Use when the task involves elizaOS core runtime concepts, plugins, actions, providers, evaluators, services, memories, state composition, or upstream elizaOS development. Covers the main abstractions and the TypeScript runtime mental model.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add elizaOS/eliza --skill elizaos --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Elizaos?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/elizaos-elizaos)More formats (shields.io, HTML) on the badges page.
---
name: elizaos
description: "Use when the task involves elizaOS core runtime concepts, plugins, actions, providers, evaluators, services, memories, state composition, or upstream elizaOS development. Covers the main abstractions and the TypeScript runtime mental model."
---
# elizaOS
elizaOS is the plugin-based agent runtime that Eliza builds on top of.
## Read These References First
- `references/core-abstractions.md` for the runtime mental model and message flow
- `references/plugin-development.md` for plugin extension points and implementation patterns
## Use This Skill When
- a change touches the elizaOS runtime in `packages/core/`
- you need to reason about `AgentRuntime`
- you are implementing or debugging actions, providers, evaluators, services, or model handlers
- you need the correct plugin lifecycle instead of guessing from Eliza wrappers
## Working Rules
- Treat the TypeScript runtime in `packages/core/src/` as the primary reference implementation.
- Prefer elizaOS-native abstractions over product-specific wrappers when reasoning about upstream behavior.
- Remember the split between persistent `Memory` and ephemeral `State`.
- Remember that plugins are the main composition mechanism.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
