/install n8n-evol-i
n8n-evol-I skill router
This is the entry point. When the user asks anything n8n-related, route to the matching sub-skill.
Mental model
- The skill package (this directory) is read-only. You never edit files here.
- The user's project state lives in
${PWD}/n8n-evol-I-workspace/(created byinit.md). - Helpers are Python scripts under
helpers/. Invoke them withpython3 ${CLAUDE_PLUGIN_ROOT}/helpers/\x3Cname>.py [args](plugin mode) orpython3 \x3Cpath-to-harness>/helpers/\x3Cname>.py [args](skill mode). - All helpers default to
--workspace ${PWD}/n8n-evol-I-workspace. Pass--workspace \x3Cpath>if the user runs from elsewhere. - Agent memory: read
N8N-WORKSPACE-MEMORY.mdin the workspace at the start of every session; append a dated entry whenever you learn something durable about this project. Full guidance inAGENTS.md(also in the workspace root).
Lifecycle skills (use when the user wants to do X)
| Skill | When |
|---|---|
| init.md | First-time setup. Creates the workspace at ${PWD}/n8n-evol-I-workspace/. |
| bootstrap-env.md | Configure an environment (dev / staging / prod). Creates env YAML + .env, validates, mints placeholder workflow IDs. |
| doctor.md | Health check. Run before/after major changes. |
| create-new-workflow.md | Author a brand-new workflow. |
| register-workflow-to-error-handler.md | Wire settings.errorWorkflow. |
| create-lock.md | First-time setup for distributed locking (Redis-backed primitives). |
| copy-primitive.md | Copy a single primitive (any) into the workspace. General-purpose; doesn't register. |
| add-lock-to-workflow.md | Wrap a workflow's main flow in lock acquire/release. |
| add-rate-limit-to-workflow.md | Gate a workflow's main flow with a Redis-backed fixed-window rate-limit check. |
| tidy-workflow.md | Apply n8n's canvas-layout algorithm to a workflow template to clean up node positions. |
| deploy.md | Deploy one workflow to one env. |
| activate-single-workflow-in-env.md | Activate after deploy. |
| deactivate-single-workflow-in-env.md | Pause triggers (commonly during dev). |
| archive-workflow.md | Retire a deployed workflow (hidden + read-only on the live instance). |
| unarchive-workflow.md | Restore a previously-archived workflow so it accepts updates again. |
| deploy_all.md | Roll out an entire env in tier order. |
| resync.md | Pull live state of one workflow back into its template. |
| resync_all.md | Snapshot a full env back to templates. |
| dehydrate-workflow.md | Convert raw exported JSON into a template. |
| validate.md | Structural REST validation before deploy. |
| run.md | Fire a webhook + assert terminal status. |
| debug.md | Investigate a failing or missing execution — from vague symptom to root-cause with evidence. |
| deploy-run-assert.md | One-shot validate → deploy → run verify. |
| find-skills.md | While authoring, find applicable patterns/integrations. |
| manage-credentials.md | Create or link n8n credentials (Path A from .env.\x3Cenv> / Path B from existing UI credential). |
| add-cloud-function.md | Scaffold a Python serverless function / cloud function / serverless API under \x3Cworkspace>/cloud-functions/. |
| iterate-prompt.md | Optimize a prompt against a paired schema + dataset using DSPy. |
| test.md | Run unit tests over n8n Code-node JS and / or cloud-function Python. |
Pattern skills (read-only knowledge)
These are reference docs, not action triggers. Read them while authoring.
- skills/patterns/subworkflows.md
- skills/patterns/error-handling.md
- skills/patterns/credential-refs.md
- skills/patterns/multi-env-uuid-collision.md
- skills/patterns/validate-deploy.md
- skills/patterns/code-node-discipline.md
- skills/patterns/llm-providers.md
- skills/patterns/locking.md
- skills/patterns/pindata-hygiene.md
- skills/patterns/position-recalculation.md
- skills/patterns/prompt-and-schema-conventions.md
- skills/patterns/agent-api-discipline.md
- skills/patterns/investigation-discipline.md
Integration skills (per-service quirks)
- skills/integrations/microsoft-365/excel-and-sharepoint.md
- skills/integrations/gmail/sending-email.md
- skills/integrations/redis/lock-pattern.md
- skills/integrations/sentry/README.md
- skills/integrations/datadog/README.md
- skills/integrations/slack/README.md
- skills/integrations/google-drive/README.md
- skills/integrations/notion/README.md
- skills/integrations/airtable/README.md
- skills/integrations/webhooks/README.md
Placeholder syntax (workflow templates)
Templates use {{@:type:path}} (preferred form) or the canonical long form {{INTERPOLATE:type:path}}. The two are equivalent — @ is an alias for INTERPOLATE. Examples below use the @ form.
| Type | Syntax | Source |
|---|---|---|
env |
{{@:env:key.path}} |
YAML config value (dot notation) |
txt |
{{@:txt:relative/path.txt}} |
Text file in workspace |
json |
{{@:json:relative/path.json}} |
JSON file (stringified) |
html |
{{@:html:relative/path.html}} |
HTML file |
js |
{{@:js:relative/path.js}} |
JavaScript file |
py |
{{@:py:relative/path.py}} |
Python file (Code-node language: python) |
uuid |
{{@:uuid:identifier}} |
Fresh UUID v4 (consistent within one hydration) |
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install n8n-evol-i - 安装完成后,直接呼叫该 Skill 的名称或使用
/n8n-evol-i触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
N8N EVOL I 是什么?
A harness to help coding agents build, deploy, maintain, and debug multi-workflow n8n-powered automation systems. No lock-in — work from the agent, continue... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 79 次。
如何安装 N8N EVOL I?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install n8n-evol-i」即可一键安装,无需额外配置。
N8N EVOL I 是免费的吗?
是的,N8N EVOL I 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
N8N EVOL I 支持哪些平台?
N8N EVOL I 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 N8N EVOL I?
由 Mo Acen(@mwamedacen)开发并维护,当前版本 v1.0.1。