Skip to content
Back to skills

Relewise Core

ASecurity

Discover, identify, inspect, and compare Relewise Datasets. Use when a user asks which Datasets they can access, wants details or Agent Gateway capabilities for a Dataset, or needs Dataset context resolved before another Relewise task.

  • 9 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added September 19, 2026
ai-agents

Works with

  • cli
  • mcp

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 19, 2026

npx -y skills add Relewise/relewise-agent-plugins --skill relewise-core --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Relewise Core?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Relewise Core
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/relewise-relewise-core/badge)](https://www.skillsdirectory.com/skills/relewise-relewise-core)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: relewise-core
metadata:
  relewise-execution-skill: relewise-agent-gateway
description: Discover, identify, inspect, and compare Relewise Datasets. Use when a user asks which Datasets they can access, wants details or Agent Gateway capabilities for a Dataset, or needs Dataset context resolved before another Relewise task.
---

# Relewise Core

Before any Agent Gateway call, activate and follow the installed `relewise-agent-gateway` skill from this plugin. Pass it the selected REST operation ID and/or MCP tool plus validated parameters; do not resolve the CLI, choose a transport, or handle authentication in this domain skill.

## Resolve Dataset context

1. Discover candidate Datasets and authentication metadata for the current connection using REST operation `IdentityGetCurrentUser` or related MCP tool `get_me` through the Agent Gateway skill.
   For no Datasets or a missing expected Dataset, follow the setup skill's [Dataset access guidance](../relewise-setup/references/dataset-access.md), selecting PAT or OAuth guidance from the returned authentication method.
2. Match the user's wording against returned Dataset and License display names. Never invent or infer a Dataset ID that was not returned.
3. If multiple Datasets plausibly match and the intended one changes the answer, present the concise candidates and ask the user to choose.
4. Retrieve details for each selected Dataset before relying on its metadata or effective Agent Gateway policy. Use REST operation `CoreGetDataset` or related MCP tool `get_dataset_details` through the Agent Gateway skill.

Keep Dataset selection local to the current request. Do not establish one global Dataset. Resolve and validate each Dataset independently for comparisons.

## Work with Dataset capabilities

For missing configuration or a policy restriction, follow [Dataset policy guidance](../relewise-setup/references/dataset-access.md#dataset-listed-policy-needs-attention) and verify again after the user confirms changes.

Use the effective policy to explain whether REST and MCP are enabled and which Agent Gateway Areas are available. Do not claim a capability that its policy disables.

When Dataset-specific vocabulary such as languages, currencies, Data Keys, or Classification Values is needed, use the Dataset-metadata capability. Inspect the selected transport's current schema first; over REST its operation ID is `CoreGetDatasetMetadata`. Treat Data Key names as case-sensitive.

## Respond

Use Dataset display names in the answer and include IDs only when they help disambiguate or the user requests them. For comparisons, preserve the association between each result and its Dataset. Explain access or policy limitations plainly; do not silently substitute another Dataset.

Files in this skill

  • SKILL.md2.7 KB
  • operations.json109 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.