicks or guessed API calls.
Use when the user wants to push past conventional workflow limits with advanced performance techniques like parallel orchestration, streaming pipelines, or adaptive routing.
Mechanize Pattern 15 — the seven-pass adversarial review protocol for academic manuscripts. Spawns 7 forked subagents in parallel (abstract, intro, methods, results, robustness, prose, citations), then synthesizes a prioritized revision checklist. Use for submission-ready or R&R-stage papers where single-pass review isn't enough.
Use this skill when the user types "/notes" or "@notes" with phrases like "save this", "document this", "file this under <project/client>", "extract decisions", "extract action items", or "update notes from this discussion". The skill spawns the notes-librarian subagent to extract durable knowledge and file it into the right Docmost page using the existing workspace structure. Falls back to a configured inbox page when confidence is low.
TanStack AI (alpha) provider-agnostic type-safe chat with streaming for OpenAI, Anthropic, Gemini, Ollama. Use for chat APIs, React/Solid frontends with useChat/ChatClient, isomorphic tools, tool approval flows, agent loops, multimodal inputs, or troubleshooting streaming and tool definitions.
Use when the user asks you to start, join, or continue a conversation with other agents via chatter, agent-chat, or talking to other agents about X.
Execute Python code in isolated rootless containers with MCP server proxying for token-efficient agent workflows