# Skills: Keep the Agent Prompt Small, Load the Playbook When Needed

**URL:** <https://community.solace.com/t/skills-keep-the-agent-prompt-small-load-the-playbook-when-needed/4958>\
**Category:** Solace Agent Mesh\
**Created:** [November 17, 2026, 2:11pm UTC](https://community.solace.com/t/skills-keep-the-agent-prompt-small-load-the-playbook-when-needed/4958 "2026-11-17T14:11:28Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Tamimi](https://yyz1.discourse-cdn.com/solace/user_avatar/community.solace.com/tamimi/32/2190_2.png) [@Tamimi](https://community.solace.com/u/Tamimi)\
**Post date:** [November 17, 2026, 2:11pm UTC](https://community.solace.com/t/skills-keep-the-agent-prompt-small-load-the-playbook-when-needed/4958/1 "2026-11-17T14:11:28Z")

</div>

Let’s say you have an invoice reconciliation agent whose system prompt kept growing: tolerances, accessorial rules, duplicate detection, dispositions. Most chats never needed half of it. Skills in Solace Agent Mesh fixed that. A skill is a named bundle of instructions (plus optional references, assets and tools) that the agent loads on demand.

**The skill itself is a folder with a `SKILL.md`**

Mine has no tools, just instructions. The frontmatter is what the model sees when deciding whether to load it:

```markdown
---
name: freight-audit-playbook
description: Freight invoice audit rules for Northwind Freight. Contracted-rate
  matching, accessorial validation, duplicate detection, and variance tolerances.
  Load before reconciling or approving any carrier invoice.
---

# Freight Audit Playbook

1. Linehaul: invoice linehaul must equal the contracted lane rate for the ship
   date. Tolerance is 0.5% or USD 25, whichever is lower.
...

```

Tip: write the `description` around the problem the user has, not the skill’s name. That one sentence is the trigger.

Scaffolding, checking and packaging are three commands:

```bash
sam skill init freight-audit-playbook # add --with-tool --lang python for a bundled tool
sam skill validate freight-audit-playbook
sam skill package freight-audit-playbook

```

Then **Builder** \> **Skills** \> **Create Skill** and upload the zip. The list shows custom and built-in skills side by side, with tool, reference and asset counts and how many agents use each.

 ![The Skills page with custom and built-in skills](https://canada1.discourse-cdn.com/solace/original/2X/3/3080bf93f7105f93d1af213a41327ebbd862d152.jpeg)

**Attach it to an agent**

In the agent editor, the **Skills** section opens a selector with **Built-in Skills** (Word Documents, Excel Workbooks, Task Scheduling, Reusable Report Templates and more) and **Custom Skills**. Tick the box, **Apply** , save and deploy.

 ![Attaching a custom skill in the agent editor](https://canada1.discourse-cdn.com/solace/original/2X/a/afdc84dd6159927dfd2bbacbbfd945ab733871af.jpeg)

**Watching it load**

I asked the agent to audit a carrier invoice that was $200 over the contracted linehaul. In the Activity view, the first tool call was `load_skill` with `name: freight-audit-playbook`, and the agent then applied the playbook’s $25 tolerance and came back with a SHORT-PAY disposition.

 ![The load_skill call in the Activity view](https://canada1.discourse-cdn.com/solace/original/2X/c/c2da9aca37cd3c0fae7f1e1ce60038d7a8780bc0.jpeg)

Note:

- You don’t add `load_skill` to the agent yourself. Attaching any skill registers `load_skill` and `unload_skill`.
- To update a deployed skill, use **Re-upload** on its row.

Docs:

- [Creating Skills](https://docs.solace.com/Agent-Mesh/Framework/building/skills.htm)
- [Skills](https://docs.solace.com/Agent-Mesh/Framework/concepts/skills.htm)

If you want to try this on your own playbook, [download the Solace Agent Mesh desktop app](https://solace.com/products/agent-mesh/) and start with an instruction-only skill like mine.

What would you move out of your agent’s system prompt and into a skill first?
