Human Auth Delegation

Organization

pockebot

human-auth-delegation

Overview of how Human Phone authorization and delegation artifacts work. For specific capability handling, see the individual human-auth-* skills.

Overview

Publisher	pockebot
Repository	`openpocket`
Skill name	`human-auth-delegation`
Stars	848
Forks	6
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

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 pockebot on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/pockebot/openpocket/tree/main/skills/human-auth-delegation
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.

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/pockebot/openpocket.git /tmp/openpocket
mkdir -p .claude/skills
cp -r /tmp/openpocket/skills/human-auth-delegation .claude/skills/human-auth-delegation

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Human Auth Delegation 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 Human Auth Delegation 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 Human Auth Delegation 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.

Human Auth Delegation Overview

When a task requires real-world data or sensitive authorization, you call request_human_auth. The human on their phone approves and may return a delegation artifact — a file containing the data you need.

How It Works

You call request_human_auth(capability, instruction, ...).
The human sees an authorization page on their phone.
They approve/reject and optionally attach data (photo, audio, coordinates, code, credentials, etc.).
You receive a result with artifact_path and artifact_summary.
You decide what to do next based on the artifact and current screen state.

Artifact Result Format

After request_human_auth returns, the tool result contains:

status: approved / rejected / timeout
artifact_path: local file path to the saved artifact
artifact_summary: structured key-value description (kind, size, fields, etc.)

What to Do With the Artifact

Each capability has its own skill with detailed handling instructions:

Capability	Skill	Typical Artifact
camera	human-auth-camera	Photo file (JPEG/PNG)
photos	human-auth-photos	Photo file(s)
microphone	human-auth-microphone	Audio file (WebM/OGG)
location	human-auth-location	JSON with lat/lon
oauth	human-auth-oauth	JSON with credentials
payment	human-auth-payment	JSON with card fields
sms, 2fa	human-auth-sms-2fa	JSON with code text
qr	human-auth-qr	JSON with scanned text
nfc	human-auth-nfc	JSON/binary NFC data
biometric	human-auth-biometric	Approval signal
contacts, calendar, files	human-auth-contacts-data	JSON/file data

Use read(<skill_location>) to load the relevant skill for detailed instructions.

Key Principles

You decide. The runtime only saves the artifact. You choose how to apply it.
Redo the flow. The app's UI may have changed while waiting for human auth. After receiving the artifact, you typically need to:
- Press Back (keyevent KEYCODE_BACK) to exit the current screen (camera preview, file picker, etc.)
- Push/prepare the data (adb push, type_text, geo fix, etc.)
- Re-navigate to the point where the data is needed (re-open picker, re-focus input field)
- Complete the action (select file, tap submit, etc.)
Read the artifact first. For JSON artifacts (credentials, codes, coordinates), call read(<artifact_path>) to get the actual values. OTP values are not in the session log.
Clean up sensitive data. Delete credential/payment artifacts after use: exec("rm <path>").
File artifacts are auto-pushed. When you receive a file artifact (image, audio, etc.), the runtime automatically pushes it to /sdcard/Download/ on Agent Phone and runs media scan. The result includes device_path=/sdcard/Download/openpocket-human-auth-<ts>.<ext> — this is the path you use in file pickers. You do NOT need to manually adb push.

Frequently asked questions

What does the Human Auth Delegation AI skill do?

Overview of how Human Phone authorization and delegation artifacts work. For specific capability handling, see the individual human-auth-* skills.

Why use Human Auth Delegation on TypingMind?

Because you install it once and use it with any model. Human Auth Delegation 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 Human Auth Delegation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pockebot/openpocket/tree/main/skills/human-auth-delegation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Human Auth Delegation?

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 Human Auth Delegation?

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

Is the Human Auth Delegation AI skill free?

Yes. It is published on GitHub by pockebot 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

Weights And Biases

NousResearch

OrganizationPopular

W&B: log ML experiments, sweeps, model registry, dashboards.

Nemo Curator

Curate LLM training data: dedupe, filter, PII redaction.

Obliteratus

OBLITERATUS: abliterate LLM refusals (diff-in-means).

Prompt Lookup

Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Human Auth Delegation Overview

How It Works

Artifact Result Format

What to Do With the Artifact

Key Principles

Frequently asked questions

Related AI Skills

Set up your own AI workspace now