Agent skill

Migrate To Rivers

Translate a Dagster or Prefect project to rivers, the Rust-powered asset orchestrator.

Apache-2.0Auto-check passedData & Analytics

Install Migrate To Rivers

skills CLI

$ npx skills add ion-elgreco/rivers --skill migrate-to-rivers -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install ion-elgreco/rivers migrate-to-rivers --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/ion-elgreco/rivers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/migrate-to-rivers .claude/skills/migrate-to-rivers && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "migrate-to-rivers" agent skill from https://github.com/ion-elgreco/rivers/tree/main/skills/migrate-to-rivers into .claude/skills/migrate-to-rivers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "migrate-to-rivers", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/ion-elgreco/rivers/tree/main/skills/migrate-to-rivers

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add ion-elgreco/rivers --skill migrate-to-rivers -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install ion-elgreco/rivers migrate-to-rivers --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ion-elgreco/rivers.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/migrate-to-rivers .agents/skills/migrate-to-rivers && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "migrate-to-rivers" agent skill from https://github.com/ion-elgreco/rivers/tree/main/skills/migrate-to-rivers into .agents/skills/migrate-to-rivers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "migrate-to-rivers", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ion-elgreco/rivers --skill migrate-to-rivers -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install ion-elgreco/rivers migrate-to-rivers --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ion-elgreco/rivers.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/migrate-to-rivers .cursor/skills/migrate-to-rivers && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "migrate-to-rivers" agent skill from https://github.com/ion-elgreco/rivers/tree/main/skills/migrate-to-rivers into .cursor/skills/migrate-to-rivers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "migrate-to-rivers", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/ion-elgreco/rivers.git --path skills/migrate-to-rivers

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add ion-elgreco/rivers --skill migrate-to-rivers -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install ion-elgreco/rivers migrate-to-rivers --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ion-elgreco/rivers.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/migrate-to-rivers .gemini/skills/migrate-to-rivers && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "migrate-to-rivers" agent skill from https://github.com/ion-elgreco/rivers/tree/main/skills/migrate-to-rivers into .gemini/skills/migrate-to-rivers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "migrate-to-rivers", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install ion-elgreco/rivers migrate-to-rivers

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add ion-elgreco/rivers --skill migrate-to-rivers -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/ion-elgreco/rivers.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/migrate-to-rivers .github/skills/migrate-to-rivers && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "migrate-to-rivers" agent skill from https://github.com/ion-elgreco/rivers/tree/main/skills/migrate-to-rivers into .github/skills/migrate-to-rivers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "migrate-to-rivers", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ion-elgreco/rivers --skill migrate-to-rivers -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install ion-elgreco/rivers migrate-to-rivers --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ion-elgreco/rivers.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/migrate-to-rivers .opencode/skills/migrate-to-rivers && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "migrate-to-rivers" agent skill from https://github.com/ion-elgreco/rivers/tree/main/skills/migrate-to-rivers into .opencode/skills/migrate-to-rivers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "migrate-to-rivers", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: migrate-to-rivers
GitHub stars: 102
Token cost: ~1.2k tokens
SKILL.md length: 578 words
Files: 4 (incl. references)
Skills in repo: 1
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Translate a Dagster or Prefect project to rivers, the Rust-powered asset orchestrator.

Works in 5 steps: Inventory the source project → Map concepts → Port, in dependency order → …
Automation conditions to rivers —
SKILL.md covers Ground rule, Workflow and Scope discipline
Calls python

What it does

Migrate To Rivers is an agent skill from ion-elgreco/rivers. Translate a Dagster or Prefect project to rivers, the Rust-powered asset orchestrator. Use when porting assets, ops, flows, tasks, jobs, schedules, sensors, partitions, IO managers, resources, retries, or automation conditions to rivers — or when asked to migrate/convert a data pipeline to rivers.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/from-dagster.md`, `references/from-prefect.md` and `references/rivers-api.md`).

It sits in Data & Analytics, covering Data pipelines and ETL. It works with Dagster and Rust. The repository describes itself as: Rivers is an orchestration platform for data and ML pipelines, written in Rust for native performance with a Python-first development experience. The licence is Apache-2.0.

When your agent uses it

Automation conditions to rivers —
Asked to migrate/convert a data pipeline to rivers

Example prompts

“/migrate-to-rivers”

Requirements

Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Inventory the source project
Map concepts
Port, in dependency order
Validate continuously
Report

What it can do on your machine

Read from SKILL.md and the folder at commit a9ee281. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- orchestrator.rs
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Migrate To Rivers loads about 1.2k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 79 tokens; SKILL.md has 578 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~79
When it runs · the whole SKILL.md, loaded when a task matches: ~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~14k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ion-elgreco/rivers at commit a9ee281, republished under its Apache-2.0 licence (© ion-elgreco). 578 words, ~1,210 tokens.

Download SKILL.mdSave it as .claude/skills/migrate-to-rivers/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.

name: migrate-to-rivers
description: Translate a Dagster or Prefect project to rivers, the Rust-powered asset orchestrator. Use when porting assets, ops, flows, tasks, jobs, schedules, sensors, partitions, IO managers, resources, retries, or automation conditions to rivers — or when asked to migrate/convert a data pipeline to rivers.

Migrate to rivers

Port a Dagster or Prefect project to rivers without inventing API.

rivers is asset-centric like Dagster, so most Dagster concepts map closely — but the spellings differ in ways that look right and fail at import. Prefect maps loosely: its flows are imperative, rivers' graph is declarative, so parts of a Prefect project need design decisions rather than translation.

Ground rule

Never write a rivers symbol you have not verified. The API is small enough to check and niche enough that a plausible guess is usually wrong. Before using any name:

Check references/rivers-api.md (in this skill) — signature-exact, generated from the type stubs.
If it isn't there, read the stubs directly: python/rivers/_core/**/__init__.pyi in the rivers source, or python -c "import rivers; help(rivers.X)".
Only then, the docs site.

Guessing costs more than checking: PartitionsDefinition.static_ (trailing underscore), MetadataValue.float_, daily(start=datetime(...)) (a datetime, not a string) are all things a confident guess gets wrong.

Workflow

1. Inventory the source project

Read the whole source project before porting anything. Produce a written inventory:

Assets/flows — name, upstream deps, partitioning, IO manager, resources used
Orchestration — jobs, schedules, sensors, automation conditions/triggers
Infrastructure — executors, work pools, K8s config, concurrency limits
Config & secrets — dg.Config classes, ConfigurableResources, Prefect Blocks, env vars
Things with no rivers equivalent — asset checks, dbt/dlt integrations, Prefect transactions, Cloud-only features

Report the last group to the user early. Do not silently drop or fake them.

2. Map concepts

Read the relevant reference file in full before writing code:

Dagster → references/from-dagster.md
Prefect → references/from-prefect.md

Both carry a mapping table, before/after code for every concept, and a gotchas section covering the traps that survive a naive port (sensor cursors, config generics, partition key formats).

3. Port, in dependency order

Bottom-up. The graph is the skeleton; everything else attaches to it.

Resources and IO handlers — assets reference them, so they exist first
Assets — the DAG, without partitions or automation
Partitions — partition defs, then partition mappings on the edges
Automation — automation conditions, schedules, sensors
Jobs, executors, concurrency — the run-shaping layer
CodeRepository — assembled last, since it registers all of the above

Port a slice at a time and validate it (step 4) before moving on. A 40-asset project ported in one shot fails with 40 tangled errors.

Keep the source project's module layout unless the user asks otherwise — a diffable port is easier to review than a reorganized one.

Show full SKILL.md (182 more words)Show less

4. Validate continuously

Three gates, cheapest first:

bash

python -c "from my_pipeline import repo; repo.validate()"   # graph only — no storage, no side effects
rivers materialize my_pipeline --memory                     # end-to-end, in-memory storage
rivers dev my_pipeline                                      # UI on :3000 — does the graph look right?

repo.validate() is the fast inner loop: it catches cycles, missing upstreams, unresolvable resource params, and bad partition defs in milliseconds without touching storage. Run it after every slice; only reach for the other two once a slice validates.

Then port the tests. If the source project has none, write at least one materialization test per asset group — rivers tests are ordinary pytest against repo.materialize() and repo.load_node().

5. Report

Summarize for the user:

What ported cleanly
What changed semantically — every place the rivers version behaves differently (see the gotchas sections; sensor cursors and Prefect's imperative control flow are the usual culprits)
What was dropped, and why
What needs their decision

Semantic drift is the thing a migration must surface. A port that runs but computes something subtly different is worse than one that fails loudly.

Scope discipline

Translate what exists. A migration is not the moment to redesign the pipeline, add error handling the original lacked, or "improve" asset boundaries. If the source has a genuine bug, mention it — don't fix it silently in the port.

Files

SKILL.md and 3 other files (references) in skills/migrate-to-rivers of ion-elgreco/rivers.

SKILL.md
references/from-dagster.md
references/from-prefect.md
references/rivers-api.md

Open the folder on GitHubat commit a9ee281

Compare with similar skills

Migrate To Rivers next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Migrate To Rivers compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Migrate To Rivers this skillion-elgreco/rivers	102	—	~1.2k	Automated safety check: Pass	Apache-2.0	2 days ago
Migrating Dagster To Airflowastronomer/agents	451	—	~3.8k	Automated safety check: Pass	Apache-2.0	3 days ago
Dagster Expertdagster-io/skills	211	—	~2k	Automated safety check: Pass	Apache-2.0	yesterday
Dagster Expertdagster-io/skills	211	—	~321	Automated safety check: Pass	Apache-2.0	yesterday
AI Data Engineeringancoleman/ai-design-components	525	—	~3.5k	Automated safety check: Pass	MIT	10 mo ago
AI Pipeline Orchestrationsickn33/agentic-awesome-skills	47k	1 repos	~2.5k	Automated safety check: Pass	MIT	2 days ago

Similar skills

Migrating Dagster To Airflow
astronomer/agents
Guide for migrating Dagster projects to Apache Airflow 3 on Astro.
451 GitHub stars~3.8k tokensUpdated 3 days ago
Data & AnalyticsAuto-check passed
Dagster Expert
dagster-io/skills
Official
Expert guidance for working with Dagster and the dg CLI. An agent skill from dagster-io/skills.
211 GitHub stars~2k tokensUpdated yesterday
Data & AnalyticsAuto-check passed
Dagster Expert
dagster-io/skills
Official
A skill your agent uses for any task involving Dagster, the dg CLI, assets, materialization, components, data tools or data pipelines, matching the situations the Dagster skill handles.
211 GitHub stars~321 tokensUpdated yesterday
Data & AnalyticsAuto-check passed
AI Data Engineering
ancoleman/ai-design-components
Data pipelines, feature stores, and embedding generation for AI/ML systems.
525 GitHub stars~3.5k tokensUpdated 10 mo ago
Data & AnalyticsAuto-check passed
AI Pipeline Orchestration
sickn33/agentic-awesome-skills
Orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster.
47k GitHub starsUsed in 1 repo~2.5k tokens
Data & AnalyticsAuto-check passed
Azure Eventhub Rust
aiskillstore/marketplace
Azure Event Hubs SDK for Rust. An agent skill from aiskillstore/marketplace.
433 GitHub starsUsed in 4 repos~936 tokens
Data & AnalyticsAuto-check passed

Works with

Questions about Migrate To Rivers

What does Migrate To Rivers do?

Translate a Dagster or Prefect project to rivers, the Rust-powered asset orchestrator. Migrate To Rivers is an agent skill from ion-elgreco/rivers. Translate a Dagster or Prefect project to rivers, the Rust-powered asset orchestrator.

When should I use Migrate To Rivers?

Migrate To Rivers fits situations like: automation conditions to rivers —; asked to migrate/convert a data pipeline to rivers.

How do I install Migrate To Rivers in Claude Code?

Run `npx skills add ion-elgreco/rivers --skill migrate-to-rivers -a claude-code`. Or copy the skill folder (skills/migrate-to-rivers in ion-elgreco/rivers) into .claude/skills/migrate-to-rivers in your project. Claude Code loads it when a task matches its description.

How do I install Migrate To Rivers in Codex?

Run `npx skills add ion-elgreco/rivers --skill migrate-to-rivers -a codex`. Or copy the skill folder (skills/migrate-to-rivers in ion-elgreco/rivers) into .agents/skills/migrate-to-rivers in your project. Codex loads it when a task matches its description.

Can I use Migrate To Rivers in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ion-elgreco/rivers --skill migrate-to-rivers -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/migrate-to-rivers, .gemini/skills/migrate-to-rivers, .github/skills/migrate-to-rivers and .opencode/skills/migrate-to-rivers in your project.

What does Migrate To Rivers need to run?

Going by SKILL.md and its folder, Migrate To Rivers needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Migrate To Rivers access the network?

SKILL.md names 1 domain. As links in the text: orchestrator.rs. This is read from the text; nothing was executed.

Is Migrate To Rivers safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Migrate To Rivers use?

Migrate To Rivers is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Migrate To Rivers use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 12k tokens, read only when the agent opens those files.

What are the alternatives to Migrate To Rivers?

Skills that share tags, products or a category with Migrate To Rivers: Migrating Dagster To Airflow (astronomer/agents, 451 stars), Dagster Expert (dagster-io/skills, 211 stars), Dagster Expert (dagster-io/skills, 211 stars) and AI Data Engineering (ancoleman/ai-design-components, 525 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Migrate To Rivers?

ion-elgreco (a GitHub user) maintains it in ion-elgreco/rivers, which has 102 GitHub stars. The repository was last updated on October 9, 2026.

Source: ion-elgreco/rivers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Migrate To Rivers

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Migrate to rivers

Ground rule

Workflow

1. Inventory the source project

2. Map concepts

3. Port, in dependency order

4. Validate continuously

5. Report

Scope discipline

Files

Compare with similar skills

Similar skills

Migrating Dagster To Airflow

Dagster Expert

Dagster Expert

AI Data Engineering

AI Pipeline Orchestration

Azure Eventhub Rust

Related

Questions about Migrate To Rivers