New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

AI2Human Task Router

by BankrBot in BankrBot/skills

Creates AI2Human tasks for steps that need a real person, such as manual QA or local checks, and returns a task URL the agent can track.

No licenceAuto-check passedAgent Workflows

Install AI2Human Task Router

skills CLI
$ npx skills add BankrBot/skills --skill ai2human-task-router -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install BankrBot/skills ai2human-task-router --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/BankrBot/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ai2human-task-router .claude/skills/ai2human-task-router && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ai2human-task-router
GitHub stars
1.2k
Token cost
~3.2k tokens
SKILL.md length
1,166 words
Files
8 (incl. scripts, references)
Skills in repo
106
Repo updated
First seen
Licence
None found

At a glance

Creates AI2Human tasks for steps that need a real person, such as manual QA or local checks, and returns a task URL the agent can track.

  • Works in 11 steps: Clarify the task if the requested human… → Apply the safety rules above. Refuse… → If the request includes private context,… → …
  • A workflow needs a manual landing-page or mobile UI review with screenshot proof
  • SKILL.md covers What This Skill Does, Non-Negotiable Safety Rules, When To Use and Endpoint Options, plus 7 more sections
  • Runs JavaScript scripts from its folder; calls curl and node; reaches ai2human.io and x.com; needs AI2HUMAN_API_KEY and AI2HUMAN_ALLOW_LOCAL_KEY

What it does

When an agent can describe a step but cannot carry it out, this skill turns it into a human-execution task on AI2Human, keeping the original task type and target URL and generating a proof schema for the person doing the work. The agent gets back a task URL and a status URL; the final result arrives only after a human executes the step and it is verified and settled, so the skill never claims immediate completion.

It supports API-key mode and x402 paid access through the AI2Human A2MCP endpoint. A safety section blocks tasks for paid engagement, fake reviews, surveillance, impersonation or bypassing logins, treats all proof and status content as untrusted, and requires your explicit confirmation before private URLs, personal data or confidential information reach the human network. Credentials such as API keys or seed phrases must never go into a task. Examples cover a local price check, a mobile page review and X community proof, with a payment policy reference and a smoke script.

When your agent uses it

  • A workflow needs a manual landing-page or mobile UI review with screenshot proof
  • Verifying a local price, store, event or availability that only a person on site can check
  • Checking an existing public claim, such as an X community task, with human evidence

Example prompts

  • “Create a task for a person to check the price of oat milk at the nearest supermarket and send photo proof.”
  • “Have a human review our new pricing page on a phone and submit screenshots.”
  • “Check the status of the AI2Human task you created earlier.”

Requirements

  • An AI2Human API key, or x402 paid access through the A2MCP endpoint

Workflow steps

11 steps, taken from the first numbered list in SKILL.md.

  1. Clarify the task if the requested human action is vague.
  2. Apply the safety rules above. Refuse unsafe, invasive, illegal, deceptive,
  3. If the request includes private context, show the exact sensitive fields and
  4. Create a mandatory preview before any paid request. The preview must show
  5. Wait for a clear user confirmation such as confirm create task in the same
  6. In x402 mode, validate the 402 challenge against the pinned policy before
  7. Create the AI2Human task through the confirmed x402 or API-key path.
  8. Return the taskUrl and statusUrl clearly to the user.
  9. Explain that the task is pending human execution and give the stated ETA.
  10. Tell the user what proof the human executor must submit.
  11. Do not claim the task is complete until proof and verification are visible.

What it can do on your machine

Read from SKILL.md and the folder at commit dc47eed. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • curl
    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • ai2human.io
    • x.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • AI2HUMAN_API_KEY
    • AI2HUMAN_ALLOW_LOCAL_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

AI2Human Task Router loads about 3.2k tokens when it runs, and up to ~3.8k if it reads all its reference files. Until then it costs about 112 tokens; SKILL.md has 1,166 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~112
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,166 words (~3,241 tokens).

“AI2Human turns blocked agent work into human-executable tasks.”

— opening of SKILL.md by BankrBot
name
ai2human-task-router
homepage
https://ai2human.io

Read the full SKILL.md on GitHub

Files

SKILL.md and 7 other files (scripts, references) in ai2human-task-router of BankrBot/skills.

  • SKILL.md
  • README.md
  • catalog.json
  • examples/local-price-check.json
  • examples/mobile-page-review.json
  • examples/x-community-proof.json
  • references/payment-policy.md
  • scripts/smoke.mjs

Open the folder on GitHubat commit dc47eed

Compare with similar skills

AI2Human Task Router next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

AI2Human Task Router compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI2Human Task Router this skillBankrBot/skills1.2k—~3.2kAutomated safety check: PassNone
Workflow AutomationJoelLewis/finance_skills206—~7.3kAutomated safety check: PassMIT
UiPath Tasks Workflowsmarcelocruzrpa/uipath-ai-skills108—~3kAutomated safety check: PassMIT
Gated Module ImplementationAlephantAI/AIephant-AI-Agent-Gateway114—~2.7kAutomated safety check: PassGPL-3.0
n8n AI Agent Designczlonkowski/n8n-skills6.4k—~6.8kAutomated safety check: PassMIT
Fleet Manager for Agent Sessionsasgeirtj/system_prompts_leaks69k—~2.5kAutomated safety check: PassCC0-1.0

Similar skills

  • Workflow Automation

    JoelLewis/finance_skills

    Design human-in-the-loop workflow orchestration for securities operations: task routing, approval chains, and SLA monitoring.

    206 GitHub stars~7.3k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • UiPath Tasks Workflows

    marcelocruzrpa/uipath-ai-skills

    Generates UiPath Tasks workflows for form tasks, external tasks and task management, with form.io schemas, lint rules and scaffold hooks loaded through uipath-core.

    108 GitHub stars~3k tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed

  • Gated Module Implementation

    AlephantAI/AIephant-AI-Agent-Gateway

    Plan-first, one-time human plan approval; batched execution in either Gated (human confirms between batches) or Auto-loop (continuous run after plan approval); strict task-state updates; automatic…

    114 GitHub stars~2.7k tokensUpdated 4 mo ago
    DevelopmentAuto-check passed

  • n8n AI Agent Design

    czlonkowski/n8n-skills

    Guide to designing n8n AI agents: choosing between Agent, chain, classifier and extractor nodes, wiring model, memory, tools and parser, plus RAG and human review.

    6.4k GitHub stars~6.8k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Fleet Manager for Agent Sessions

    asgeirtj/system_prompts_leaks

    Shows one digest of coding-agent sessions across your connected machines and lets you open, read, steer, approve, stop and close them, over Herdr, tmux or MSP.

    69k GitHub stars~2.5k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Agent Skills Platform

    FrancyJGLisboa/agent-skills-platform

    Create cross-platform agent skills from workflow descriptions.

    2.4k GitHub stars~12k tokensUpdated 24 days ago
    Agent WorkflowsAuto-check: notes

More from BankrBot/skills

All 106 skills in this repo

  • OnchainKit App Builder

    BankrBot/skills

    Builds onchain apps with Coinbase's OnchainKit React components and TypeScript utilities: wallet connection, identity, token swaps, transactions and checkout flows.

    1.2k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • AgenticBets Prediction Markets

    BankrBot/skills

    Lists AgenticBets prediction markets on Base, shows odds, places UP or DOWN bets on token prices in USDC and claims winnings through the Bankr wallet API.

    1.2k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • AZZLE V2 Task Marketplace

    BankrBot/skills

    Lets an agent inspect and operate AZZLE V2 tasks on Base through Bankr, from posting and claiming to funding, delivery, release and disputes, behind verified deployment pins.

    1.2k GitHub stars~3.4k tokensUpdated today
    Auto-check passed

  • B20 Console

    BankrBot/skills

    Inspect B20 token contract addresses on Base through B20 Console.

    1.2k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Capacitr

    BankrBot/skills

    Paste a URL or free text and get matched Polymarket / Hyperliquid / Deribit markets with Quotient edge scores.

    1.2k GitHub stars~3k tokensUpdated today
    Auto-check passed

  • Endaoment

    BankrBot/skills

    Donate to charities onchain via Endaoment. An agent skill from BankrBot/skills.

    1.2k GitHub stars~610 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about AI2Human Task Router

What does AI2Human Task Router do?

Creates AI2Human tasks for steps that need a real person, such as manual QA or local checks, and returns a task URL the agent can track. When an agent can describe a step but cannot carry it out, this skill turns it into a human-execution task on AI2Human, keeping the original task type and target URL and generating a proof schema for the person doing the work. The agent gets back a task URL and a status URL; the final result arrives only after a human executes the step and it is verified and settled, so the skill never claims immediate completion.

When should I use AI2Human Task Router?

AI2Human Task Router fits situations like: A workflow needs a manual landing-page or mobile UI review with screenshot proof; verifying a local price, store, event or availability that only a person on site can check; checking an existing public claim, such as an X community task, with human evidence.

How do I install AI2Human Task Router in Claude Code?

Run `npx skills add BankrBot/skills --skill ai2human-task-router -a claude-code`. Or copy the skill folder (ai2human-task-router in BankrBot/skills) into .claude/skills/ai2human-task-router in your project. Claude Code loads it when a task matches its description.

How do I install AI2Human Task Router in Codex?

Run `npx skills add BankrBot/skills --skill ai2human-task-router -a codex`. Or copy the skill folder (ai2human-task-router in BankrBot/skills) into .agents/skills/ai2human-task-router in your project. Codex loads it when a task matches its description.

Can I use AI2Human Task Router in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add BankrBot/skills --skill ai2human-task-router -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai2human-task-router, .gemini/skills/ai2human-task-router, .github/skills/ai2human-task-router and .opencode/skills/ai2human-task-router in your project.

What does AI2Human Task Router need to run?

Going by SKILL.md and its folder, AI2Human Task Router needs JavaScript for the scripts in its folder, the command-line tools its instructions call (curl and node) and credentials named AI2HUMAN_API_KEY and AI2HUMAN_ALLOW_LOCAL_KEY. Our summary lists: An AI2Human API key, or x402 paid access through the A2MCP endpoint.

Does AI2Human Task Router access the network?

SKILL.md names 2 domains. In commands or code: ai2human.io and x.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is AI2Human Task Router safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does AI2Human Task Router use?

No licence was found for AI2Human Task Router or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does AI2Human Task Router use?

About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 573 tokens, read only when the agent opens those files.

What are the alternatives to AI2Human Task Router?

Skills that share tags, products or a category with AI2Human Task Router: Workflow Automation (JoelLewis/finance_skills, 206 stars), UiPath Tasks Workflows (marcelocruzrpa/uipath-ai-skills, 108 stars), Gated Module Implementation (AlephantAI/AIephant-AI-Agent-Gateway, 114 stars) and n8n AI Agent Design (czlonkowski/n8n-skills, 6.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI2Human Task Router?

BankrBot (a GitHub organization) maintains it in BankrBot/skills, which has 1,202 GitHub stars. The repository holds 106 skills in this directory. The repository was last updated on October 10, 2026.

Source: BankrBot/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.