What it does
The incredible HULL - Helm Uniform Layer Library - is a Helm library chart to improve Helm chart based workflows.
- Connects Instruction files the AI reads
- Account or key Not confirmed yet (README not read yet)
- Category Automation and agents
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/vidispine-hull)Similar Skills
Same kind of work, ordered like the Skills list
1 skills (instruction sets) by vidispine that an AI reads and follows · not an MCP server
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Not stated by the maker · SKILL.md skills work in apps that support Agent Skills, such as Claude Code, Codex and Cursor
Install
Is it safe?
- Who made it
GitHub account vidispine (organization), 9 years old
- Use and upkeep
★ 295 stars, few users so far · code last changed Nov 2, 2026
- Any scripts?
No, plain text files the AI reads and follows
- Uses the internet?
No scripts, so it does not go online by itself
- Changes machine-wide settings?
No hooks or writes to machine settings found
Checked automatically from the repo files at commit eb6dc02 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
First: which AI do you use?
Pick your app and this page shows only how to install it there
Option 1Upload to claude.ai (web and app)
Uploading to claude.ai would fail: the description is over 200 characters (417). Use "Let the AI install it" instead
Option 1Let Claude Code install it
Copy this sentence and paste it into a Claude Code chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Restart Claude Code, then type /hull or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.claude/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Claude Code, then type /hull or ask for a matching task and Claude picks it up
ChatGPT desktop app
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Option 1Let ChatGPT install it
Open Codex in the ChatGPT desktop app and paste this sentence into the chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Option 2Put the folder there yourself
Put the hull folder at ~/.agents/skills/hull
~ is your home folder ($HOME)
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
After installing
- ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
- To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
- Codex picks up newly installed skills by itself; if one does not show up, restart Codex
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
ChatGPT on the web and mobile
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Option 1Let Codex install it
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Codex, then ask for a matching task; Codex lists the skill
Option 1Let Cursor install it
Copy this sentence and paste it into a Cursor chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
In Cursor’s Agent chat, type / and pick hull
Checked against official docs Nov 12, 2026 · Source: cursor.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.cursor/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
In Cursor’s Agent chat, type / and pick hull
Option 1Let the AI install it
For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
View the original SKILL.md
The text below comes from the maker’s repo, not from PopNx MCP
5,484 characters · Open the full file on GitHub
---
name: hull
description: Write, convert, check and fix Helm charts built with the HULL library (vidispine/hull), whose Kubernetes objects are defined as values under hull.objects instead of templates. Use when a chart depends on hull, when values contain hull.objects or _HT transformations, when a HULL rendering error ("HULL failed with error [CODE]") needs fixing, or when converting an existing Helm chart or Kubernetes manifests to HULL.
---
# Working with HULL charts
A HULL chart has a single template, `templates/hull.yaml`, and defines every Kubernetes object as data in `values.yaml` under `hull.objects.<type>.<key>`. The values are validated by the JSON schema of the chart's HULL dependency. Do not write Go templates for objects.
The rules below describe HULL 1.35.5, 1.36.2, 1.37.1 and later. Older versions lack some features, for example image digests and explicit selectors; `hull_docs` with the chart's directory as `chart_dir` returns the documentation of the chart's own HULL version.
## Workflow
Use the `hull` MCP tools when they are available:
1. Before writing values, read the rules once: `hull_docs` with topic `guide`. For common tasks start from a tested recipe: `hull_docs` with topic `cookbook`.
2. Look up what is allowed instead of guessing: `hull_schema` with a values path such as `hull.objects.deployment.web.pod.containers.main`, an object type or a definition name.
3. After every change run `hull_validate` on the chart and fix every reported problem. Each problem is one line: `HULL failed with error [CODE] (@Values.<path>) <message> Fix: <hint>`. For details about a code use `hull_docs` with the code as topic.
4. Inspect the result with `hull_render`, using `kind` and `name` to select objects.
5. To convert an existing chart, render it with `helm template <release> <chart> --namespace <ns>` and pass the output to `hull_import` with the same release name and namespace. It writes a HULL chart and verifies that it renders the same objects. Then refactor the verified values into idiomatic HULL in small steps and compare the rendering after each step.
Without the MCP tools, the same is available as scripts in the HULL chart, in `files/scripts` of the dependency (unpack it with `tar -xzf charts/hull-*.tgz -C /tmp`): `python3 hull_validate.py <chart>`, `python3 hull_import.py --chart <dir> --verify <manifests>`, and the documentation in `files/doc`, starting with `agents.md` and `cookbook.md`.
## Rules that differ from Kubernetes YAML
- The instance key is the name: `hull.objects.deployment.web` renders `<release>-<chart>-web`. `staticName: true` or `hull.config.general.noObjectNamePrefixes: true` keep the key unchanged.
- Write the fields of `spec` directly below the instance key, without `spec:`. Pod based objects take the pod spec in `pod`, CronJobs in `job.pod`. Pod labels and annotations go to `pod.labels` and `pod.annotations`.
- Named arrays are dictionaries keyed by name: `containers`, `initContainers`, `volumes`, `env`, `ports`. Never add `name:` to them. `volumeMounts`, `envFrom`, Ingress `rules`, `paths`, `tls` and `webhooks` are dictionaries with free keys. Elements render in key order, use an integer `order` property where order matters.
- Images: `image: {registry, repository, tag, digest}`; a non-empty digest replaces the tag. Quote tags like `"1.10"`.
- Selectors are generated from chart, release and key. A Service without `selector` selects the pods of the workload with the same key. An explicit `selector` keeps an existing selector; the pod labels must then match it.
- References to chart objects use the key and get the name prefix: configMap/secret/PVC volumes, env and envFrom refs, Ingress backends and TLS secrets, HPA targets. Add `staticName: true` next to a name that refers to an object outside the chart. `serviceAccountName`, `imagePullSecrets` and RoleBinding names are rendered as written; use `_HT^<key>` for the full name of a chart object.
- ConfigMap and Secret data: `data.<key>.inline` or `data.<key>.path`. Secret values are plain text, HULL encodes them. Add `noTemplating: true` to content containing `{{`.
- Defaults: `_HULL_OBJECT_TYPE_DEFAULT_` instances or elements, and named `sources`.
- The `default` ServiceAccount, Role and RoleBinding: since HULL 1.37 they only exist with `hull.config.general.createDefaultRbacTriplet: true`. Up to 1.36 they are rendered for every release and pods without `serviceAccountName` get the `default` ServiceAccount; set `enabled: false` on them to leave them out.
- Kinds without a HULL object type are `generic` objects with `apiVersion`, `kind` and their fields.
## Transformations
Strings starting with these prefixes are computed:
| Prefix | Result |
| ------ | ------ |
| `_HT*hull.config.specific.x` | the value at the path below `.Values` |
| `_HT**Release.Name` | the same from the root context |
| `_HT!{{ ... }}` | a Go template result; `(index . "$")` is the root context |
| `_HT?<condition>` | a boolean, for `enabled` |
| `_HT^<key>` | the full name of a chart object |
| `_HT&<key>` | the generated selector labels of a key |
Keep shared values in `hull.config.specific` and reference them with `_HT*`. Write lists and dictionaries returned by `_HT!` in flow style, with embedded references inside `{{ }}`: `_HT![ {{ _HT*hull.config.specific.host }} ]`. Transformations are not applied to single list elements: a transformation as first element replaces the whole list, later elements stay literal.
Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 295
- Maker
- vidispine
- License
- Apache-2.0
- Last code change
- Nov 2, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 1
- Topics
- ai, dry, helm, helm-chart, helm-charts, helm-deployment, helm-interface, helm-plugin, helm-plugins, helm-wrapper, helm3, json-schema
- Repo
- vidispine/hull