{
  "markdown": "# Agent Blueprint Skills\n\nOpen-source AI agent skills for enterprise deployment. Built for coding agents (Claude Code, Codex, Cursor, Copilot, Windsurf) using the [Agent Skills](https://agentskills.io) open standard.\n\n**7 skills. Zero vendor lock-in. Works with any coding agent.**\n\n### Skills\n\n| Skill | What it does |\n|-------|-------------|\n| [agent-fundamentals](plugins/agent-blueprint-skills/skills/agent-fundamentals/SKILL.md) | Agentic AI fundamentals: what agents are, when to use them vs. workflows, architecture patterns, decision frameworks, failure modes, worked examples |\n| [servicenow-ai-agents](plugins/agent-blueprint-skills/skills/servicenow-ai-agents/SKILL.md) | ServiceNow AI Agent Studio reference: data model, entity mapping, tool types, prompting patterns, browser navigation, MCP setup |\n| [agent-deployment](plugins/agent-blueprint-skills/skills/agent-deployment/SKILL.md) | Vendor-agnostic deployment methodology: phased rollout, pilot-first, test gates, access tier adaptation |\n| [research-agent](plugins/agent-blueprint-skills/skills/research-agent/SKILL.md) | Multi-tool research with automatic depth routing: free tools first, paid escalation, caching, structured output |\n\n### Blueprint Patterns\n\nPre-designed agent team architectures for common enterprise use cases. Each pattern describes the full agent team, roles, orchestration, and integration points. Use as a starting point, or generate a full customized blueprint via the [Agent Blueprint MCP server](https://github.com/agent-blueprint/mcp-server).\n\n| Pattern | What it does |\n|---------|-------------|\n| [it-service-desk-triage](plugins/agent-blueprint-skills/skills/it-service-desk-triage/SKILL.md) | 5-agent IT help desk: triage, classification, knowledge search, auto-resolution, escalation |\n| [procurement-rfx-processing](plugins/agent-blueprint-skills/skills/procurement-rfx-processing/SKILL.md) | 6-agent RFP/RFQ/RFI lifecycle: intake, requirements, vendor matching, compliance, evaluation, communication |\n| [customer-onboarding](plugins/agent-blueprint-skills/skills/customer-onboarding/SKILL.md) | 5-agent onboarding pipeline: intake, verification, provisioning, communication, handoff |\n\n## Install\n\n### Claude Code\n\nAdd the marketplace, then install the plugin:\n\n```\n/plugin marketplace add agent-blueprint/agent-blueprint-skills\n/plugin install agent-blueprint-skills@agent-blueprint\n```\n\nSkills appear in your session automatically. Claude loads them when your task matches the skill description.\n\n### OpenAI Codex CLI\n\nCopy skills into your project:\n\n```bash\ngit clone https://github.com/agent-blueprint/agent-blueprint-skills.git /tmp/ab-skills\ncp -r /tmp/ab-skills/plugins/agent-blueprint-skills/skills/* .agents/skills/\n```\n\n### Cursor / Copilot / Windsurf / Any Agent\n\nClone this repo and point your agent to the SKILL.md files:\n\n```bash\ngit clone https://github.com/agent-blueprint/agent-blueprint-skills.git .agent-skills\n```\n\nThe SKILL.md format is an open standard. Any agent that reads markdown can use these skills.\nSkills are in `plugins/agent-blueprint-skills/skills/`.\n\n### Manual (single skill)\n\nCopy just the skill you need:\n\n```bash\n# Agent Fundamentals\ncurl -o SKILL.md https://raw.githubusercontent.com/agent-blueprint/agent-blueprint-skills/main/plugins/agent-blueprint-skills/skills/agent-fundamentals/SKILL.md\n\n# ServiceNow AI Agents\ncurl -o SKILL.md https://raw.githubusercontent.com/agent-blueprint/agent-blueprint-skills/main/plugins/agent-blueprint-skills/skills/servicenow-ai-agents/SKILL.md\n\n# Deployment Methodology\ncurl -o SKILL.md https://raw.githubusercontent.com/agent-blueprint/agent-blueprint-skills/main/plugins/agent-blueprint-skills/skills/agent-deployment/SKILL.md\n\n# Research Agent\ncurl -o SKILL.md https://raw.githubusercontent.com/agent-blueprint/agent-blueprint-skills/main/plugins/agent-blueprint-skills/skills/research-agent/SKILL.md\n\n# IT Service Desk Triage pattern\ncurl -o SKILL.md https://raw.githubusercontent.com/agent-blueprint/agent-blueprint-skills/main/plugins/agent-blueprint-skills/skills/it-service-desk-triage/SKILL.md\n\n# Procurement RFx Processing pattern\ncurl -o SKILL.md https://raw.githubusercontent.com/agent-blueprint/agent-blueprint-skills/main/plugins/agent-blueprint-skills/skills/procurement-rfx-processing/SKILL.md\n\n# Customer Onboarding pattern\ncurl -o SKILL.md https://raw.githubusercontent.com/agent-blueprint/agent-blueprint-skills/main/plugins/agent-blueprint-skills/skills/customer-onboarding/SKILL.md\n```\n\n## What's in each skill\n\n### agent-fundamentals\n\nA practical guide for understanding AI agents in enterprise environments:\n\n- **Agent vs. workflow vs. chatbot**: When do you actually need an agent? Decision framework with clear criteria\n- **Anatomy of an agent**: Instructions, tools, memory, guardrails, orchestration\n- **Architecture patterns**: Single agent, orchestrator + workers, pipeline, human-in-the-loop — with selection criteria\n- **Common failure modes**: Over-agenting, tool sprawl, vague instructions, missing guardrails, skipping validation\n- **Use case evaluation framework**: 9-question walkthrough to determine if a process needs an agent\n- **Worked examples**: Three detailed walkthroughs (simple ticket triage, workflow-not-agent invoice processing, complex multi-agent procurement)\n\n### servicenow-ai-agents\n\nEverything a coding agent needs to deploy AI agents on ServiceNow's AI Agent Studio:\n\n- **Data model**: All `sn_aia_*` tables, fields, and relationships\n- **Entity mapping**: How blueprint roles (Manager, Worker) map to ServiceNow entities (Workflow, Agent)\n- **Tool types**: Record Operation, Script, Flow, Search Retrieval, MCP Tool, etc.\n- **Prompting patterns**: Markdown format, parameter naming, gate definitions\n- **Browser navigation**: Verified URL patterns and Playwright selectors for AI Agent Studio\n- **MCP setup**: servicenow-mcp-server and nowsdk-ext-mcp configuration\n\n### agent-deployment\n\nA structured methodology for deploying AI agents on any enterprise platform:\n\n- **Phased rollout**: Pilot first, validate, then expand\n- **Simulation-to-real progression**: Prove orchestration works, then connect real data\n- **Test gates**: Mandatory validation checkpoints before expanding scope\n- **Access tier adaptation**: Full access, read-only, or no-access workflows\n- **Research-backed**: Cites Microsoft, McKinsey, Forrester on why simulation-only pilots fail\n\n### research-agent\n\nA reusable research methodology that routes queries through the right tools:\n\n- **Depth routing**: WebSearch (free) to Brave to Perplexity to Gemini (expensive)\n- **Escalation rules**: Start cheap, escalate when results are thin\n- **Supplemental sources**: Financial filings, careers pages, reviews, competitive intel\n- **Caching**: Avoid redundant queries with freshness-aware cache\n- **Tool-agnostic**: Works with whatever MCP servers you have configured\n\n### Blueprint Patterns\n\n#### it-service-desk-triage\n\nA 5-agent architecture for automating IT service desk operations:\n\n- **Triage Agent**: Extracts structured data, sets priority, routes tickets\n- **Classification Agent**: Deep categorization, duplicate detection, assignment group recommendation\n- **Knowledge Search Agent**: Semantic search across knowledge base, relevance ranking\n- **Resolution Agent**: Auto-resolves known patterns (password resets, access requests, known errors)\n- **Escalation Agent**: Packages context for human analysts, monitors SLA compliance\n- **Orchestration**: Routing pattern with Knowledge Search as utility agent\n\n#### procurement-rfx-processing\n\nA 6-agent architecture for end-to-end RFx lifecycle automation:\n\n- **Intake Agent**: Extracts requirements from source documents, creates structured RFx record\n- **Requirements Agent**: Validates requirements, identifies gaps and conflicts, builds scoring rubric\n- **Vendor Matching Agent**: Identifies qualified vendors from database, past performance, compliance status\n- **Compliance Agent**: Validates regulatory and policy compliance at every stage\n- **Evaluation Agent**: Scores vendor responses, produces comparative analysis and award recommendation\n- **Communication Agent**: Manages all stakeholder and vendor communications\n- **Orchestration**: Orchestrator + Workers with parallel vendor matching and compliance\n\n#### customer-onboarding\n\nA 5-agent architecture for customer onboarding pipeline automation:\n\n- **Intake Agent**: Receives applications from any channel, validates completeness, sets risk tier\n- **Verification Agent**: Identity, compliance, KYC/AML, document validation\n- **Provisioning Agent**: Account creation, billing, access, integrations (parallel tasks)\n- **Communication Agent**: Status updates, document requests, activation packages\n- **Handoff Agent**: Transitions to ongoing service with structured CSM package\n- **Orchestration**: Pipeline with parallel branches, async waits for customer actions\n\n## Cross-platform compatibility\n\nThese skills follow the [Agent Skills](https://agentskills.io) open standard, supported by:\n\n| Platform | Skill location | How it works |\n|----------|---------------|-------------|\n| Claude Code | `.claude/skills/` or plugin | Loaded via plugin system or project skills |\n| OpenAI Codex | `.agents/skills/` | Same SKILL.md format, automatic discovery |\n| Cursor | Project context | Read SKILL.md as context |\n| GitHub Copilot | `.github/skills/` | Agent Skills standard |\n| Any agent | Direct file read | SKILL.md is just markdown |\n\n## Want more?\n\nThese community skills cover the fundamentals. [Agent Blueprint](https://agentblueprint.ai) provides:\n\n- **Full AI advisory pipeline**: Business profile analysis, AI readiness assessment, use case generation, agent blueprints, business cases, and implementation plans\n- **Expert-level deployment skills**: Battle-tested patterns, version-specific configuration, security hardening, and proprietary gotchas from real enterprise deployments\n- **Living blueprints**: Ongoing advisory with bidirectional state sync, performance monitoring, and strategic recommendations\n- **MCP server + CLI**: `agentblueprint` npm package for programmatic blueprint access\n\n## Contributing\n\nContributions welcome. Found a missing URL pattern, a better prompting technique, or a useful deployment tip? Open a PR.\n\nPlease keep contributions:\n- **Vendor-agnostic** in deployment and research skills\n- **Verified** against real instances (for ServiceNow patterns)\n- **Concise** -- these skills are loaded into LLM context windows, every token counts\n\n## License\n\nApache 2.0. See [LICENSE](LICENSE).\n\nBuilt by [Agent Blueprint](https://agentblueprint.ai) (NowGentic LLC).\n",
  "bytes": 10623,
  "sha": "0f129ef1894ee6f879cf0577fb6d2f5e4232f23c69d8c535f2b6cdfb39caf2ca",
  "repo_slug": "agent-blueprint/agent-blueprint-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_agent_blueprint_agent_blueprint_skills_a_00e59b3d/readme"
}