Rolling out now. Custom skills are being released gradually. If you don’t see a Skills tab in your dashboard yet, it’s on its way — reach out to your account manager to have it switched on for your team. You can already ask the Neo Support Agent to build a skill for you today.
Why custom skills make outputs reliable
When an agent takes on a complex, multi-step task, it normally works out the approach each time it runs — which data to pull, how to crunch it, how to format the result. That flexibility is exactly what you want for one-off problems. But for a job you run every week, you want the opposite: the same proven steps, every time, no surprises. A custom skill gives the agent a fixed recipe to follow instead of reinventing it. The result:- Consistent — the Monday report looks the same every Monday, in the same shape and format.
- Reliable — the tricky parts (a fiddly query, a specific calculation) were worked out and tested once, then reused. The agent doesn’t re-derive them and occasionally get them wrong.
- Faster — the agent follows the recipe rather than reasoning the whole job out from first principles.
What’s inside a skill
A skill is a small bundle of files. There are two kinds:| File | What it is | Can you edit it? |
|---|---|---|
SKILL.md | The procedure written in plain English — the steps the agent follows, and when to use the skill | Yes — edit it any time |
scripts/… | The code the skill runs (for example, to pull and crunch data) | No — read-only |
SKILL.md — a written procedure the agent reads and follows. Skills that do real data work usually include one or more scripts that the agent runs in its secure code sandbox.
The plain-English procedure (
SKILL.md) is yours to fine-tune whenever you like. The scripts are locked to keep a tested skill working exactly as verified — to change a script, just ask Neo Support. This split is deliberate: you stay in control of the instructions while the code stays safe.How your agents use a skill
- Available everywhere. Every skill you create is automatically available to every agent in your tenant — there’s no per-agent setup or toggle.
- Loaded when relevant. When an agent takes on a task that matches a skill, it loads that skill, reads the procedure, and runs any scripts — instead of working the task out from scratch.
- Guaranteed for a scheduled job. For a scheduled agent whose entire job is one procedure (say, a weekly report), name the skill in the agent’s instructions — for example, “Load and run the
weekly-ticket-summaryskill” — so it’s used on every run.
A typical example
Say every Monday a scheduled agent builds an open-ticket summary for your team — grouped by client and priority, with totals and a short list of the oldest tickets. It works, but you notice small differences week to week: the grouping order shifts, the wording changes, occasionally a count looks off. Turn that job into a skill, and it stops drifting. The procedure and the code are fixed, so the report comes out in the same shape — same sections, same calculations, same format — every single Monday. New technicians reading the report always see the layout they’re used to, and you can trust the numbers because the same tested logic runs each time.Skills vs. instructions & memory
A skill, custom instructions, and memory all shape how an agent behaves, but they do different jobs:| Best for | |
|---|---|
| Custom skill | A specific, repeatable procedure you want done the same way every time (a report, a reconciliation, a multi-step routine) |
| Custom instructions | Ongoing rules and preferences that apply across an agent’s work (tone, sign-off, which clients to prioritize) |
| Memory | Facts about your company and clients the agent should remember and reuse |
Create & manage your skills
Ask Neo Support to build a skill, then view and fine-tune it in the Skills tab