create-plugin
Create OpenClaw plugins/extensions (TypeScript modules) from natural‑language requests. Use when the user asks to create a plugin/extension, add a new slash command, add plugin tools, or says “create plugin that does …” or “create OpenClaw plugin called NAME …”. Trigger for /create-plugin NAME WHAT-IT-DOES, /create-plugin GENERAL-PROMPT, “create extension that does ACTION”, or similar.
What this skill does
# Create Plugin
**Note to User:** Depending on its permissions, OpenClaw can already create its own plugins. This skill streamlines the process. Plugins can change how OpenClaw works. They run in‑process with the gateway, so treat them as trusted code.
## References
Use any of the following sources for reference, as they may be more up to date than this skill:
- [OpenClaw Plugin Docs](https://docs.openclaw.ai/plugins/)
- [OpenClaw Plugins > Agent Tools](https://docs.openclaw.ai/plugins/agent-tools/)
- [Repo docs: Plugins](https://github.com/openclaw/openclaw/blob/main/docs/plugin.md)
- [Repo docs: Agent tools](https://github.com/openclaw/openclaw/blob/main/docs/plugins/agent-tools.md)
- If local repo exists: `<openclaw-repo>/docs/plugin.md`, and `<openclaw-repo>/docs/plugins/agent-tools.md`
If you can access those links, they may be more up to date than this skill. Defer to them if there are discrepancies. Otherwise, this skill shows how to create an OpenClaw plugin as of February 2026.
## Overview
Turn a user request into a working OpenClaw plugin: choose an id, scaffold files (`openclaw.plugin.json`, `index.ts`, optional `package.json`), implement commands/tools/services, and document how to enable/restart.
## Workflow
### 1) Parse intent + confirm scope
- Identify the plugin id and primary capability (auto‑reply command, agent tool, CLI command, channel, service, etc.).
- If the request is ambiguous, ask for:
- Desired plugin id/name
- What triggers it (slash command? agent tool?)
- Expected output/side effects
- Any dependencies or external binaries
- Config fields (API keys, flags, defaults)
### 2) Choose location + id
Pick a plugin root directory:
- **Recommended (safe from upgrades):** `~/.openclaw/extensions/<id>`
- Local dev (workspace‑scoped): `<workspace>/.openclaw/extensions/<id>`
- Custom path: add to `plugins.load.paths`
Local dev install options:
- Copy install: `openclaw plugins install /path/to/plugin`
- Symlink install: `openclaw plugins install -l /path/to/plugin`
Normalize id to lowercase, hyphenated, <=64 chars.
### 3) Create required files
**Always include a manifest** (`openclaw.plugin.json`):
```json
{
"id": "my-plugin",
"name": "My Plugin",
"description": "...",
"configSchema": {
"type": "object",
"additionalProperties": false,
"properties": {}
}
}
```
Notes:
- `configSchema` is required even if empty.
**Plugin entrypoint** (`index.ts`):
```ts
import type { OpenClawPluginApi } from "openclaw/plugin-sdk";
export default function register(api: OpenClawPluginApi) {
// registerCommand / registerTool / registerCli / registerService / etc.
}
```
**Optional `package.json`** when you want a pack or npm metadata:
```json
{
"name": "@openclaw/my-plugin",
"version": "0.1.0",
"type": "module",
"openclaw": { "extensions": ["./index.ts"] }
}
```
### 4) Implement features
Always write and run tests for your plugin features.
**Auto‑reply command** (no LLM run):
```ts
api.registerCommand({
name: "mycmd",
description: "...",
acceptsArgs: true,
requireAuth: true,
handler: async (ctx) => ({ text: "OK" }),
});
```
Rules:
- Commands are global, case‑insensitive, and must not override reserved names.
- `acceptsArgs: false` means `/cmd args` won’t match.
**Agent tool** (LLM‑callable):
```ts
import { Type } from "@sinclair/typebox";
api.registerTool({
name: "my_tool",
description: "Do a thing",
parameters: Type.Object({ input: Type.String() }),
async execute(_id, params) {
return { content: [{ type: "text", text: params.input }] };
},
});
```
Optional tools (opt‑in):
```ts
api.registerTool({ ... }, { optional: true });
```
Enable optional tools via `tools.allow` or `agents.list[].tools.allow`.
### 5) Enable + restart
If you have ability to run commands, ask the user whether you can run the following commands, otherwise provide them as instructions.
- Enable: `openclaw plugins enable <id>` (or set `plugins.entries.<id>.enabled = true`)
- Restart gateway after changes.
- Check errors: `openclaw plugins doctor`
## Output expectations
When creating a plugin, produce:
- The plugin file tree
- The exact file contents for `openclaw.plugin.json` and `index.ts`
- Any config snippet required (`plugins.entries.<id>.config` or tool allowlist)
- Reminder and instructions to enable the plugin and restart the gateway, and how to test the new functionality
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.