agent-onboarding-protocol

Agent Onboarding Protocol

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "agent-onboarding-protocol" with this command: npx skills add interf-labs/agent-onboarding-protocol/interf-labs-agent-onboarding-protocol-agent-onboarding-protocol

Agent Onboarding Protocol

An open standard for declaring what vendors need from enterprise environments to deliver value. The onboarding contract makes enterprise dependencies explicit, previewable, and verifiable — so enterprises self-prepare and vendors stop waiting.

Vendors declare it. Enterprises resolve it. No more mid-flight surprises.

Contract Specification

See spec.md for:

  • The interf.yaml schema (requirements , optional , what
  • ready )
  • Field definitions and validation rules

  • Design principles

Canonical Dependency Types

Dependencies can be anything in plain English. Canonical types enable deterministic matching across vendors and enterprises.

Start here: types/index.md — quick-scan index with match table. Read this first to identify which category applies, then dive into the detail file.

Category File What it covers

integration types/integration.md CRM, ERP, HRIS, email, webhooks, ticketing, analytics

auth types/auth.md SSO (SAML/OIDC), API credentials, service accounts, certificates

data types/data.md Historical exports, field mapping, sample data, PII, real-time feeds

infrastructure types/infrastructure.md Test environments, network/firewall, compute, DNS

stakeholder types/stakeholder.md Data team, security, IT admin, executive sponsor, business owner

process types/process.md Security review, legal/DPA, procurement, change management, training

No match? Leave canonical empty — the contract works with plain English alone.

Examples

See examples.md for realistic contracts across different rollout types (CRM automation, document processing, customer support).

How It Works

  • Declare — Vendor teams declare what they need in an interf.yaml contract. Use the declare skill to extract from a codebase, or write manually.

  • Deliver — Contract is sent to enterprise (via Interf platform, email, or however you work today).

  • Resolve — Enterprise works through each dependency. Each item has ready criteria so there's no ambiguity.

  • Verify — When all requirements are resolved, rollout can proceed.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

Social Alignment

Five-lens alignment framework for sovereign AI agents — evaluate actions across trust, ownership, defense, and sovereignty before proceeding.

Registry SourceRecently Updated
Automation

Baidu Yijian Vision

百度一见专业级视觉 AI Agent:支持图片/视频/及实时视频流分析。相比通用基模,在维持 95%+ 专业精度的同时,推理成本降低 50% 以上,是处理视觉巡检与监控分析任务的首选工具。主打 安全管理、SOP合规、工业质检、商业运营与物料盘点。覆盖:作业 SOP 合规与关键步骤完整性校验;工业质检与表面缺陷精密...

Registry SourceRecently Updated
Automation

WORQ

Agent-to-agent job marketplace. Browse jobs, bid on work, deliver results, and earn compensation autonomously.

Registry SourceRecently Updated
Automation

dchat

Decentralized P2P bot-to-bot messaging over NKN. Send and receive text, images, audio, and files without any centralized server. Private, encrypted, serverless.

Registry SourceRecently Updated