dsx-ai-factory/run-ai/runai-docs-ui-how-to

Claude Code and agent skill by dsx-ai-factory/run-ai

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Generate documentation for a new NVIDIA Run:ai UI resource type — one page covering the intro, table, and all UI procedures (create, edit, delete, and any additional flows), plus nav registration. Use when a new object with UI flows is added to the platform.

Install

npx vskill@latest install dsx-ai-factory/run-ai/runai-docs-ui-how-to

SKILL.md

NVIDIA Run:ai UI Resource Documentation

Use when a new UI resource type is introduced — an object that has its own table and create/edit/delete flows in the NVIDIA Run:ai platform.

Examples: Departments, Projects, Node Pools, Environments, Compute Resources, Data Sources, Credentials, Workload Templates.

On Activation

Before drafting anything:

  1. Ask: "What is the name of the new resource? What UI flows does it have

(create, edit, delete, metrics, policies, access rules)?"

  1. Read the API spec for this resource from fern/apis/ if it exists.
  2. Read docs/platform-management/aiinitiatives/organization/departments.md

in full — this is your structural reference.

  1. Read docs/AGENTS.md for writing rules, Fern components, and terminology.

Document only what the code and API spec confirm. Anything you cannot verify needs verification before it's included.

Page to Create

One page at docs/.../[resource-name].md following the departments.md pattern exactly:

  • H1: bare noun — # [Resource Name]
  • Opening paragraph(s): 1-2 sentences explaining what the resource is and

what it enables. No steps, no table yet.

  • [Resource] Table section: where to find it in the UI, what it lists,

then a column definitions table. Include a <figure> image placeholder if a screenshot exists in docs/assets/.

  • One section per UI flow:
  • ## Creating a [Resource] — numbered steps, bold UI elements
  • ## Editing a [Resource]
  • ## Deleting a [Resource] — include <Warning> for destructive action
  • Additional sections for any other flows (scheduling rules, access rules,

policies, metrics)

  • Use <Warning> for destructive actions and important caveats — never plain text
  • Use <Note> for notes about defaults, limits, or constraints — never plain text
  • Bold all UI element names: +NEW RESOURCE, SAVE, DELETE
  • `## Using CLI` at the end: one line linking to the specific command page

under docs/reference/cli/runai/, if a CLI command exists for this resource. Pages are named runai_<noun>_<verb>.md (e.g. runai_department_list.md) — find the actual file for the resource rather than guessing the filename, and link to that file, not to the directory. Only include if confirmed in the code.

  • `## Using API` after Using CLI: one line linking to the API reference, if the resource has an API. Use Fern's api: link syntax (e.g. api:[api-name]:[METHOD path]), not a hardcoded domain — it resolves at build time regardless of URL pattern or version.
  • `## Using MCP` after Using API: one line naming the relevant MCP tool

from docs/agents/tools-reference.md, if the resource has a real, confirmed tool there — check the domain tables (Identity, Credentials, Workloads, Cluster and Infrastructure, Resources and Organization) rather than guessing a tool name. MCP tools are not individually addressable pages, so link to the domain section anchor (e.g. ../../agents/tools-reference.md#workloads), not a per-tool anchor, and name the tool itself in backticks. Only include if confirmed in tools-reference.md.

Nav Registration

Register the page in the correct product nav files under fern/products/. Add to every product the resource applies to (self-hosted.yml, multi-tenant.yml as appropriate).

Quality Checks

Before finishing:

  • [ ] All field names, defaults, and behaviors verified against API spec or

source code — no invented values

  • [ ] No unverified claims — anything not confirmed by source needs verification first
  • [ ] <Warning> used for every destructive action — never plain text
  • [ ] <Note> used for every note — never plain text
  • [ ] All cross-references are markdown links — never plain text
  • [ ] Nav entries added to all applicable product files
  • [ ] fern docs dev runs without errors

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
519
Repository forks
74
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/dsx-ai-factory/run-ai/runai-docs-ui-how-to/badge)](https://verified-skill.com/skills/dsx-ai-factory/run-ai/runai-docs-ui-how-to)

Something wrong with this skill or its page? Tell us.