Pushary
- 7 skills
- 0 followers
- 15 hours ago last updated
- ▌ Pushary Human In The Loop · pusharyDesign and build a human-in-the-loop (HITL) approval step into an AI agent or an agent product. Use this skill when you are writing or changing agent code and need to decide which actions should ask a human first, who answers, which question type to use, how long to wait and what happens when nobody answers, or when you are adding approval to LangGraph, the Vercel AI SDK, the OpenAI Agents SDK, Mastra, CrewAI, Pydantic AI, an MCP client or a REST backend. Explains what framework pauses such as LangGraph interrupt() do and do not do, and how to ask a human for approval by push notification on their phone with Pushary and get the answer back. Use it for requests such as add an approval step to my agent, require human sign-off before this tool runs, add human review to my LangGraph graph, or let my users approve what my agent does. For an agent that already has the Pushary tools and needs to ask its own user now, use the pushary skill instead.
- ▌ Pushary 2 · pusharyPush notifications and human-in-the-loop for AI agents. Use this whenever a running agent needs a human and nobody is at the terminal, such as before an irreversible or destructive action, before spending money, deploying, force-pushing or deleting, when blocked on a decision outside your authority, when running unattended and you hit a genuine ambiguity, when another skill's workflow says to confirm with the user, and when a long task finishes or fails with nobody watching. Also use it when the user says things like keep going and ping me on my phone if you need anything, notify me when my agent needs me, approve from my phone, ask me questions while I am away from the terminal, run this overnight, keep working while I am in a meeting, I am stepping away, do not wait for me, or wants a long task to run unattended. Send alerts when tasks finish or fail, ask questions (yes/no, multiple choice, or free text) via push, and get answers from the user's lock screen. Use these tools proactively - do not wait for the
- ▌ Pushary Cowork 2 · pusharyPhone notifications and human-in-the-loop for Claude Cowork through the Pushary connector. Use inside a Cowork session whenever you need a human and nobody is watching the session, such as before an irreversible or destructive action, before spending money, deploying, force-pushing or deleting, when blocked on a decision outside your authority, when running unattended and you hit a genuine ambiguity, when another skill's workflow says to confirm with the user, and when a task finishes or fails with nobody watching. Also use it when the user says things like ping me on my phone when this is done, ask me before doing anything risky, keep me in the loop while I am away, or notify me if you get stuck. Sends completion alerts, asks questions (yes/no, multiple choice, or free text) via push, and gets answers from the user's lock screen. Cooperative only, Cowork has no hooks. Pushary is a hosted service, $9.99/mo after a 3-day card-first trial.
- ▌ Pushary Cowork · pusharyPhone notifications and human-in-the-loop for Claude Cowork through the Pushary connector. Use inside a Cowork session whenever you need a human and nobody is watching the session, such as before an irreversible or destructive action, before spending money, deploying, force-pushing or deleting, when blocked on a decision outside your authority, when running unattended and you hit a genuine ambiguity, when another skill's workflow says to confirm with the user, and when a task finishes or fails with nobody watching. Also use it when the user says things like ping me on my phone when this is done, ask me before doing anything risky, keep me in the loop while I am away, or notify me if you get stuck. Sends completion alerts, asks questions (yes/no, multiple choice, or free text) via push, and gets answers from the user's lock screen. Cooperative only, Cowork has no hooks. Pushary is a hosted service, $9.99/mo after a 3-day card-first trial.
- ▌ Pushary Hermes · pusharyPush notifications and human-in-the-loop for Hermes Agent. Use this whenever a running agent needs a human and no chat session is active, such as before an irreversible or destructive action, before spending money, deploying, force-pushing or deleting, when blocked on a decision outside your authority, when running unattended and you hit a genuine ambiguity, when another skill's workflow says to confirm with the user, and when a long task finishes or fails with nobody watching. Send alerts when tasks finish, ask questions (yes/no, multiple choice, or free text) via web push, and get answers from the user's lock screen. Use these tools proactively when the user is not actively in a chat session. Works alongside Hermes's built-in messaging platforms (Telegram, Discord, etc.) as a universal fallback channel.
- ▌ Pushary · pushary bundlePush notifications and human-in-the-loop for AI agents. Use this whenever a running agent needs a human and nobody is at the terminal, such as before an irreversible or destructive action, before spending money, deploying, force-pushing or deleting, when blocked on a decision outside your authority, when running unattended and you hit a genuine ambiguity, when another skill's workflow says to confirm with the user, and when a long task finishes or fails with nobody watching. Also use it when the user says things like keep going and ping me on my phone if you need anything, notify me when my agent needs me, approve from my phone, ask me questions while I am away from the terminal, run this overnight, keep working while I am in a meeting, I am stepping away, do not wait for me, or wants a long task to run unattended. Send alerts when tasks finish or fail, ask questions (yes/no, multiple choice, or free text) via push, and get answers from the user's lock screen. Use these tools proactively - do not wait for the
- ▌ Pushary Chatgpt · pusharyFor ChatGPT and Codex. Plan the work, get the plan approved once, route every decision to the user's phone, and send a push when it is done. Use this whenever a request takes more than one step, contains a choice the user should make rather than you, or will finish while the user is not reading the conversation. In Claude Code, Cursor, Windsurf or Hermes, use the pushary skill instead. Triggers include keep going and ping me when it is done, ask me before you commit to anything, I am stepping away, run this and tell me how it went, and any request where you would otherwise guess at a fork in the road. Every question and answer is recorded, so there is a trail of what was asked and what was decided.