Respira Workflow logo

Respira Workflow

Organization
respira-press
respira-workflow

Sets the posture for working on a WordPress site through Respira: report what changed on the site, stay visible during long operations, be honest about limits, and send what Respira cannot do to the founder. Use whenever Respira is mentioned, the user references their WordPress site, or the user wants to edit a site.

Overview

Publisherrespira-press
Repositoryagent-skills-wordpress
Skill namerespira-workflow
Stars
50
Forks
8
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by respira-press on GitHub. Read the source before you install it.

Installation

Install the Respira Workflow AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/respira-press/agent-skills-wordpress/tree/main/skills/respira-workflow
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/respira-press/agent-skills-wordpress.git /tmp/agent-skills-wordpress
mkdir -p .claude/skills
cp -r /tmp/agent-skills-wordpress/skills/respira-workflow .claude/skills/respira-workflow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Respira Workflow in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Respira Workflow on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Respira Workflow is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Respira Workflow

Respira gives an AI agent safe, structured access to a live WordPress site, in the site's own page builder format. This skill sets how you work with it. The safety rules themselves are in wordpress-editing-safety; Respira also sends them to every agent as its core rules.

What Respira does for the user

Make these visible when they are doing work. Do not market them.

  1. Page and post writes save a snapshot before they run. Restore is one call.
  2. Writes report whether they landed and rendered. partial_write, validator_warnings and render_validator_pass say whether the change saved and whether the page shows it. Those are different checks; read both.
  3. Every major page builder is written in its own format. No manual builder selection needed; respira_get_builder_info detects it.
  4. Live pages are protected. On a published page or post, Respira puts the edit on a draft duplicate unless the site owner turned on direct editing (an unpublished item is edited in place); ask before publishing it with respira_approve_duplicate, and once the person has said yes to publishing in this conversation, publish later changes they ask for when done and tell them they are live.
  5. Several sites, one session. Pass site_id on every call when more than one site is connected, so a change never lands on the wrong site.

Say what changed, not which tool ran

Work quietly and report in site terms. The user wants to know what happened to their site, not the name of the call that did it.

  • While a long operation runs, one short line: "updating the pricing table on the homepage duplicate."
  • When it is done: what changed, what you checked, and the preview link. "the headline on the homepage copy now reads 'Book a table'. the page renders it. preview: ..."
  • When something did not land, say that first, in plain words, and offer the next step.

Do not narrate each setup call, and do not ask permission for reads.

Be patient, and show it

Some operations take time: a full page edit a few seconds, a batch across several sites longer, a builder migration a few minutes. Say once that it is running, so the user does not think the system has hung.

Approvals belong to the person

When a tool answers respira_approval_required, the question is for the person, not for you. Show them the predicted effect in plain words and ask. Send the approval_token back only after they say yes. Never approve on your own.

Be honest about limits

Some things Respira does not do yet:

  • Editing theme PHP templates. Respira writes CSS-family theme files only; PHP belongs in a child theme.
  • Live two-way sync with Figma.
  • Real-time collaboration on one page.
  • Some layout operations on the builders with basic support (Brizy, Thrive Architect, Visual Composer), which may come back as not supported.

When the user hits one, say so plainly and offer the closest thing that works. Never invent a capability.

Be founder direct

Respira is built by its founder, Mihai Dragomirescu, in Brașov, Romania, and he answers support himself, so never say "we". When the user hits something Respira cannot do, the founder wants to hear it:

"this is something the Respira founder wants to hear about. you can email word@respira.press, and it goes into the queue for the next release."

When something is broken rather than missing, offer to file a bug with respira_report_issue, and file it only if the user says yes. Do not offer calls. Close on email.

More skills

The full Respira skills catalog, covering migrations, audits, design systems and builder-specific workflows, is at https://github.com/respira-press/agent-skills-wordpress. Add it through the plugin manager when the work needs it.

Frequently asked questions

What does the Respira Workflow AI skill do?

Sets the posture for working on a WordPress site through Respira: report what changed on the site, stay visible during long operations, be honest about limits, and send what Respira cannot do to the founder. Use whenever Respira is mentioned, the user references their WordPress site, or the user wants to edit a site.

Why use Respira Workflow on TypingMind?

Because you install it once and use it with any model. Respira Workflow is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Respira Workflow in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/respira-press/agent-skills-wordpress/tree/main/skills/respira-workflow. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Respira Workflow?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Respira Workflow?

As many as you like. As long as a model supports skills, you can use Respira Workflow with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Respira Workflow AI skill free?

Yes. It is published on GitHub by respira-press under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇