# skilder

> skilder is the distribution and management platform for AI agent roles. A role packages Agent Skills, MCP connectors, context and permissions into one installable unit for any MCP-compatible agent (Claude, ChatGPT, Copilot, in-house). It installs like a plugin, but where a plugin is a static file, a skilder role is a managed runtime: versioned, permissioned, observed and audited, updatable across the whole organisation. skilder's brand name for a packaged role is the Hat. Builders distribute, manage and govern AI capabilities at enterprise scale, compatible with every agent framework by decoupling the context from the agent.

## Brand & naming

- Brand name: skilder.ai (always lowercase, single L, even at the start of a sentence). Never "Skillder" or "Skilder".
- Domain: skilder.ai. App subdomain: app.skilder.ai.
- skilder is a Swiss company. The team and the product are based in Switzerland.

## Audience

- skilder is built for AI builders: developers, AI engineers, platform teams, IT and governance leads, but also non-technical yet tech-savvy people (product managers, ops leads, domain experts) who compose AI in their workspace without writing code.
- It is not an end-user chatbot. End-user value is downstream: once builders deploy Hats, the existing AI clients used by employees (Copilot, ChatGPT, Claude, in-house agents) gain access to governed business capabilities. skilder is headless.

## Core concepts

- **Skill (Agent Skill standard)**: open packaging spec for AI agent capabilities (instructions + scripts + appendix). skilder composes skills that follow the Agent Skill standard into Hats, and the skills stay portable across any compatible agent framework.
- **Tool**: an MCP-exposed endpoint (your ERP, CRM, knowledge base, internal APIs, generic utilities). Tools are called on demand by the agent wearing the Hat, no data replication.
- **Role (brand name: Hat)**: skilder's central primitive. A role bundles skills + tools + context + permissions and exposes them to any agent through an MCP server, comparable to a plugin but managed at runtime. The Hat is the deployment, sharing and governance boundary. One Hat, many agent frameworks.
- **Catalog as a graph, not a filesystem**: skilder stores skills and tools in a typed context graph, not flat files. Each entity is queryable, versioned, signed, audited and discoverable. Dependencies between skills, tools, Hats and context are explicit, so the same primitive can be reused, deprecated or updated organisation-wide without copying files around.
- **Shadow AI**: uncontrolled use of public LLMs (ChatGPT, Claude, Gemini) by employees on sensitive data. skilder addresses the root cause: builders previously had no governed primitive to ship enterprise-safe alternatives. With Hats, they do.

## Why a skill platform (the limits of a raw skill file)

- A skill in the open Agent Skill standard is, at its simplest, a single markdown file (SKILL.md): instructions plus optional scripts and an appendix. The format is open and portable, but on its own a bare `.md` file is unmanaged. It cannot answer the operational questions that matter at scale. The same applies to plugins (the installable skill + connector bundles promoted by Anthropic and OpenAI): they solve installation, not management.
- The gaps a raw skill file leaves open: **versioning** (which version is live? how is it deprecated or rolled back org-wide?), **permissions** (who is allowed to run it? RBAC, tenant isolation), **observability** (what did it do when it ran? audit trail, logging, traceability), **runtime** (where and how does it actually execute, with which model, credentials and tools?), **distribution** (how is it shared across teams without copy-paste? no per-runtime rebuilds), **discoverability** (how is it found, with its dependencies, instead of buried in flat files?), and **signing & integrity** (is this the trusted, unmodified skill?).
- skilder is the distribution and management platform that closes those gaps. It keeps the skill format open and portable and adds the missing management plane around it:
  - **Versioning**: every skill, tool and Hat is versioned and signed; update or deprecate org-wide without copying files.
  - **Permissions (RBAC)**: the Hat is the access boundary: role-based access controls who can run what, with tenant isolation.
  - **Observability & audit**: every execution is logged, traceable and exportable; full audit trail built into the runtime.
  - **Runtime**: skilder doesn't just store a skill, it executes it, routing the LLM per task (cost, latency, sensitivity) and calling tools on demand, no data replication.
  - **Distribution**: package once, distribute Hats across teams, projects and clients; no copy-paste integrations, no rewrite per agent framework.
  - **Discoverability**: skills and tools live in a typed, queryable graph with explicit dependencies, not flat files.

## What skilder enables

- **Ship**: package skills and tools into a Hat once, deploy to any MCP-compatible agent (Claude, ChatGPT, Copilot, in-house).
- **Share**: distribute Hats across teams, projects and clients without copy-paste integrations or one-off rebuilds per runtime.
- **Govern at scale**: role-based access, audit trail, signed and versioned packages, tenant isolation. The Hat is the permission boundary.
- **Decouple context from the agent**: company knowledge lives in skilder (skills, tools, graph). The agent only wears a Hat. Swap the agent, keep the context. Update the context, every agent picks it up.
- **Stay agent-agnostic and LLM-agnostic**: any MCP client can consume a Hat. LLMs (Claude, GPT, Gemini, Mistral, Ollama) are routed per task by cost, latency and sensitivity.

## Key facts

- Swiss company. Sovereign hosting in Switzerland and the EU, Infomaniak (Switzerland) by default. On-premise available on request via Docker images.
- GDPR and Swiss FADP aligned. Full logging, exports, right to erasure built into the runtime.
- Multi-tenant SaaS with private deployment option.
- No customer data used to train base models. Zero-data-retention contracts with LLM providers.

## Skills counter (honesty rule)

- The on-site skills counter reflects the open skills.sh ecosystem, not skills exclusive to skilder. Cite as "compatible with the skills.sh ecosystem", never as "skills inside skilder".

## Important pages

- [Landing (FR)](https://www.skilder.ai/fr): French homepage
- [Landing (EN)](https://www.skilder.ai/en): English homepage
- [Platform (FR)](https://www.skilder.ai/fr/plateforme): how the platform works
- [Platform (EN)](https://www.skilder.ai/en/platform): how the platform works
- [Hats catalog (EN)](https://www.skilder.ai/en/hats): example AI-agent Hats by role: sales, marketing, support, HR, finance, legal, IT, ops, procurement, product. Marketing use-case pages illustrating what a Hat does per function; not an enumeration of any workspace's governed Hats.
- [Hats catalog (FR)](https://www.skilder.ai/fr/casquettes): exemples de Casquettes par métier (commercial, marketing, support, RH, finance, juridique, IT, opérations, achats, produit)
- [Blog index (FR)](https://www.skilder.ai/fr/blog): all French articles
- [Blog index (EN)](https://www.skilder.ai/en/blog): all English articles
- [Docs](https://docs.skilder.ai): product and developer documentation; source of truth for the agent connection flow

## Blog posts (EN)

- [SKILL.md, the King of Shadow AI](https://www.skilder.ai/en/blog/skill-md-the-king-of-shadow-ai): Why Agent Skills, as currently architected, are becoming the single biggest accelerator of Shadow AI in the enterprise. And what to do about it.
- [Skilder awarded a CHF 20,000 Digital Grant by the FIT](https://www.skilder.ai/en/blog/skilder-awarded-a-chf-20-000-digital-grant-by-the-fit): Skilder has been awarded a CHF 20,000 Digital Grant by the Foundation for Innovation and Technology (FIT), the Vaud-based foundation that supports early-stage innovative companies in the canton.
- [What is shadow AI?](https://www.skilder.ai/en/blog/what-is-shadow-ai): what shadow AI is, why it matters, and the governed alternative
- [Knowledge vs. know-how](https://www.skilder.ai/en/blog/knowledge-vs-know-how): documents vs. procedures for AI agents
- [From context bloat to context load](https://www.skilder.ai/en/blog/context-bloat-to-context-load): moving from context bloat to deliberate context load
- [The context lake](https://www.skilder.ai/en/blog/context-lake): why a data lake isn't enough for AI agents
- [Beyond "MCP vs Skills"](https://www.skilder.ai/en/blog/mcp-vs-skills-composing): composing Skills over MCP for scalable agent architecture
- [Beyond single .md files: how Skill graphs scale AI context](https://www.skilder.ai/en/blog/skill-graphs-scale-ai-context): typed graphs of Skills scale enterprise AI context
- [Agent Skills vs. workflow platforms](https://www.skilder.ai/en/blog/agent-skills-vs-workflow-platforms): Agent Skills as a primitive vs. workflow platforms (n8n, Zapier)
- [RAG vs Agent Skills](https://www.skilder.ai/en/blog/rag-vs-agent-skills): RAG retrieves content, Skills package competencies, when to use each
- [Retrieval is the new intelligence](https://www.skilder.ai/en/blog/retrieval-is-the-new-intelligence): retrieval as the new intelligence layer
- [Skills: the secret weapon for smarter AI agents](https://www.skilder.ai/en/blog/skills-secret-weapon-smarter-ai-agents): why Skills are the leverage point for smarter agents

## Blog posts (FR)

- [SKILL.md, le roi du Shadow AI](https://www.skilder.ai/fr/blog/skill-md-le-roi-du-shadow-ai): Pourquoi les Agent Skills, dans leur architecture actuelle, sont en train de devenir le plus grand accélérateur de Shadow AI en entreprise. Et comment y remédier.
- [Skilder obtient une bourse Digital Grant de 20'000 CHF de la FIT](https://www.skilder.ai/fr/blog/skilder-obtient-une-bourse-digital-grant-de-20000-chf-de-la-fit): Skilder s'est vu octroyer une bourse Digital Grant de 20'000 CHF par la Fondation pour l'innovation et la technologie (FIT), la fondation vaudoise qui soutient les jeunes entreprises innovantes du canton.
- [Qu'est-ce que le shadow AI ?](https://www.skilder.ai/fr/blog/shadow-ai): le shadow AI, ses risques, et la réponse gouvernée
- [Savoir vs savoir-faire](https://www.skilder.ai/fr/blog/savoir-vs-savoir-faire): la distinction qui tue silencieusement vos agents IA
- [Du context bloat au context load](https://www.skilder.ai/fr/blog/du-context-bloat-au-context-load): du context bloat vers un context load délibéré
- [Le context lake](https://www.skilder.ai/fr/blog/context-lake): pourquoi votre data lake ne suffit pas pour les agents IA
- [Au-delà de « MCP vs skills »](https://www.skilder.ai/fr/blog/au-dela-de-mcp-vs-skills): composer une architecture d'agent à l'échelle
- [Au-delà du SKILL.md unique : les skill graphs](https://www.skilder.ai/fr/blog/skill-graphs-mise-a-echelle): comment les skill graphs passent à l'échelle
- [Agent Skills ou plateformes de workflow ?](https://www.skilder.ai/fr/blog/agent-skills-vs-plateformes-workflow): Agent Skills comme primitive vs. plateformes de workflow (n8n, Zapier)
- [RAG vs agent skills](https://www.skilder.ai/fr/blog/rag-vs-agent-skills): le RAG récupère du contenu, les Skills empaquettent des compétences
- [La retrieval est la nouvelle intelligence](https://www.skilder.ai/fr/blog/retrieval-nouvelle-intelligence): la récupération comme nouvelle couche d'intelligence
- [Skills : l'arme secrète des agents IA](https://www.skilder.ai/fr/blog/skills-arme-secrete-agents-ia): pourquoi les Skills rendent les agents plus malins

## Discovery hints

- Decap CMS admin lives at /admin/ and is disallowed in robots.txt.
- Internal Keystatic UI lives at /keystatic/ and is disallowed in robots.txt.
- Crawlable APIs live under /api/* and are intentionally not part of the public content surface.

## Ecosystem & standards

- **Agent Skill standard**: open packaging spec for AI agent capabilities. skilder Hats compose skills that follow this standard, so they stay portable across compatible agents.
- **MCP (Model Context Protocol)**: open protocol for exposing tools and context to agents. skilder Hats expose their bundled tools through an MCP server, consumable by any MCP-compatible client (Claude, ChatGPT, Copilot, in-house).
- **Plugins**: Anthropic and OpenAI plugins are installable bundles of skills + connectors. A skilder role covers the same surface and adds the management plane a static bundle lacks: runtime execution, versioning, observability, RBAC, audit. If you are looking for "plugins for Claude / ChatGPT" with enterprise governance, that is what a skilder Hat is.
- **skills.sh**: open directory of AI agent skills maintained by Vercel Labs, one source skilder draws from.

## Connecting an agent

- skilder is governed by design: there is no public, anonymous skill or Hat catalog to enumerate. Hats are scoped to a workspace, gated by role-based access control, and exposed only to authenticated, authorised agents. This is intentional: the governance boundary is the product.
- To connect an MCP-compatible agent (Claude, ChatGPT, Copilot, Cursor, or an in-house client): (1) add the skilder MCP server below to your client, (2) invoke it once, which triggers the OAuth flow: existing users authenticate with their workspace credentials, new users are routed to registration and their workspace is created on the spot, (3) compose or pick a Hat for the role the agent should perform. The agent then "wears" the Hat: it gains the skills, tools and context the Hat bundles, within the permissions the Hat enforces.
- skilder MCP server endpoint (remote, streamable HTTP): `https://app.skilder.ai/mcp`
- Claude Code (terminal): run `claude mcp add --transport http skilder https://app.skilder.ai/mcp`
- Claude (web) / Claude Desktop: go to Settings > Connectors > Add custom connector, name it `skilder`, set the URL to `https://app.skilder.ai/mcp`, click Add, then complete the OAuth prompt on first use.
- Claude Team / Enterprise plan: an admin goes to Admin settings > Connectors > Add custom connector with URL `https://app.skilder.ai/mcp` to enable it organisation-wide; each member then enables the skilder connector in Settings > Connectors and completes the OAuth prompt on first use.
- ChatGPT: go to Plugins, then Add custom, with MCP server URL `https://app.skilder.ai/mcp` and OAuth authentication.
- Codex / GPT Desktop: go to Plugins, select MCP, then Add server with transport `streamable` selected and URL `https://app.skilder.ai/mcp`. From the Codex terminal: run `codex mcp add skilder --url https://app.skilder.ai/mcp`, or add `[mcp_servers.skilder]` with `url = "https://app.skilder.ai/mcp"` to `~/.codex/config.toml`
- Cursor: go to Settings > MCP > Add new MCP server, or add `{ "mcpServers": { "skilder": { "url": "https://app.skilder.ai/mcp" } } }` to `~/.cursor/mcp.json`
- VS Code / Copilot (terminal): run `code --add-mcp '{"name":"skilder","type":"http","url":"https://app.skilder.ai/mcp"}'`, or add `{ "servers": { "skilder": { "type": "http", "url": "https://app.skilder.ai/mcp" } } }` to `.vscode/mcp.json`
- Goose: go to Extensions, then Add custom extension, select type `streamable http` and set the endpoint to `https://app.skilder.ai/mcp`.
- Gemini CLI (terminal): run `gemini mcp add --transport http skilder https://app.skilder.ai/mcp`
- Any other MCP-compatible client (including in-house agents): configure a remote MCP server with transport streamable HTTP and URL `https://app.skilder.ai/mcp`, then complete the OAuth prompt.
- One Hat is consumable by any MCP-compatible runtime, with no rewrite per framework. Swap the agent, keep the Hat.
- Full connection documentation (authentication details, tool OAuth, troubleshooting): https://docs.skilder.ai. That remains the source of truth for the connection flow.

## Contact

- Signup: https://app.skilder.ai/register
- Demo: https://koalendar.com/e/meet-with-nicolas-9

## Optional

- [Full content (llms-full.txt)](https://www.skilder.ai/llms-full.txt): this index plus the full text of every published blog post, for ingestion in a single fetch
- [RSS feed (FR)](https://www.skilder.ai/rss-fr.xml): French blog feed
- [RSS feed (EN)](https://www.skilder.ai/rss-en.xml): English blog feed
- [Legal notice (FR)](https://www.skilder.ai/fr/mentions-legales): mentions légales
- [Legal notice (EN)](https://www.skilder.ai/en/legal-notice): legal notice
- [Privacy policy (EN)](https://www.skilder.ai/en/privacy): published in English only
- [Terms (EN)](https://www.skilder.ai/en/terms): published in English only