Agent skill

Catalog Sample Data

Generate or update sample YAML data for a catalog plugin. An agent skill from kubeflow/hub.

Apache-2.0Auto-check passedBackend & APIs

Install Catalog Sample Data

skills CLI

$ npx skills add kubeflow/hub --skill catalog-sample-data -a claude-code

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

GitHub CLI

$ gh skill install kubeflow/hub catalog-sample-data --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/kubeflow/hub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/catalog-sample-data .claude/skills/catalog-sample-data && 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 "catalog-sample-data" agent skill from https://github.com/kubeflow/hub/tree/main/.agents/skills/catalog-sample-data into .claude/skills/catalog-sample-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "catalog-sample-data", 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/kubeflow/hub/tree/main/.agents/skills/catalog-sample-data

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 kubeflow/hub --skill catalog-sample-data -a codex

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

GitHub CLI

$ gh skill install kubeflow/hub catalog-sample-data --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/kubeflow/hub.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/catalog-sample-data .agents/skills/catalog-sample-data && 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 "catalog-sample-data" agent skill from https://github.com/kubeflow/hub/tree/main/.agents/skills/catalog-sample-data into .agents/skills/catalog-sample-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "catalog-sample-data", 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 kubeflow/hub --skill catalog-sample-data -a cursor

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

GitHub CLI

$ gh skill install kubeflow/hub catalog-sample-data --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/kubeflow/hub.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/catalog-sample-data .cursor/skills/catalog-sample-data && 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 "catalog-sample-data" agent skill from https://github.com/kubeflow/hub/tree/main/.agents/skills/catalog-sample-data into .cursor/skills/catalog-sample-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "catalog-sample-data", 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/kubeflow/hub.git --path .agents/skills/catalog-sample-data

--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 kubeflow/hub --skill catalog-sample-data -a gemini-cli

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

GitHub CLI

$ gh skill install kubeflow/hub catalog-sample-data --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/kubeflow/hub.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/catalog-sample-data .gemini/skills/catalog-sample-data && 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 "catalog-sample-data" agent skill from https://github.com/kubeflow/hub/tree/main/.agents/skills/catalog-sample-data into .gemini/skills/catalog-sample-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "catalog-sample-data", 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 kubeflow/hub catalog-sample-data

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 kubeflow/hub --skill catalog-sample-data -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/kubeflow/hub.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/catalog-sample-data .github/skills/catalog-sample-data && 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 "catalog-sample-data" agent skill from https://github.com/kubeflow/hub/tree/main/.agents/skills/catalog-sample-data into .github/skills/catalog-sample-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "catalog-sample-data", 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 kubeflow/hub --skill catalog-sample-data -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 kubeflow/hub catalog-sample-data --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/kubeflow/hub.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/catalog-sample-data .opencode/skills/catalog-sample-data && 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 "catalog-sample-data" agent skill from https://github.com/kubeflow/hub/tree/main/.agents/skills/catalog-sample-data into .opencode/skills/catalog-sample-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "catalog-sample-data", 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: catalog-sample-data
GitHub stars: 186
Token cost: ~1.1k tokens
SKILL.md length: 370 words
Files: 1
Skills in repo: 5
Repo updated: Oct 6, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Generate or update sample YAML data for a catalog plugin. An agent skill from kubeflow/hub.

Works in 6 steps: Identify Plugin + Target → Read the Entity Schema → Ask About Content → …
Plugins that already have a YAML provider (model
SKILL.md covers Phase 1: Identify Plugin +…, Phase 2: Read the Entity Schema, Phase 3: Ask About Content and Phase 4: Generate the YAML…, plus 2 more sections
Calls go

What it does

Catalog Sample Data is an agent skill from kubeflow/hub. Generate or update sample YAML data for a catalog plugin. Creates a data file with realistic entries matching the plugin's OpenAPI schema, and adds a source entry to sources.yaml. Does not implement the loader — use for plugins that already have a YAML provider (model, mcp) or as a data template for new plugins.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering OpenAPI specifications. It works with Model Context Protocol and OpenAPI. The repository describes itself as: Model Registry provides a single pane of glass for ML model developers to index and manage models, versions, and ML artifacts metadata. It fills a gap between model… The licence is Apache-2.0.

When your agent uses it

Plugins that already have a YAML provider (model
As a data template for new plugins

Example prompts

“/catalog-sample-data”

Workflow steps

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

Identify Plugin + Target
Read the Entity Schema
Ask About Content
Generate the YAML Data File
Update sources.yaml
Report

What it can do on your machine

Read from SKILL.md and the folder at commit 3369d7e. 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:
- go
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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

Catalog Sample Data loads about 1.1k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 370 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~83
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

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 kubeflow/hub at commit 3369d7e, republished under its Apache-2.0 licence (© kubeflow). 370 words, ~1,087 tokens.

Download SKILL.mdSave it as .claude/skills/catalog-sample-data/SKILL.md (or your agent's skills folder).

name: catalog-sample-data
description: Generate or update sample YAML data for a catalog plugin. Creates a data file with realistic entries matching the plugin's OpenAPI schema, and adds a source entry to sources.yaml. Does not implement the loader — use for plugins that already have a YAML provider (model, mcp) or as a data template for new plugins.
user-invocable: true

Catalog Sample Data

Generate sample YAML data for a catalog plugin and register it in sources.yaml.

Phase 1: Identify Plugin + Target

Ask the user:

Which plugin to generate data for? Validate that api/openapi/src/plugins/<name>.yaml exists.
Where to put the data? Default: manifests/kustomize/options/catalog/overlays/e2e/. Other options if asked:
- manifests/kustomize/options/catalog/overlays/demo/ — development
- Custom path
Do NOT put sample data in manifests/kustomize/options/catalog/base/ — base is for production config only.

Phase 2: Read the Entity Schema

Read api/openapi/src/plugins/<name>.yaml and extract each entity's schema properties from components.schemas. These are the fields each sample record should have.

Also read the DatastoreEntries in catalog/internal/plugins/<name>/plugin.go to confirm which fields are persisted as properties — the data file must use these exact names.

Combine both to build a field list for each entity, noting:

Field name
Type (string, boolean, array, integer)
Whether it's a core field (id, name) or a property (description, provider, etc.)

Phase 3: Ask About Content

Ask the user:

How many sample records? (default: 3-5)
Theme or domain? (e.g., "weather agents", "code review tools") — if not specified, generate something realistic based on the plugin name

Phase 4: Generate the YAML Data File

Generate the data file following the established format. Use existing files as reference:

Models: manifests/kustomize/options/catalog/base/sample-catalog.yaml
MCP: manifests/kustomize/options/catalog/overlays/e2e/test-mcp-servers.yaml

Format for context entities

yaml

source: Sample <PascalName>s
<entity_plural>:
  - name: example-name
    description: "A realistic description"
    <string_field>: "value"
    <array_field>:
      - item1
      - item2
    <boolean_field>: true
    customProperties: {}
    createTimeSinceEpoch: "<epoch_millis>"
    lastUpdateTimeSinceEpoch: "<epoch_millis>"

Show full SKILL.md (168 more words)Show less

Guidelines for realistic data

Names should be realistic and varied (e.g., "mistralai/Mistral-7B" not "test-1")
Descriptions should be 1-2 sentences, distinct per record
Use current epoch milliseconds for timestamps
Array fields should have 2-4 items
Boolean fields should have a mix of true/false across records
Include customProperties: {} on each record (empty is fine)
source_id is NOT included in the data file — it's set automatically from the sources.yaml id

Write to: <target_dir>/sample-<name>-catalog.yaml

If the file already exists, ask whether to overwrite or append.

Phase 5: Update sources.yaml

Read the existing sources.yaml at the target path. If it doesn't exist, create it with a minimal structure.

Add an entry for this plugin under <name>_catalogs:

yaml

<name>_catalogs:
  - name: "Sample <PascalName> Catalog"
    id: sample_<name>_catalog
    type: yaml
    enabled: true
    properties:
      yamlCatalogPath: sample-<name>-catalog.yaml
    labels:
      - sample

If an entry with id: sample_<name>_catalog already exists, ask whether to replace it.

Important: preserve all existing content in sources.yaml — only add or replace the specific entry. Use Read + Edit rather than Write to avoid clobbering other plugins' entries.

Phase 6: Report

Print:

Data file path and record count
Sources.yaml entry status (added/replaced/unchanged)

Then print a reminder:

Note: For this data to load at startup, the plugin needs:
  1. A YAML provider registered (e.g., in <pkg>/providers.go)
  2. PerformLeaderOperations wired to call the provider

Model and MCP plugins have this built-in. For new plugins like 'agent',
these need to be implemented separately.

To test with the catalog server:
  PGHOST=localhost PGPORT=5432 PGDATABASE=catalog PGUSER=catalog PGPASSWORD=catalog \
    go run . catalog --catalogs-path=<target_dir>/sources.yaml

Files

Just SKILL.md in .agents/skills/catalog-sample-data of kubeflow/hub.

Open the folder on GitHubat commit 3369d7e

Compare with similar skills

Catalog Sample Data 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.

Catalog Sample Data compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Catalog Sample Data this skillkubeflow/hub	186	—	~1.1k	Automated safety check: Pass	Apache-2.0	yesterday
OpenAPI to MCP Servermcp-use/mcp-use	11k	—	~5.2k	Automated safety check: Pass	Apache-2.0	yesterday
API Endpoint Contracttrycompai/comp	2k	—	~2.7k	Automated safety check: Pass	AGPL-3.0	5 days ago
SpikardGoldziher/spikard	123	—	~799	Automated safety check: Pass	MIT	4 days ago
Executor Usagejeremyosih/pi-executor	104	—	~1.4k	Automated safety check: Pass	MIT	3 mo ago
Kingdee MCP DevWaHaiLong/KingdeeMCP	103	—	~853	Automated safety check: Pass	MIT	1 mo ago

Similar skills

OpenAPI to MCP Server
mcp-use/mcp-use
Turns an OpenAPI or Swagger spec into an MCP server with the mcp-use TypeScript SDK, mapping each operation to a tool, wiring auth, testing and deploying.
11k GitHub stars~5.2k tokensUpdated yesterday
Backend & APIsAuto-check passed
API Endpoint Contract
trycompai/comp
The contract every new or modified API endpoint must follow so it is correct for the public OpenAPI spec, the MCP server (npm @trycompai/mcp-server), the ValidationPipe, and the docs.
2k GitHub stars~2.7k tokensUpdated 5 days ago
Backend & APIsAuto-check passed
Spikard
Goldziher/spikard
Scaffold Spikard projects and generate code from OpenAPI, AsyncAPI, OpenRPC, GraphQL, and Protobuf schemas using the Spikard CLI or its MCP server.
123 GitHub stars~799 tokensUpdated 4 days ago
Backend & APIsAuto-check passed
Executor Usage
jeremyosih/pi-executor
Load this skill before using the execute tool. An agent skill from jeremyosih/pi-executor.
104 GitHub stars~1.4k tokensUpdated 3 mo ago
Backend & APIsAuto-check passed
Kingdee MCP Dev
WaHaiLong/KingdeeMCP
Knowledge base for the Kingdee MCP Dev Squad. An agent skill from WaHaiLong/KingdeeMCP.
103 GitHub stars~853 tokensUpdated 1 mo ago
Backend & APIsAuto-check passed
Release Workflow
Goldziher/spikard
Release/publish the spikard Rust core crate and CLI end-to-end.
123 GitHub stars~909 tokensUpdated 4 days ago
Backend & APIsAuto-check passed

Questions about Catalog Sample Data

What does Catalog Sample Data do?

Generate or update sample YAML data for a catalog plugin. An agent skill from kubeflow/hub. Catalog Sample Data is an agent skill from kubeflow/hub. Generate or update sample YAML data for a catalog plugin.

When should I use Catalog Sample Data?

Catalog Sample Data fits situations like: plugins that already have a YAML provider (model; as a data template for new plugins.

How do I install Catalog Sample Data in Claude Code?

Run `npx skills add kubeflow/hub --skill catalog-sample-data -a claude-code`. Or copy the skill folder (.agents/skills/catalog-sample-data in kubeflow/hub) into .claude/skills/catalog-sample-data in your project. Claude Code loads it when a task matches its description.

How do I install Catalog Sample Data in Codex?

Run `npx skills add kubeflow/hub --skill catalog-sample-data -a codex`. Or copy the skill folder (.agents/skills/catalog-sample-data in kubeflow/hub) into .agents/skills/catalog-sample-data in your project. Codex loads it when a task matches its description.

Can I use Catalog Sample Data 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 kubeflow/hub --skill catalog-sample-data -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/catalog-sample-data, .gemini/skills/catalog-sample-data, .github/skills/catalog-sample-data and .opencode/skills/catalog-sample-data in your project.

What does Catalog Sample Data need to run?

Going by SKILL.md and its folder, Catalog Sample Data needs the command-line tools its instructions call (go).

Does Catalog Sample Data access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Catalog Sample Data 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 Catalog Sample Data use?

Catalog Sample Data 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 Catalog Sample Data use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Catalog Sample Data?

Skills that share tags, products or a category with Catalog Sample Data: OpenAPI to MCP Server (mcp-use/mcp-use, 11k stars), API Endpoint Contract (trycompai/comp, 2k stars), Spikard (Goldziher/spikard, 123 stars) and Executor Usage (jeremyosih/pi-executor, 104 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Catalog Sample Data?

kubeflow (a GitHub organization) maintains it in kubeflow/hub, which has 186 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 6, 2026.

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

Catalog Sample Data

Install Catalog Sample Data

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Catalog Sample Data

Phase 1: Identify Plugin + Target

Phase 2: Read the Entity Schema

Phase 3: Ask About Content

Phase 4: Generate the YAML Data File

Format for context entities

Guidelines for realistic data

Phase 5: Update sources.yaml

Phase 6: Report

Files

Compare with similar skills

Similar skills

OpenAPI to MCP Server

API Endpoint Contract

Spikard

Executor Usage

Kingdee MCP Dev

Release Workflow

More from kubeflow/hub

Create Agent Catalog Source

Catalog Add Route

Init Catalog

Sync Catalog

Questions about Catalog Sample Data

Install Catalog Sample Data

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Catalog Sample Data

Phase 1: Identify Plugin + Target

Phase 2: Read the Entity Schema

Phase 3: Ask About Content

Phase 4: Generate the YAML Data File

Format for context entities

Guidelines for realistic data

Phase 5: Update sources.yaml

Phase 6: Report

Files

Compare with similar skills

Similar skills

More from kubeflow/hub

Related

Questions about Catalog Sample Data