Agent skill

KubeSphere Fluid Management

Installs and manages the Fluid caching extension on KubeSphere: InstallPlan and Dataset manifests, Alluxio, JuiceFS or Thin runtimes, DataLoad cache warming and troubleshooting.

Custom licenceAuto-check passedDevOps & Cloud

Install KubeSphere Fluid Management

skills CLI

$ npx skills add kubesphere/kubesphere --skill kubesphere-fluid -a claude-code

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

GitHub CLI

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

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 kubesphere/kubesphere --skill kubesphere-fluid -a codex

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

GitHub CLI

$ gh skill install kubesphere/kubesphere kubesphere-fluid --agent codex

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

Manual copy

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

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

GitHub CLI

$ gh skill install kubesphere/kubesphere kubesphere-fluid --agent cursor

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

Manual copy

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

--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 kubesphere/kubesphere --skill kubesphere-fluid -a gemini-cli

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

GitHub CLI

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

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 kubesphere/kubesphere --skill kubesphere-fluid -a github-copilot

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

Manual copy

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

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

Manual copy

$ git clone --depth 1 https://github.com/kubesphere/kubesphere.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/kubesphere-fluid .opencode/skills/kubesphere-fluid && 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 "kubesphere-fluid" agent skill from https://github.com/kubesphere/kubesphere/tree/master/skills/kubesphere-fluid into .opencode/skills/kubesphere-fluid/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kubesphere-fluid", 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: kubesphere-fluid
GitHub stars: 17k
Token cost: ~5.2k tokens
SKILL.md length: 1,219 words
Files: 8
Skills in repo: 32
Repo updated: Jul 15, 2026
First seen: Oct 7, 2026
Licence: Custom licence

At a glance

Installs and manages the Fluid caching extension on KubeSphere: InstallPlan and Dataset manifests, Alluxio, JuiceFS or Thin runtimes, DataLoad cache warming and troubleshooting.

Works in 9 steps: Pre-check → InstallPlan Template → InstallPlan or extension failed → …
Installing or enabling the Fluid extension on a KubeSphere cluster
SKILL.md covers Response Rules, CRITICAL: Parameter Handling, CRITICAL: Operation Scope and Version Mapping Discovery, plus 9 more sections
Calls kubectl, jq and curl; needs KS_PASSWORD

What it does

The whole Fluid lifecycle inside KubeSphere is covered here. The agent installs or upgrades the Fluid extension through an InstallPlan, queries its status, CRDs, pods and logs, writes Dataset manifests with mount settings, and writes AlluxioRuntime, JuiceFSRuntime or ThinRuntime manifests for caching. It can also run a DataLoad to warm the cache, scale runtime replicas and uninstall the extension.

Strict rules govern the output. Names, namespaces, mount points, replicas and quotas must be taken exactly from what you say and never guessed. The agent checks the extension name and version before producing an InstallPlan, sets upgradeStrategy to Manual by default, and checks the installed API versions with kubectl api-resources. Advanced topics such as DataBackup or GooseFS are treated as follow-up work, and uninstall requests come with a warning that deleting CRDs can remove application configuration. Example YAML files for each manifest type sit in an examples folder.

When your agent uses it

Installing or enabling the Fluid extension on a KubeSphere cluster
Creating a Dataset that mounts an S3 bucket, OSS bucket or PVC
Warming a cache with a DataLoad before a training or analytics job
Troubleshooting Fluid pods, CRDs or mount failures

Example prompts

“Install Fluid on my KubeSphere cluster and show me the InstallPlan first.”
“Create a Dataset named spark-data in namespace demo that mounts s3://mybucket/spark-data.”
“Generate an AlluxioRuntime with 3 replicas and a 5Gi quota for the spark-data dataset.”
“Run a DataLoad to warm the cache for the spark-data dataset.”

Requirements

A KubeSphere cluster with kubectl access
The Fluid extension available in KubeSphere

Workflow steps

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

Pre-check
InstallPlan Template
InstallPlan or extension failed
Fluid Pods are unhealthy
CRD missing or not established
Runtime Not Ready
Mount Failed
DataLoad Stuck
Scaling Slow

What it can do on your machine

Read from SKILL.md and the folder at commit 04a29b5. 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:
- kubectl
- jq
- curl
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use kubectl and curl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- KS_PASSWORD
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

KubeSphere Fluid Management loads about 5.2k tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 1,219 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~78
When it runs · the whole SKILL.md, loaded when a task matches: ~5.2k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,219 words (~5,151 tokens).

“Use this skill for the full Fluid lifecycle in KubeSphere:”

— opening of SKILL.md by kubesphere, Custom licence

name: kubesphere-fluid

Outline of SKILL.md

KubeSphere Fluid Management
Response Rules
CRITICAL: Parameter Handling
CRITICAL: Operation Scope
Version Mapping Discovery
Discovery Commands
Option 1: Using KubeSphere API (curl)
CRUD Operations via KubeSphere API
Option 2: Using kubectl (Direct Cluster Access)
Option 3: Using ksctl CLI
When to Use Which Approach
Example Files
Install Fluid in KubeSphere
1. Pre-check
2. InstallPlan Template
Manage Dataset
Dataset Template
Manage AlluxioRuntime
AlluxioRuntime Template (Standalone)
Key fields:
Scale Runtime
Manage JuiceFSRuntime
JuiceFSRuntime Template (Standalone)
Key fields:
DataLoad (Cache Warming)
DataLoad Template - COMPLETE VERSION
Uninstall Fluid
Uninstall Pre-check
Default uninstall path:
Troubleshooting Playbook

Read the full SKILL.md on GitHub

Files

SKILL.md and 7 other files in skills/kubesphere-fluid of kubesphere/kubesphere.

SKILL.md
evals/evals.json
examples/alluxioruntime.yaml
examples/dataload.yaml
examples/dataset.yaml
examples/installplan.yaml
examples/juicefs.yaml
examples/thinruntime.yaml

Open the folder on GitHubat commit 04a29b5

Compare with similar skills

KubeSphere Fluid Management 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.

KubeSphere Fluid Management compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
KubeSphere Fluid Management this skillkubesphere/kubesphere	17k	—	~5.2k	Automated safety check: Pass	Custom licence	2 mo ago
Provider Bug Reviewmondoohq/mql	412	—	~2.9k	Automated safety check: Pass	Custom licence	today
Create Pipeline V1harness/harness-skills	115	—	~3.1k	Automated safety check: Pass	Apache-2.0	2 days ago
Kubeshark Installerkubeshark/kubeshark	12k	—	~3.6k	Automated safety check: Notes	Apache-2.0	yesterday
Sim Helmsimstudioai/sim	30k	—	~2.2k	Automated safety check: Pass	Apache-2.0	today
Helm Chart ScaffoldingCybereason-Public/owLSM	280	13 repos	~381	Automated safety check: Pass	GPL-2.0	today

Similar skills

Provider Bug Review
mondoohq/mql
Deep static code review of an mql provider for logic errors, nil-handling bugs, pagination truncation, caching/id collisions, and other defects that silently give users wrong data.
412 GitHub stars~2.9k tokensUpdated today
DevOps & CloudAuto-check passed
Create Pipeline V1
harness/harness-skills
Generate Harness v1 simplified Pipeline YAML using the new concise syntax with flat structure, ${{ }} expressions, script field, and action steps.
115 GitHub stars~3.1k tokensUpdated 2 days ago
DevOps & CloudAuto-check passed
Kubeshark Installer
kubeshark/kubeshark
Installs and configures Kubeshark on a Kubernetes cluster, choosing between the quick CLI path and a Helm install with custom values.
12k GitHub stars~3.6k tokensUpdated yesterday
DevOps & CloudAuto-check: notes
Sim Helm
simstudioai/sim
Install, upgrade, and operate the Sim Helm chart on Kubernetes.
30k GitHub stars~2.2k tokensUpdated today
DevOps & CloudAuto-check passed
Helm Chart Scaffolding
Cybereason-Public/owLSM
Comprehensive guidance for creating, organizing, and managing Helm charts for packaging and deploying Kubernetes applications.
280 GitHub starsUsed in 13 repos~381 tokens
DevOps & CloudAuto-check passed
Kubeshark KFL2 Filter Reference
kubeshark/kubeshark
Syntax reference for KFL2, the CEL-based display filter language used to search Kubernetes network traffic captured by Kubeshark, loaded before any filter is written.
12k GitHub stars~3.6k tokensUpdated yesterday
DevOps & CloudAuto-check passed

Questions about KubeSphere Fluid Management

What does KubeSphere Fluid Management do?

Installs and manages the Fluid caching extension on KubeSphere: InstallPlan and Dataset manifests, Alluxio, JuiceFS or Thin runtimes, DataLoad cache warming and troubleshooting. The whole Fluid lifecycle inside KubeSphere is covered here. The agent installs or upgrades the Fluid extension through an InstallPlan, queries its status, CRDs, pods and logs, writes Dataset manifests with mount settings, and writes AlluxioRuntime, JuiceFSRuntime or ThinRuntime manifests for caching.

When should I use KubeSphere Fluid Management?

KubeSphere Fluid Management fits situations like: installing or enabling the Fluid extension on a KubeSphere cluster; creating a Dataset that mounts an S3 bucket, OSS bucket or PVC; warming a cache with a DataLoad before a training or analytics job; troubleshooting Fluid pods, CRDs or mount failures.

How do I install KubeSphere Fluid Management in Claude Code?

Run `npx skills add kubesphere/kubesphere --skill kubesphere-fluid -a claude-code`. Or copy the skill folder (skills/kubesphere-fluid in kubesphere/kubesphere) into .claude/skills/kubesphere-fluid in your project. Claude Code loads it when a task matches its description.

How do I install KubeSphere Fluid Management in Codex?

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

Can I use KubeSphere Fluid Management 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 kubesphere/kubesphere --skill kubesphere-fluid -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kubesphere-fluid, .gemini/skills/kubesphere-fluid, .github/skills/kubesphere-fluid and .opencode/skills/kubesphere-fluid in your project.

What does KubeSphere Fluid Management need to run?

Going by SKILL.md and its folder, KubeSphere Fluid Management needs the command-line tools its instructions call (kubectl, jq and curl) and credentials named KS_PASSWORD. Our summary lists: A KubeSphere cluster with kubectl access; The Fluid extension available in KubeSphere.

Does KubeSphere Fluid Management access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is KubeSphere Fluid Management 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 KubeSphere Fluid Management use?

KubeSphere Fluid Management has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does KubeSphere Fluid Management use?

About 5.2k tokens (SKILL.md is roughly 21k 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 KubeSphere Fluid Management?

Skills that share tags, products or a category with KubeSphere Fluid Management: Provider Bug Review (mondoohq/mql, 412 stars), Create Pipeline V1 (harness/harness-skills, 115 stars), Kubeshark Installer (kubeshark/kubeshark, 12k stars) and Sim Helm (simstudioai/sim, 30k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains KubeSphere Fluid Management?

kubesphere (a GitHub organization) maintains it in kubesphere/kubesphere, which has 17,057 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on July 15, 2026.

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

KubeSphere Fluid Management

Install KubeSphere Fluid Management

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Files

Compare with similar skills

Similar skills

Provider Bug Review

Create Pipeline V1

Kubeshark Installer

Sim Helm

Helm Chart Scaffolding

Kubeshark KFL2 Filter Reference

More from kubesphere/kubesphere

KubeSphere Multi-Tenant Management

KubeSphere ServiceMesh Manager

KubeEye Cluster Inspection

KubeSphere NodeGroup Operations

WizTelemetry Platform Service

Frontend Forge Extension Operations

Questions about KubeSphere Fluid Management

Install KubeSphere Fluid Management

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Files

Compare with similar skills

Similar skills

More from kubesphere/kubesphere

Related

Questions about KubeSphere Fluid Management