diff --git a/blog/posts/speed-run-n8n-skill.html b/blog/posts/speed-run-n8n-skill.html index 59af11a..834ce07 100644 --- a/blog/posts/speed-run-n8n-skill.html +++ b/blog/posts/speed-run-n8n-skill.html @@ -152,6 +152,73 @@ Deploy your n8n-connected agent now.

+

Standalone n8n Prompt for Hermes Agent

+

Copy this entire prompt into any Hermes agent (derez.ai or self-hosted) to give it direct n8n integration skills — REST API access, skill library awareness, and workflow execution management. Replace the API key with your own n8n instance key.

+ +
+ ## Integrations

+ + ### N8N Skills
+ Create a skill that integrates with n8n's skill library and REST API.

+ + ## Configuration
+ N8N_URL=https://n8n.derez.ai/
+ N8N_API_KEY=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiJhOTY0NDQ1Ni1hZGUxLTRlZjUtYmE0NC03MjRiZjhhY2JmNGUiLCJpc3MiOiJuOG4iLCJhdWQiOiJwdWJsaWMtYXBpIiwianRpIjoiZTExMTY3YjUtMGU1Yy00MTNhLWI0YzAtNGU5MGYyODFiMzk2IiwiaWF0IjoxNzgxNzcyNzE3LCJleHAiOjE3ODIzNTY0MDB9.g-SG9u7g9sD0lhD6fr6PZKcBs38Eq3p14Yf8yiPXO-U

+ + ## Skill library
+ You have access to n8n's official skill library at https://github.com/n8n-io/skills

+ At the start of every task, clone or pull the latest version of this repo to discover available skills.

+ if [ ! -d /tmp/n8n-skills ]; then
+   git clone --depth 1 https://github.com/n8n-io/skills /tmp/n8n-skills
+ else
+   cd /tmp/n8n-skills && git pull --ff-only
+ fi

+ Read the README.md and INDEX.md files in that repo to understand what skills are available. Each skill has a dedicated directory with a README.md describing its purpose and usage. Choose the most relevant skill(s) for the user's request.

+ + ## API basics
+ All calls go to {N8N_URL}/rest/... with the header:
+ X-N8N-API-KEY: {N8N_API_KEY}

+ The n8n REST API documentation is available at {N8N_URL}/api/v1/openapi.json — fetch it if you need to discover available endpoints.

+ + ### Common operations

+ List workflows:
+ curl -s -H 'X-N8N-API-KEY: {key}' '{N8N_URL}/rest/workflows'

+ Get a workflow by ID:
+ curl -s -H 'X-N8N-API-KEY: {key}' '{N8N_URL}/rest/workflows/<id>'

+ List executions:
+ curl -s -H 'X-N8N-API-KEY: {key}' '{N8N_URL}/rest/executions'

+ List credentials:
+ curl -s -H 'X-N8N-API-KEY: {key}' '{N8N_URL}/rest/credentials'

+ List tags:
+ curl -s -H 'X-N8N-API-KEY: {key}' '{N8N_URL}/rest/tags'

+ + ## Workflow skill execution pattern

+ When a skill from the library maps to a workflow to run:

+ 1. Read the skill's README.md to understand the inputs, outputs, and workflow structure.
+ 2. Check if a matching workflow already exists in n8n (use the list endpoint).
+ 3. If it does, create an execution:

+ curl -s -X POST '{N8N_URL}/rest/workflows/<id>/run' \
+   -H 'X-N8N-API-KEY: {key}' \
+   -H 'Content-Type: application/json' \
+   -d '{"data": <input_data>}'

+ 4. If it doesn't, create a new workflow using the skill's specification:

+ curl -s -X POST '{N8N_URL}/rest/workflows' \
+   -H 'X-N8N-API-KEY: {key}' \
+   -H 'Content-Type: application/json' \
+   -d '{"name": "<skill-name>", "nodes": [...], "connections": {...}}'

+ 5. Poll execution status:

+ curl -s -H 'X-N8N-API-KEY: {key}' '{N8N_URL}/rest/executions/<id>' | jq '.data'

+ + ## Solved cases log
+ After every successful n8n task, append to ~/n8n_solutions.md:

+ ## <short title> (<date>)
+ Goal: <one sentence>
+ Skill used: <skill path in the library>
+ Key commands: <the curl | jq pipelines that worked>
+ Gotchas: <anything non-obvious>

+ Read ~/n8n_solutions.md at task start — if a matching case exists, reuse it directly. +
+

derez.ai — Deploy your AI agent in 10 Minutes.