{"slug": "aws-quick-skills-and-agents-build-publish-and-share-team-workflows", "title": "AWS Quick Skills and Agents: Build, Publish and Share Team Workflows", "summary": "AWS published a November 9 Machine Learning blog post detailing how agents, skills and connected data work in AWS Quick, the agentic workspace rebranded from Amazon Quick, including how teams build, publish and share skills and custom agents. Skills use the Agent Skills SKILL.md folder format with YAML name and description fields and rely on progressive disclosure, in which the model sees only the name and description until a task matches; AWS Quick ships system skills for Office documents, research, flows and coding handoff to Kiro, and grounds agents in spaces, knowledge bases, Quick Sight datasets and dashboards, and connectors including Outlook, Slack, Jira, Asana, Salesforce and remote and local MCP servers. AWS warns that sharing an agent without sharing its data sources produces incomplete answers.", "body_md": "**AWS Quick** — the agentic workspace AWS [rebranded from Amazon Quick on November 9](https://explainx.ai/blog/amazon-quick-agentic-primitives-taxonomy-triggers-agents-capabilities-learned-context-2026) — now has a companion post that goes deeper on **skills and agents** than the earlier **taxonomy of primitives**. The [November 9 Machine Learning blog article](https://aws.amazon.com/blogs/machine-learning/how-skills-and-agents-work-in-aws-quick/?ref=explainx) explains how **agents**, **skills**, and **connected data** fit together, how to **build and publish** skills, and how the **official catalog** and **custom agents** let teams operationalize repeatable work.\n\nIf you already think in **triggers, capabilities, and learned context**, this post is the **how-to layer**. If you build agents elsewhere, it is still worth reading because AWS anchored Quick on the same **Agent Skills `SKILL.md` format** Cursor and Claude Code popularized — see our [agent skills guide](https://explainx.ai/blog/what-are-agent-skills-complete-guide) for the cross-vendor picture.\n\n## TL;DR\n\n| Question | AWS Quick answer (Nov 9 post) | \n|---|---|\n| Skill format? | Folder with **SKILL.md** plus optional scripts; YAML**name** and**description** | \n| Triggering? | **Progressive disclosure** — model sees name and description until task matches | \n| Default agent? | **Quick** — no fixed scope; uses your spaces, dashboards, connectors | \n| Custom agent? | Fixed instructions plus scoped spaces, connectors, skills | \n| Share workflow? | **Publish** , then**Share** ; recipients add via**Shared with me** | \n| System skills? | Built-ins for Office docs, research, flows, coding handoff to **Kiro** | \n\n## Agents at the center\n\nAWS Quick agent hub diagram showing skills connectors and data sources for agent skills\n\n*Image: [Amazon Web Services](https://aws.amazon.com/blogs/machine-learning/how-skills-and-agents-work-in-aws-quick/?ref=explainx)*\n\nAWS diagrams Quick as a **hub-and-spoke** system: the **agent** follows its instructions, **loads skills** a task needs, acts through **connectors**, and grounds answers in **spaces**, **knowledge bases**, **datasets**, and **dashboards**.\n\n**Quick** is the default agent every user gets. It has **no fixed scope** — each conversation can draw on whatever the user can access: spaces, Quick Sight assets, connectors, and skills. AWS positions that as the **low-friction starting point** for one-off questions.\n\nA **custom agent** is scoped to a job — AWS gives **HR onboarding** as the example — with its own instructions and explicit limits on spaces, connectors, and skills. After testing, owners **publish** and **share** it inside the AWS Quick account.\n\nThat split mirrors the taxonomy post's **Who** primitive: sometimes you add a **trigger** to an existing agent; sometimes you need a **new agent** with a narrower world. Read the [primitives explainer](https://explainx.ai/blog/amazon-quick-agentic-primitives-taxonomy-triggers-agents-capabilities-learned-context-2026) for the vocabulary map.\n\n## Data sources Quick agents can use\n\nAWS groups grounding assets into:\n\n- **Spaces** — curated document and resource collections you attach to an agent or conversation.\n- **Knowledge bases** — indexed corpora synced from Drive, OneDrive, Confluence, SharePoint, S3, crawlers, or**Bedrock Managed Knowledge Bases** .\n- **Datasets and dashboards** — Quick Sight semantic layers for natural-language analytics.\n- **Connectors** — cloud integrations such as Outlook, Slack, Jira, Asana, and Salesforce, plus**remote MCP servers** , and**local MCP** hosts on the user's machine.\n\nThe connector list matters for **skills authors**: instructions often assume a **Jira query** or **Slack post** step. AWS warns that sharing an agent without sharing its data sources yields **incomplete answers** — the **\"works on my machine\"** problem translated to agent permissions.\n\nFor MCP-heavy stacks, compare with [Home Assistant's MCP server patterns](https://explainx.ai/blog/homeassistant-ha-mcp-claude-chatgpt-mcp-server-2026) and AWS's own [Bedrock AgentCore layering](https://explainx.ai/blog/aws-pluggable-agentic-ai-framework-bedrock-agentcore-seven-layers-2026).\n\n## Skills: Agent Skills spec inside a ReAct loop\n\nAWS says Quick agents run in a **managed ReAct loop**, aligning with frameworks such as the **Strands Agents SDK**. **System skills** supply default behaviors: generate Office files, browse the web, run code, deep research, transcribe media, build **Quick Flows**, schedule routines, delegate to **Kiro**, or manage memories.\n\n**Custom skills** are where teams encode recurring procedures — weekly status updates, release notes, cross-app workflows. AWS states they follow the **Agent Skills specification** Anthropic open-sourced. Quick desktop entered **preview in April 2026** and **GA in September 2026** with that format.\n\n### What goes in SKILL.md\n\nAWS Quick SKILL.md folder layout for release-notes-generator agent skill\n\n*Image: [Amazon Web Services](https://aws.amazon.com/blogs/machine-learning/how-skills-and-agents-work-in-aws-quick/?ref=explainx)*\n\nAWS shows a **release-notes-generator** example:\n\n```\n---\nname: release-notes-generator\ndescription: \"Generates human-readable release notes from merged pull requests, commits, or changelogs ... Use when asked to 'generate release notes', 'write changelog', ...\"\n---\n```\n\nThe post stresses **name** and **description** as the **trigger surface**. Quick loads only those fields until a user request matches; then it pulls the full instructions — **progressive disclosure** identical to how [Claude Code skills](https://explainx.ai/blog/claude-code-commands-complete-reference-guide-2026) describe catalog loading.\n\nLimits cited: **64 characters** for `name`, **1,024** for `description`, and guidance to keep body instructions under **5,000 tokens**.\n\n### Building from chat\n\nAWS suggests starting from a template that names **cadence**, **data sources**, **transformation steps**, **report format**, **stakeholders**, and **connectors**, then asking Quick to **create a skill** and propose **test scenarios**. Alternatively, promote a **multi-turn chat** that already accomplished the task.\n\nCreation paths include **chat**, uploading **.md or .zip**, or importing a folder that already contains **SKILL.md**.\n\n## Publish, share, and version drift\n\nAWS is explicit that **publishing and sharing are separate**:\n\n1. Open **Customize → Skills** , select the draft, open the detail panel.\n2. **Publish** .\n3. **Share** with users or groups.\n4. Recipients add the skill via **Add to Quick → Shared with me** .\n\nRepublishing updates downstream copies — important for **change control** when a skill wraps a regulated workflow.\n\nProduction guidance reads like **software engineering**:\n\n- Document **prerequisites** in a README when sharing skills alone.\n- Plan **failure branches** (\"if email send fails, stop and notify user\").\n- **Test** in the same environment recipients use; add regression prompts when editing skills.\n- Avoid hardcoded personal paths; use declared inputs.\n- Track **release notes** ,**checksums** , and**lint-like structure checks** .\n\nAWS points to the catalog's **Skill Architect** skill — install from **Official** browse — as a guided way to apply those practices. That is Quick's answer to **platform governance**, not a substitute for your own CI on skill folders in git.\n\n## Catalog versus custom agents\n\nAWS Quick team skills sharing visualized as collaboration puzzle around a central agent workspace\n\nThe **official catalog** lists tested skills for sales, marketing, HR, legal, engineering, and verticals such as healthcare and energy. AWS claims each resource is **scanned for quality and security** before publication.\n\n**Custom agents** should bind **one use case** to a bounded set of spaces, skills, and connectors. AWS warns that giving an agent **all** skills while sharing it widely creates **nondeterministic behavior**: two users with different entitlements get different effective tools.\n\nThe post links a workshop module, **personal agent architect**, for tying agents, skills, and spaces together — useful if you are designing **role-based agent templates** similar to [Tencent's git-based team skills CLI](https://explainx.ai/blog/tencent-teamai-cli-git-based-team-skills-2026).\n\n## Overlap with Claude Fable 5.2 on AWS\n\nThe same week, AWS published [Introducing Claude Fable 5.2 on AWS](https://aws.amazon.com/blogs/machine-learning/introducing-claude-fable-5-2-on-aws/?ref=explainx) for Bedrock. Quick skills orchestrate **business workflows**; Fable on Bedrock powers **model inference** underneath other products.\n\nIf you are standardizing on **skills folders** for both Quick and Claude Code, keep **one git repo per skill**, pin versions in agent configs, and mirror AWS's **publish/share** discipline with **PR reviews** — the Skill Architect checklist is a reasonable template for your internal linter.\n\nSee [Fable 5.2 pricing and migration](https://explainx.ai/blog/claude-fable-5-2-mythos-5-2-launch-pricing-api-2026) for token economics when skills call frontier models frequently.\n\n## What people are asking\n\n**Do I need IT to ship a skill?** AWS markets Quick as **natural-language authoring** without a ticket, but enterprise governance hooks — **Purview**, **IAM**, **Active Directory**, sensitivity labels — sit in the November 9 rebrand post. Expect **admin approval** for shared agents in large tenants.\n\n**Is this only desktop?** The skills post references **Quick on desktop** history; connectors split **cloud** versus **local MCP**. Mobile-only users may lack local tool paths.\n\n**How does this differ from Lambda or Step Functions?** Skills steer a **model-driven loop** with judgment; AWS's taxonomy post positions **workflows** as **deterministic code paths**. Crystallization between skill and workflow still lives in the promised **continuous learning** follow-up AWS teased in the primitives article.\n\n**Can I export skills to other hosts?** Because the format is the **Agent Skills spec**, folders you build in Quick should be portable to other spec-compliant agents, subject to connector differences.\n\n## Try it: checklist for one skill\n\n1. Pick a **weekly chore** with clear inputs and outputs — status email, release notes, ticket digest.\n2. Draft **name** and**description** with phrases users already say aloud.\n3. Wire **connectors** in a test space with**least privilege** .\n4. Add **failure handling** sentences AWS exemplifies for email steps.\n5. Run **three test prompts** including an edge case (empty Jira week, missing folder).\n6. **Publish** , share with one colleague, confirm their**Shared with me** sync after you edit.\n\nOptional: embed AWS's recorded session **Encode Your Enterprise with Agents and Skills on AWS Quick** (YouTube id **m9gN2GapOps** on the blog page) for a walkthrough of catalog demo flow.\n\nIf your organization already version-controls prompts in git, treat each published Quick skill as a **release artifact**: tag the commit, note connector dependencies in the README AWS recommends, and re-run the three regression prompts after every publish so teammates who synced from **Shared with me** do not inherit a broken skill silently.\n\n## Related reading\n\n*Product names, connector lists, and certification claims come from AWS's November 9, 2026 post and the November 9 rebrand article cited in our taxonomy coverage.*", "url": "https://wpnews.pro/news/aws-quick-skills-and-agents-build-publish-and-share-team-workflows", "canonical_source": "https://explainx.ai/blog/aws-quick-skills-agents-catalog-build-guide-2026?utm_source=rss&utm_medium=feed&utm_campaign=blog", "published_at": "2026-11-10 00:00:00+00:00", "updated_at": "2026-11-10 01:51:14.256471+00:00", "lang": "en", "topics": ["ai-agents", "agent-protocols", "ai-products", "ai-tools", "artificial-intelligence"], "entities": ["AWS", "AWS Quick", "Amazon Quick", "Kiro", "Slack", "Jira", "Salesforce", "Bedrock Managed Knowledge Bases"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/aws-quick-skills-and-agents-build-publish-and-share-team-workflows", "markdown": "https://wpnews.pro/news/aws-quick-skills-and-agents-build-publish-and-share-team-workflows.md", "text": "https://wpnews.pro/news/aws-quick-skills-and-agents-build-publish-and-share-team-workflows.txt", "jsonld": "https://wpnews.pro/news/aws-quick-skills-and-agents-build-publish-and-share-team-workflows.jsonld"}}