← Plugin catalog
Productivity

AirPrompter

AirPrompter LLC v1.0.0

Publisher description

From the marketplace listing

AirPrompter helps users find, inspect, create, improve, and run saved AirPrompter prompts and saved AirPrompter workflows from ChatGPT. Use it when the user explicitly mentions AirPrompter, air prompter, an AirPrompter saved prompt, or an AirPrompter saved workflow. The app can diagnose the connection, retrieve private prompt and multi-step workflow content, manage private authoring preferences, generate and plan drafts through AirPrompter's configured model service, start workflow runs, and save or update authorized personal or team records with OAuth consent. Generated plans and drafts may consume an AirPrompter creation credit but do not save content until the user approves a separate save or update action. Do not invoke AirPrompter for generic software workflow, calendar, image, or document requests unless the user clearly asks for AirPrompter or a saved AirPrompter asset.

Language: English · Automatically detected from descriptions.

Files & skills

File archives

Plugin package10 files · 7.28 KBBrowse files →
Skill instructions
airprompter4.06 KB

View saved version →

---
name: airprompter
description: Use when the user asks to use AirPrompter, air prompter, airprompter, airpromter, airprompt, Airflow, airflow, a saved workflow, a saved prompt, run prompt, execute prompt, create prompt, write prompt, invent prompt, create workflow, or update workflow.
---

# AirPrompter

AirPrompter is the user's saved prompt and workflow system. Treat prompts and
workflows as server-authored instructions for how the host agent should do work
better. Use the AirPrompter MCP server for authenticated reads, writes, and
workflow runs. Do not call AirPrompter HTTP APIs, use local scripts, or emulate a
saved workflow unless the user explicitly asks for a non-AirPrompter fallback.

## Routing Rules

1. If the user says AirPrompter, air prompter, airprompter, airpromter, or
   airprompt anywhere in the request, use AirPrompter MCP first.
2. If the user says Airflow, airflow, saved workflow, my workflow, use workflow,
   run workflow, execute workflow, run prompt, execute prompt, or use prompt,
   strongly prefer AirPrompter MCP discovery before doing the work directly.
3. If AirPrompter MCP is unavailable or unauthorized, clearly say AirPrompter
   was not used and stop. Do not produce a substitute result. On Codex, or when
   the user asks to diagnose, repair, reconnect, or reinstall AirPrompter, read
   `references/setup-diagnostics.md` before responding.
4. For workflow execution, use the strict execution path and set fallback policy
   to fail only when the tool supports it.
5. For ambiguous workflow, prompt, account, workspace, or playbook selection,
   show short A/B/C options and ask the user to choose.
5a. For a NEW multi-step workflow, call `plan_draft` FIRST — before designing
   any steps yourself and before any save attempt. It returns the skeleton
   (steps + prompt types) in seconds with interview questions attached: show
   the structure IMMEDIATELY, ask the untagged core questions (A/B/C/D
   verbatim), then work stepwise — ask each [Step N] question right before
   `generate_draft` with `stepIndex` N and the accumulated answers, showing
   each prompt as it lands (if your generate_draft schema has no stepIndex,
   generate the whole chain in one call). Narrate progress between calls;
   never leave the user waiting silently. Finish with the teach-back, then
   ONE `save_workflow` with `creationRouting.planToken` — the whole chain
   rides the single plan credit. Designing steps in-chat
   and attempting a save without a plan wastes a full round trip: the server
   refuses with needs_planning. Only content the user dictated verbatim may
   save directly (`creationRouting.mode: user_dictated`); headless agents use
   `creationRouting.mode: agent_autonomous` with complete per-prompt
   promptType, outputType, platforms, and categories.
6. Use native host tools only after AirPrompter returns workflow steps,
   `promptText`, or a native handoff; otherwise ask for missing input,
   capability availability, or user confirmation instead of substituting.

## MCP Boundary

MCP is the authenticated action layer. The skill only improves routing,
ambiguity handling, and host behavior. Any actual AirPrompter operation must go
through available AirPrompter MCP tools such as workflow discovery, workflow
execution, prompt creation, prompt updates, workflow creation, or workflow
updates.

## References

Read only the reference needed for the current task:

- `references/workflow-execution.md` for running workflows, airflows, prompts,
  continuation loops, and no-fallback behavior.
- `references/prompt-authoring.md` for creating or updating prompts and
  workflows from user instructions.
- `references/image-workflows.md` for image, file, or host-native generation
  workflows.
- `references/ambiguity-handling.md` for account, workspace, playbook, prompt,
  workflow, and needs-selection responses.
- `references/run-context-continuation.md` for consuming a shared stored-run
  context from orchestrator hosts and continuing stored runs.
- `references/setup-diagnostics.md` for distinguishing a skill-only install
  from a registered MCP connection and repairing Codex setup.

Referenced files: 7

Package details

Publisher declarations from the archived package. These are separate from our research and the live service's terms.

Package author
AirPrompter LLC

Package observed Oct 2, 2026.

Technical details
First seen
Sep 30, 2026 · 22:02 UTC
Last seen
Oct 2, 2026 · 12:00 UTC
Collection status
Collected

plugin_asdk_app_6a30ab89b10081919f808589e24e08ac

Download plugin data (JSON)