PostPeer Agent Skills Are Live

We added PostPeer Agent Skills.

If you use a coding agent that supports skills, you can now give it PostPeer workflows with one command:

npx skills add PostPeer-API/skills --all

That gives the agent a clean way to work with the PostPeer API. It can find your connected social accounts, create posts, schedule them, prepare media uploads, list queued posts, cancel scheduled posts, and pull analytics back into the conversation.

The point is simple: your agent should not need to hand-roll Twitter, LinkedIn, Instagram, TikTok, YouTube, Pinterest, Facebook, Threads, and Bluesky logic every time it wants to post something.

What are agent skills?

Agent skills are small instruction packs for coding agents.

Instead of explaining your API, endpoints, auth rules, payload shapes, and common workflows in every prompt, you install a skill once. The agent can then read the skill when the task calls for it and follow the right workflow.

For PostPeer, that means the agent learns how to:

• authenticate with your PostPeer access key
• list connected social accounts
• create and schedule posts
• upload media before publishing
• inspect, reschedule, or cancel scheduled posts
• fetch analytics for published posts

You still stay in control. The skill gives the agent the workflow; your access key and prompt decide what it can actually do.

How to use them

Install the skills repo in your agent environment:

npx skills add PostPeer-API/skills --all

Then add your PostPeer access key wherever your agent reads environment variables:

POSTPEER_ACCESS_KEY=your_access_key_here

After that, ask for a concrete outcome:

"Schedule a LinkedIn and X post for tomorrow morning announcing this release."

The agent should use the skill to find the right connected accounts, prepare the payload, and create the scheduled post through PostPeer.

What I would use it for

The safest pattern is still scheduling, not instant publishing.

Ask the agent to turn a changelog into a few posts, schedule them across X and LinkedIn, then leave them in the PostPeer dashboard for review. You can edit, cancel, or let them go live.

That small review step matters. Agents are useful, but they should not be firing off production posts with no human in the loop unless you really trust the workflow.

Skills or MCP?

Use Agent Skills when your coding agent works well with skill files and repeatable workflows.

Use PostPeer MCP when you want an MCP-compatible client, like Claude Desktop, Cursor, or another Streamable HTTP client, to call PostPeer tools directly.

Both paths use the same PostPeer API underneath. Skills are a nice fit for coding-agent environments. MCP is a nice fit for tool-calling clients.

Try it

Install the skills repo, add your PostPeer access key to your agent environment, and ask it to schedule a post:

"Schedule this for tomorrow at 9am on X and LinkedIn."

The agent can discover the connected accounts, create the scheduled post, and leave the queue where you can inspect it.

Docs and setup notes are on the Agent Skills docs. The broader agent setup lives at PostPeer for AI agents.