# Create Workflow

> Create and run user-triggered workflows with declared steps. Use when the user asks about a workflow or wants a verifiable recipe (fetch, compare, summarize) they can run on demand from chat or the dashboard.

- **Type:** Skill
- **Install:** `agentstack add skill-ahmadrosid-nakama-create-workflow`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ahmadrosid](https://agentstack.voostack.com/s/ahmadrosid)
- **Installs:** 0
- **Category:** [Data & Analytics](https://agentstack.voostack.com/c/data-and-analytics)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ahmadrosid](https://github.com/ahmadrosid)
- **Source:** https://github.com/ahmadrosid/nakama/tree/main/packages/plugins/workflows/skills/create-workflow
- **Website:** https://ahmadrosid.github.io/nakama

## Install

```sh
agentstack add skill-ahmadrosid-nakama-create-workflow
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

When the user wants a workflow they can run on demand (for example "morning brief"), explain the step recipe clearly before saving.

Use `plugin_workflows__create_workflow` with `kind` (never `type`). Last step must be `summarize` with `prompt` (never `instruction`).

```json
[
  { "id": "news", "kind": "tool", "tool": "web_fetch", "input": { "url": "https://news.ycombinator.com" } },
  { "id": "summary", "kind": "summarize", "prompt": "Write a brief from the receipts only." }
]
```

- `tool` — assigned profile or MCP tool that can run locally; `input` must match that tool's schema. Use `web_fetch` for URLs. Do not use `web_search` — it only runs inside a provider chat turn.
- `template` — substitutes values into text only. Writing “extract stories” in a template returns those instructions; it does not call AI, parse content, or produce structured JSON.
- `compare` / `assert` — deterministic checks on prior receipts. `compare.op` is `eq` | `near` | `contains`. Do not use compare as free-text analysis
- exactly one final `summarize` — turns the receipt bag into prose (no tools). It cannot be an intermediate extraction step or feed a later database step.

For extraction or analysis before a write, use an available tool that actually performs that work. Verify its input and output schema; do not invent a tool or output field. If no suitable tool is assigned, explain the missing capability instead of saving a recipe that cannot fulfill the request.

References use the tool's actual output shape: `{{steps.fetch.content}}`, not an assumed `.output` wrapper. Missing references stop the run. Explicit null values are allowed, so check required data with assert/compare steps before writes when applicable.

For a requested quantity such as five saved stories, check the extraction count and the database result with an assert/compare step. Inspect receipts before claiming success: a completed SQL call with `changes: 0` does not prove stories were saved. Do not blindly rerun writes after a failure; inspect which writes already completed.

When the user names a profile to run as, confirm that profile and pass its `agentId`. Omit `agentId` to use the current chat profile.

When the user asks to run a saved workflow, use `plugin_workflows__list_workflows` to find it, then `plugin_workflows__run_workflow`. Pass `input` when the recipe uses `{{input.*}}` bindings.

When the user wants to change an existing workflow, use `plugin_workflows__update_workflow`.

Do not use workflows for clock-driven jobs — use `create_automation` for schedules.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ahmadrosid](https://github.com/ahmadrosid)
- **Source:** [ahmadrosid/nakama](https://github.com/ahmadrosid/nakama)
- **License:** MIT
- **Homepage:** https://ahmadrosid.github.io/nakama

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ahmadrosid-nakama-create-workflow
- Seller: https://agentstack.voostack.com/s/ahmadrosid
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.