Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/orchestra-hq/orchestra-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/orchestra-hq/orchestra-skills/migrate-to-orchestra)<a href="https://agentmods.dev/plugins/orchestra-hq/orchestra-skills/migrate-to-orchestra"><img src="https://agentmods.dev/badge/plugins/orchestra-hq/orchestra-skills/migrate-to-orchestra/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/orchestra-hq/orchestra-skills/migrate-to-orchestra"><img src="https://agentmods.dev/badge/plugins/orchestra-hq/orchestra-skills/migrate-to-orchestra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
migrate-to-orchestra scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "migrate-to-orchestra",
"description": "Skills for converting Dagster, Prefect, and Airflow pipelines into Orchestra pipeline YAML — schedules and retries, dbt/Python/Airbyte/Fivetran/Tableau/Power BI/Slack tasks, connections and secrets, alerts, sensors/automations, branching/conditions, cross-job/cross-flow/cross-DAG dependencies, asset checks/testing, and data passing.",
"version": "1.2.0",
"author": {
"name": "Orchestra"
},
"license": "Apache-2.0",
"homepage": "https://www.getorchestra.io/",
"repository": "https://github.com/orchestra-hq/orchestra-skills",
"keywords": ["orchestra", "migration", "dagster", "prefect", "airflow", "data-pipelines", "conversion"]
}
What it installs
The manifest is a name and a version. 52 skills travel with it, and installing the plugin installs all of them — 5,458 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill airflow-dag-structure-to-orchestra A 80 tokens
- Skill powerbi-dagster-to-orchestra A 139 tokens
- Skill airflow-conditions-to-orchestra A 92 tokens
- Skill airflow-connections-to-orchestra A 164 tokens
- Skill airflow-testing-to-orchestra A 79 tokens
- Skill dbt-core-airflow-to-orchestra A 137 tokens
- Skill powerbi-airflow-to-orchestra A 125 tokens
- Skill slack-prefect-to-orchestra A 189 tokens
- Skill airflow-alerts-to-orchestra A 98 tokens
- Skill airflow-bash-ssh-to-orchestra A 124 tokens
- Skill airflow-cross-dag-to-orchestra A 70 tokens
- Skill airflow-dynamic-task-mapping-to-orchestra A 148 tokens
- Skill airflow-sensors-to-orchestra A 83 tokens
- Skill airflow-xcoms-to-orchestra A 80 tokens
- Skill dagster-asset-checks-to-orchestra A 109 tokens
- Skill dagster-connections-to-orchestra A 98 tokens
- Skill dagster-definitions-to-orchestra A 98 tokens
- Skill dagster-io-managers-to-orchestra A 97 tokens
- Skill dagster-sensors-to-orchestra A 124 tokens
- Skill dagster-shell-ssh-to-orchestra A 133 tokens
- Skill dbt-core-dagster-to-orchestra A 107 tokens
- Skill powerbi-prefect-to-orchestra A 146 tokens
- Skill prefect-connections-to-orchestra A 97 tokens
- Skill prefect-data-passing-to-orchestra A 95 tokens
- Skill prefect-testing-to-orchestra A 98 tokens
- Skill python-airflow-to-orchestra A 75 tokens
- Skill python-dagster-to-orchestra A 95 tokens
- Skill python-prefect-to-orchestra A 98 tokens
- Skill slack-airflow-to-orchestra A 163 tokens
- Skill dagster-alerts-to-orchestra A 114 tokens
- Skill dagster-branching-to-orchestra A 107 tokens
- Skill dagster-cross-job-to-orchestra A 101 tokens
- Skill dbt-core-prefect-to-orchestra A 103 tokens
- Skill prefect-alerts-to-orchestra A 108 tokens
- Skill prefect-automations-to-orchestra A 93 tokens
- Skill prefect-conditions-to-orchestra A 88 tokens
- Skill prefect-cross-flow-to-orchestra A 72 tokens
- Skill prefect-flow-structure-to-orchestra A 102 tokens
- Skill prefect-secrets-to-orchestra A 86 tokens
- Skill slack-dagster-to-orchestra A 105 tokens
- Skill airbyte-cloud-airflow-to-orchestra A 94 tokens
- Skill airbyte-cloud-dagster-to-orchestra A 97 tokens
- Skill airbyte-server-airflow-to-orchestra A 97 tokens
- Skill airbyte-server-dagster-to-orchestra A 110 tokens
- Skill fivetran-airflow-to-orchestra A 90 tokens
- Skill fivetran-dagster-to-orchestra A 102 tokens
- Skill tableau-airflow-to-orchestra A 84 tokens
- Skill tableau-dagster-to-orchestra A 83 tokens
- Skill tableau-prefect-to-orchestra A 90 tokens
- Skill airbyte-cloud-prefect-to-orchestra A 92 tokens
- Skill airbyte-server-prefect-to-orchestra A 107 tokens
- Skill fivetran-prefect-to-orchestra A 92 tokens
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 13 lines scan A 550f2b451399
migrate-to-orchestra is a plugin published in the GitHub repository orchestra-hq/orchestra-skills (9 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
clip-aware-embeddings
Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities, car models), spatial reasoning, or compositional queries. Activate on "CLIP", "embeddings", "image similarity", "semantic…
tao-skill-bank
NVIDIA TAO skill bank with generated capability discovery for model training, data processing, application workflows, AutoML, and platform execution.
classifier
Text classification CLI using Bayesian, LSI, KNN, Logistic Regression, and TF-IDF algorithms.
databricks
Databricks skills for the CLI, Apps, Lakebase, Model Serving, Lakeflow Jobs, Spark Declarative Pipelines, Declarative Automation Bundles (DABs), and classic-to-serverless migration.
torch-air marketplace
Torch Accelerator Integration Readiness — evaluate how well a hardware accelerator integrates with PyTorch.
vmware-privateai
VMware Private AI (NVIDIA): GPU inventory, vGPU profiles, utilization, model serving — 17 tools.