mcpField
S
setup-rhdh-skills

setup-rhdh-skills

github.com/redhat-developerAgent workflows1972 installsUpdated 1d ago
Repository

About setup-rhdh-skills

Set Up RHDH Skills is a human-directed skill for installing the RHDH skill collection and configuring its required capabilities. It uses a setup doctor, branch-specific references, and an approval gate for changes to the user's machine and accounts.

Key features

  1. 01Install, upgrade, or repair skill collection
  2. 02Check setup status with a doctor
  3. 03Configure named capabilities by branch
  4. 04Plan and approve machine changes
  5. 05Keep credentials in owning stores

Use cases

  1. 01Installing or repairing the skill collection
  2. 02Setting up Jira or Google Workspace access
  3. 03Configuring repositories or local runtime
  4. 04Authenticating Atlassian MCP in Cursor

MCP support

One setup branch guides authentication for Atlassian MCP in Cursor. The skill's other branches cover installing skills and configuring capabilities.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/redhat-developer/rhdh-skills --skill setup-rhdh-skills

After installing, type/setup-rhdh-skillsin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
assets/
catalog.json
references/
atlassian-mcp.md
google-workspace.md
install.md
jira.md
local-runtime.md
openshift-ci.md
private-data.md
repositories.md
scripts/
setup.py

Details

From the project README

Set Up RHDH Skills

Bootstrap the complete pack, then configure the capabilities needed by its model skills. This is a human entry point because installation, credentials, and external mutations require human agency.

Choose a setup branch

RequestLoad
Install, upgrade, or repair the complete skill collectionreferences/install.md
Configure Jira CLI, REST, or GraphQL accessreferences/jira.md
Configure Google Workspace access for schedules and test plansreferences/google-workspace.md
Configure the RHDH private-data checkoutreferences/private-data.md
Authenticate Atlassian MCP in Cursorreferences/atlassian-mcp.md
Discover or configure RHDH repositoriesreferences/repositories.md
Configure containers and the local RHDH runtimereferences/local-runtime.md
Authenticate the OpenShift CI Gangway adapterreferences/openshift-ci.md

With no branch in the request, show this table and wait for the user's selection.

Preflight

Run the setup doctor before every branch:

uv run scripts/setup.py doctor --json

Consume the complete report. Reuse it during the session unless setup changes. The doctor lists installed skills, the skills still missing, capability status, and configuration locations; it does not read credentials.

Write gate

Installing skills and configuring capabilities writes to the user's machine and accounts. Invoke the named skill mutation-gate and follow it.

scripts/setup.py install-plan states the ordered install operations, and scripts/setup.py apply --plan <file> --confirm runs the approved plan and reports one outcome per operation. Configuration branches state their own operations the same way.

Credentials remain in the owning tool's credential store or OS keyring. Pass secrets directly to the tool without placing them in conversation, configuration JSON, plans, outcome reports, or pack content.

Completion

A branch is complete when the doctor reports every promoted skill in assets/catalog.json plus grilling, code-review, and handoff as installed, the branch's own capability reads as present in that same doctor report, and the branch reference's smoke check has been run with its output shown. An install branch additionally requires one reported outcome for every operation in the approved plan, and the user told to restart or rescan the agent. When a model skill sent the user here because a capability was missing, every capability it named must report installed before the branch closes. Name any capability still missing as unresolved instead of closing on it.

Comments

Markdown supported