<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/ai-native-organisations-run-on-skills-how-to-structure-and-scale-them-imad-touil-quantumblack-t6vosql5m" -->

---
title: AI-Native Organisations Run on Skills: How to Structure...
description: A conference talk from a QuantumBlack distinguished engineer explains how organizations should structure and govern 'skills' — the reusable, portable units of...
canonical: https://daily.dev/posts/ai-native-organisations-run-on-skills-how-to-structure-and-scale-them-imad-touil-quantumblack-t6vosql5m
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: AI-Native Organisations Run on Skills: How to Structure and Scale Them — Imad Touil, QuantumBlack | daily.dev
og:description: A conference talk from a QuantumBlack distinguished engineer explains how organizations should structure and govern 'skills' — the reusable, portable units of...
og:url: https://daily.dev/posts/ai-native-organisations-run-on-skills-how-to-structure-and-scale-them-imad-touil-quantumblack-t6vosql5m
og:image: https://api.daily.dev/og/posts/t6vOSQL5m.png
og:image:alt: AI-Native Organisations Run on Skills: How to Structure and Scale Them — Imad Touil, QuantumBlack
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# AI-Native Organisations Run on Skills: How to Structure and Scale Them — Imad Touil, QuantumBlack

**[AI Engineer](https://daily.dev/sources/aidotengineer)** · 20 min read · 2 upvotes · 0 comments

## Summary

A conference talk from a QuantumBlack distinguished engineer explains how organizations should structure and govern 'skills' — the reusable, portable units of agent know-how that emerged from Anthropic's skills standard roughly eight months prior. The talk maps the broader agentic software stack (context managers, MCP servers, sub-agents, hooks, workflows) and argues skills are the critical missing structure that makes agent workflows deterministic. It covers design principles borrowed from microservices (reusable, modular, discoverable, portable, specialized, composable, consistent, cost-efficient), the risks of ungoverned skills (duplication, quality decay, security/prompt injection, permission gaps), and a proposed path to organizational adoption: individual creation, team sharing, then a centralized platform with catalog, versioning, dependencies, access control, and observability, all under governance from architects and leads. A simulation illustrates how governing skills reduces duplication and cost across teams. The talk closes by pointing to skills registries, evaluation methods, and 'auto-evolving' skills as near-term developments.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.youtube.com/watch?v=M05vON8i0aI>

## Questions this post answers

### What is the agentic skills standard and when did it emerge?

Anthropic published the first article introducing skills roughly eight months before this talk, and about two months later an open standard emerged that multiple agent harnesses began adopting, with widespread adoption across coding agents visible by around February of that year. Skills let agents pull reusable, structured knowledge during task execution rather than relying on ad hoc prompting.

_Engineers tracking the fast-moving agentic tooling landscape can follow standards shifts like this one on daily.dev._

### What design principles should AI agent skills follow to scale across a team?

Skills should be reusable, modular, discoverable, portable across different coding harnesses, specialized to a single task rather than monolithic, composable without duplication or conflicts, consistent and deterministic in behavior, and cost efficient through progressive disclosure that limits token usage by loading only the right skill at the right time.

_Teams designing shared agent workflows can compare governance approaches like this through daily.dev._

### What problems arise if an organization does not govern its AI agent skills?

Without governance, teams building on the same stack duplicate the same skills repeatedly, skill quality degrades over time without testing against the latest models, skills become undiscoverable without an ownership catalog, composability breaks down without domain-driven alignment, and security risks emerge since skills can contain scripts vulnerable to prompt injection or lack proper access control for sensitive business logic.

_Platform teams weighing skills governance strategies can track this evolving practice via daily.dev._

## Similar posts on daily.dev

- [AI skills start on laptops. Enterprises inherit the mess.](https://daily.dev/posts/ai-skills-start-on-laptops-enterprises-inherit-the-mess--zurft7blo) · The New Stack · 2 upvotes · 0 comments
- [Why Agent Skills Are the Next Evolution of Software Development](https://daily.dev/posts/why-agent-skills-are-the-next-evolution-of-software-development-xw4npduve) · DevOps.com · 0 upvotes · 0 comments
- [Building Agents with Skills: Equipping Agents for Specialized Work](https://daily.dev/posts/building-agents-with-skills-equipping-agents-for-specialized-work-lvpoiatwv) · Claude · 1 upvotes · 0 comments
- [Agent Skills](https://daily.dev/posts/agent-skills-oiotdzetc) · Hacker News · 0 upvotes · 0 comments

---

Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp), [#claude](https://daily.dev/tags/claude)

[View this post on daily.dev](https://daily.dev/posts/ai-native-organisations-run-on-skills-how-to-structure-and-scale-them-imad-touil-quantumblack-t6vosql5m)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"AI-Native Organisations Run on Skills: How to Structure and Scale Them — Imad Touil, QuantumBlack","url":"https://daily.dev/posts/ai-native-organisations-run-on-skills-how-to-structure-and-scale-them-imad-touil-quantumblack-t6vosql5m","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/ai-native-organisations-run-on-skills-how-to-structure-and-scale-them-imad-touil-quantumblack-t6vosql5m"},"datePublished":"2026-08-28T18:34:53.838Z","dateModified":"2026-09-14T06:20:30.284Z","description":"A conference talk from a QuantumBlack distinguished engineer explains how organizations should structure and govern 'skills' — the reusable, portable units of...","image":"https://i.ytimg.com/vi/M05vON8i0aI/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/M05vON8i0aI/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Engineer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AI Engineer","logo":"https://media.daily.dev/image/upload/s--u5PucxNT--/f_auto/v1724338940/logos/aidotengineer","url":"https://daily.dev/sources/aidotengineer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/ai-native-organisations-run-on-skills-how-to-structure-and-scale-them-imad-touil-quantumblack-t6vosql5m","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,mcp,claude","timeRequired":"PT20M","video":{"@type":"VideoObject","name":"AI-Native Organisations Run on Skills: How to Structure and Scale Them — Imad Touil, QuantumBlack","description":"A conference talk from a QuantumBlack distinguished engineer explains how organizations should structure and govern 'skills' — the reusable, portable units of...","thumbnailUrl":"https://i.ytimg.com/vi/M05vON8i0aI/sddefault.jpg","uploadDate":"2026-08-28T18:34:53.838Z","duration":"PT20M","url":"https://api.daily.dev/r/t6vOSQL5m","embedUrl":"https://www.youtube.com/embed/M05vON8i0aI"}}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Engineer","item":"https://daily.dev/sources/aidotengineer"},{"@type":"ListItem","position":3,"name":"AI-Native Organisations Run on Skills: How to Structure and Scale Them — Imad Touil, QuantumBlack"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/ai-native-organisations-run-on-skills-how-to-structure-and-scale-them-imad-touil-quantumblack-t6vosql5m#faq","mainEntity":[{"@type":"Question","name":"What is the agentic skills standard and when did it emerge?","acceptedAnswer":{"@type":"Answer","text":"Anthropic published the first article introducing skills roughly eight months before this talk, and about two months later an open standard emerged that multiple agent harnesses began adopting, with widespread adoption across coding agents visible by around February of that year. Skills let agents pull reusable, structured knowledge during task execution rather than relying on ad hoc prompting. Engineers tracking the fast-moving agentic tooling landscape can follow standards shifts like this one on daily.dev."}},{"@type":"Question","name":"What design principles should AI agent skills follow to scale across a team?","acceptedAnswer":{"@type":"Answer","text":"Skills should be reusable, modular, discoverable, portable across different coding harnesses, specialized to a single task rather than monolithic, composable without duplication or conflicts, consistent and deterministic in behavior, and cost efficient through progressive disclosure that limits token usage by loading only the right skill at the right time. Teams designing shared agent workflows can compare governance approaches like this through daily.dev."}},{"@type":"Question","name":"What problems arise if an organization does not govern its AI agent skills?","acceptedAnswer":{"@type":"Answer","text":"Without governance, teams building on the same stack duplicate the same skills repeatedly, skill quality degrades over time without testing against the latest models, skills become undiscoverable without an ownership catalog, composability breaks down without domain-driven alignment, and security risks emerge since skills can contain scripts vulnerable to prompt injection or lack proper access control for sensitive business logic. Platform teams weighing skills governance strategies can track this evolving practice via daily.dev."}}]}
```

