Import the Agent Skills already present on this machine or in this repo into a Skilder workspace, so the whole team's agents can discover and run them from one governed endpoint. Trigger on requests like "import my skills to Skilder", "publish these skills to my team", "get my local skills into Skilder", "centralize our agent skills".
Integrations
connect-to-skilder
Try itOne-shot instruction to connect this AI agent to Skilder over MCP using the official remote endpoint and OAuth. Paste this whole skill into an agent's chat once. It should act on it immediately, without asking the user anything first.
What it does
One-shot instruction to connect this AI agent to Skilder over MCP using the official remote endpoint and OAuth. Paste this whole skill into an agent's chat once. It should act on it immediately, without asking the user anything first.
The skill document
You've just been handed this as a one-time instruction. Proceed automatically. Don't ask the user any clarifying questions first. The endpoint is fixed and already known:
https://app.skilder.ai/mcp
You don't need a workspace name, a link, or a key to get started.
Do this now
-
Register the server. Add
https://app.skilder.ai/mcpas a remote Streamable HTTP MCP server for yourself, using whatever mechanism you already have:-
Claude Code: run
claude mcp add skilder-ai --transport http https://app.skilder.ai/mcp -
Codex: run
codex mcp add skilder-ai --url https://app.skilder.ai/mcp -
Any host where you can edit your own MCP config (
.mcp.json, Cursor's~/.cursor/mcp.json, VS Code's.vscode/mcp.json,claude_desktop_config.json, etc.): add this entry, keeping the host's own top-level key (mcpServerson most hosts,serverson VS Code):"skilder-ai": { "type": "http", "url": "https://app.skilder.ai/mcp" } -
If you have no way at all to configure your own MCP servers, say so as a single fact and stop there. Don't turn it into a question back to the user.
-
-
Trigger the connection. Call the server right away (e.g.
tools/list). This is expected to redirect through a one-time browser sign-in to Skilder. That's the OAuth handshake, and approving it is the only step a human touches. Don't ask permission to attempt this; just do it and report what happens. -
Confirm and report. Once connected, list what the server now exposes, and tell the user which Roles and Skills are available. Don't wait to be asked.
-
Only if OAuth genuinely isn't possible in your environment (no browser redirect support at all): say so, then fall back to the key-based config from Skilder's Connect page → Advanced. That does require a key from the user, the one unavoidable exception to "don't ask."
That's it: one endpoint, no setup questions, act now.
Related skills
Suggest reusable skills from recurring patterns in local memory files. Human review gate, drafts only to skills/_pending/, local-first runner with optional external fallback. Triggers on "skill forge", "propose a skill", "what skills should I have", "skill candidates", "what patterns have I been doing", "forge me a skill", "forge show", "forge accept", "forge reject", "forge promote".
Curated catalog of quality AI agent skills. Find the right tool for every task — verified recommendations for memory, productivity, security, and automation....
Convert a book, paper, document, documentation site, or code repository into a structured, on-demand agent skill. Use when the user wants to turn a PDF, EPUB, DOCX, a URL, a docs site, or a GitHub repo into a skill they can load later — "make a skill from this book", "turn this paper into a skill", "turn these docs into a skill", "I want an agent that knows this library".
Use when the user wants to turn a script, repeated workflow, runbook, or hard-won procedure into a reusable agent skill, or asks "make this a skill", "extrac...
Use when you need to compile any prompt OR multi-source content (PDF/video/URL/image/doc) into a production-grade, reusable AI Skill. Triggers on: 'prompt to...