Create Agent Skill
oocx/tfplan2md
Create a new Agent Skill following project standards and templates.
A skill your agent uses when you need to deploy HyperShift clusters on bare metal, edge environments, or disconnected infrastructures using pre-provisioned agents
$ npx skills add openshift-eng/ai-helpers --skill hcp-create-agent -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install openshift-eng/ai-helpers hcp-create-agent --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/hcp/skills/hcp-create-agent .claude/skills/hcp-create-agent && rm -rf skills-srcUse ~/.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/
Install the "hcp-create-agent" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/hcp/skills/hcp-create-agent into .claude/skills/hcp-create-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hcp-create-agent", 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 install https://github.com/openshift-eng/ai-helpers/tree/main/plugins/hcp/skills/hcp-create-agentType 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.
$ npx skills add openshift-eng/ai-helpers --skill hcp-create-agent -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install openshift-eng/ai-helpers hcp-create-agent --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/hcp/skills/hcp-create-agent .agents/skills/hcp-create-agent && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "hcp-create-agent" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/hcp/skills/hcp-create-agent into .agents/skills/hcp-create-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hcp-create-agent", 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.
$ npx skills add openshift-eng/ai-helpers --skill hcp-create-agent -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install openshift-eng/ai-helpers hcp-create-agent --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/hcp/skills/hcp-create-agent .cursor/skills/hcp-create-agent && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "hcp-create-agent" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/hcp/skills/hcp-create-agent into .cursor/skills/hcp-create-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hcp-create-agent", 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 https://github.com/openshift-eng/ai-helpers.git --path plugins/hcp/skills/hcp-create-agent--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add openshift-eng/ai-helpers --skill hcp-create-agent -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install openshift-eng/ai-helpers hcp-create-agent --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/hcp/skills/hcp-create-agent .gemini/skills/hcp-create-agent && rm -rf skills-srcUse ~/.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/
Install the "hcp-create-agent" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/hcp/skills/hcp-create-agent into .gemini/skills/hcp-create-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hcp-create-agent", 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.
$ gh skill install openshift-eng/ai-helpers hcp-create-agentInstalls 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).
$ npx skills add openshift-eng/ai-helpers --skill hcp-create-agent -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/hcp/skills/hcp-create-agent .github/skills/hcp-create-agent && rm -rf skills-srcUse ~/.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/
Install the "hcp-create-agent" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/hcp/skills/hcp-create-agent into .github/skills/hcp-create-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hcp-create-agent", 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.
$ npx skills add openshift-eng/ai-helpers --skill hcp-create-agent -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install openshift-eng/ai-helpers hcp-create-agent --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/hcp/skills/hcp-create-agent .opencode/skills/hcp-create-agent && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "hcp-create-agent" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/hcp/skills/hcp-create-agent into .opencode/skills/hcp-create-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hcp-create-agent", 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.
hcp-create-agentA skill your agent uses when you need to deploy HyperShift clusters on bare metal, edge environments, or disconnected infrastructures using pre-provisioned agents
Hcp Create Agent is an agent skill from openshift-eng/ai-helpers. Use this skill when you need to deploy HyperShift clusters on bare metal, edge environments, or disconnected infrastructures using pre-provisioned agents
Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Building AI agents. The repository describes itself as: Developer productivity tools for Claude Code & other AI assistants. The licence is Apache-2.0.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit a627176. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
kubectlFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
console.redhat.comamd64.ocp.releases.ci.openshift.orgFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Hcp Create Agent loads about 3.7k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 670 words of instructions outside code blocks.
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.
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.
The full file from openshift-eng/ai-helpers at commit a627176, republished under its Apache-2.0 licence (© openshift-eng). 670 words, ~3,690 tokens.
.claude/skills/hcp-create-agent/SKILL.md (or your agent's skills folder).This skill provides implementation guidance for creating HyperShift clusters using the Agent provider, which is designed for bare metal and edge deployments where pre-provisioned agents are available.
This skill is automatically invoked by the /hcp:generate agent command to guide the Agent provider cluster creation process.
The Agent provider:
Parse the natural language description for Agent-specific requirements:
Environment Type Detection:
Resource Indicators:
Special Requirements:
Required Parameters:
--agent-namespace: Namespace where agents are located--pull-secret: Path to pull secret file--release-image: OpenShift release image--base-domain: Base domain for the cluster (prompt user if not in description)Smart Defaults by Environment:
Edge Environment:
--control-plane-availability-policy SingleReplica
--node-pool-replicas 1
--arch amd64 # or arm64 if specifiedBare Metal Environment:
--control-plane-availability-policy HighlyAvailable
--node-pool-replicas 3
--auto-repair trueDisconnected Environment:
--render # Always render for review
--image-content-sources /path/to/image-content-sources.yaml
--additional-trust-bundle /path/to/ca-bundle.pemRequired Information Collection:
Cluster Name
🔹 **Cluster Name**: What would you like to name your cluster?
- Must be DNS-compatible (lowercase, hyphens allowed)
- Will be used for resource naming
- Example: edge-lab-01, production-clusterAgent Namespace
🔹 **Agent Namespace**: In which namespace are your agents located?
- This should be the namespace where you registered your agents
- Example: default, agent-system, cluster-agents
- [Press Enter for default: default]Pull Secret
🔹 **Pull Secret**: Path to your OpenShift pull secret file?
- Required for accessing OpenShift container images
- Download from: https://console.redhat.com/openshift/install/pull-secret
- Example: /home/user/pull-secret.jsonBase Domain (if not specified in description)
🔹 **Base Domain**: What base domain should be used for cluster DNS?
- This will be used for cluster API and application routes
- Example: example.com, lab.internal, edge.localOpenShift Version
🔹 **OpenShift Version**: Which OpenShift version do you want to use?
📋 **Check supported versions**: https://amd64.ocp.releases.ci.openshift.org/
- Enter release image URL: quay.io/openshift-release-dev/ocp-release:X.Y.Z-multi
- [Press Enter for default: quay.io/openshift-release-dev/ocp-release:4.18.0-multi]Optional Configuration (based on description analysis):
Architecture (if detected)
🔹 **Architecture**: Detected ARM architecture mention. Confirm architecture:
- amd64 (x86_64)
- arm64 (aarch64)
- [Press Enter for default: amd64]FIPS Mode (if compliance mentioned)
🔹 **FIPS Mode**: Enable FIPS mode for compliance?
- Required for certain regulatory environments
- May impact performance
- [yes/no] [Press Enter for default: no]If disconnected/airgapped environment is detected:
Additional Required Information:
Mirror Registry
🔹 **Mirror Registry**: What is your mirror registry domain?
- This registry should contain mirrored OpenShift images
- Example: registry.example.com:5000Image Content Sources
🔹 **Image Content Sources**: Path to image content sources file?
- Required for mapping official images to mirror registry
- Example: /path/to/image-content-sources.yamlAdditional Trust Bundle (optional)
🔹 **Additional Trust Bundle**: Path to custom CA bundle? (Optional)
- Required if mirror registry uses custom certificates
- Example: /path/to/ca-bundle.pem
- [Press Enter to skip]Always Use --render for Disconnected:
--render flag to generate manifests for reviewProvide Agent Check Commands:
Before creating the cluster, verify your agents are available:
Check agents in namespace:
kubectl get agents -n <agent-namespace>
Verify agent status:
kubectl describe agents -n <agent-namespace>
Ensure agents are:
- In "Available" state
- Not bound to other clusters
- Meet minimum resource requirementsBasic Agent Cluster Command:
hypershift create cluster agent \
--name <cluster-name> \
--namespace <cluster-name>-ns \
--agent-namespace <agent-namespace> \
--pull-secret <pull-secret-path> \
--release-image <release-image> \
--base-domain <base-domain>With Environment-Specific Flags:
Edge/Minimal Configuration:
hypershift create cluster agent \
--name edge-cluster \
--namespace edge-cluster-ns \
--agent-namespace default \
--pull-secret /path/to/pull-secret.json \
--release-image quay.io/openshift-release-dev/ocp-release:4.18.0-multi \
--base-domain edge.local \
--control-plane-availability-policy SingleReplica \
--node-pool-replicas 1Production/HA Configuration:
hypershift create cluster agent \
--name production-cluster \
--namespace production-cluster-ns \
--agent-namespace agent-system \
--pull-secret /path/to/pull-secret.json \
--release-image quay.io/openshift-release-dev/ocp-release:4.18.0-multi \
--base-domain example.com \
--control-plane-availability-policy HighlyAvailable \
--node-pool-replicas 3 \
--auto-repairDisconnected Configuration:
hypershift create cluster agent \
--name secure-cluster \
--namespace secure-cluster-ns \
--agent-namespace agent-system \
--pull-secret /path/to/pull-secret.json \
--release-image quay.io/openshift-release-dev/ocp-release:4.18.0-multi \
--base-domain internal.example.com \
--image-content-sources /path/to/image-content-sources.yaml \
--additional-trust-bundle /path/to/ca-bundle.pem \
--renderFIPS-Enabled Configuration:
hypershift create cluster agent \
--name compliance-cluster \
--namespace compliance-cluster-ns \
--agent-namespace agent-system \
--pull-secret /path/to/pull-secret.json \
--release-image quay.io/openshift-release-dev/ocp-release:4.18.0-multi \
--base-domain secure.example.com \
--fipsFor Disconnected Environments:
Provide additional configuration needed after cluster creation:
## Post-Creation Configuration (Disconnected)
After running the command above (with --render), you'll need to modify the generated manifests:
1. **Add ImageContentSources to HostedCluster:**
```yaml
spec:
imageContentSources:
- source: quay.io/openshift-release-dev/ocp-v4.0-art-dev
mirrors:
- registry.example.com:5000/openshift/release
- source: quay.io/openshift-release-dev/ocp-release
mirrors:
- registry.example.com:5000/openshift/release-images
- source: registry.redhat.io/multicluster-engine
mirrors:
- registry.example.com:5000/openshift/multicluster-engine
```
2. **Disable Default OperatorHub Sources:**
```yaml
spec:
configuration:
operatorhub:
disableAllDefaultSources: true
```
3. **Apply the manifests:**
```bash
kubectl apply -f <rendered-manifest-files>
```For All Environments:
## Next Steps
1. **Verify agents are available:**
kubectl get agents -n <agent-namespace>
2. **Monitor cluster creation:**
kubectl get hostedcluster -n <cluster-namespace>
kubectl get nodepool -n <cluster-namespace>
3. **Check agent assignment:**
kubectl get agents -n <agent-namespace> -o wide
4. **Access cluster when ready:**
hypershift create kubeconfig --name <cluster-name> --namespace <cluster-namespace>Scenario: No agents found in specified namespace.
Action:
No agents found in namespace "default".
Please ensure:
1. Agents are registered and visible via `kubectl get agents -A`
2. Agents are in "Available" state
3. Correct namespace specified
Check agents:
kubectl get agents -A
Register new agents using the agent-based installer or manual process.Scenario: Not enough agents for requested replicas.
Action:
Only 2 agents available, but you requested 3 node replicas.
Options:
1. Reduce node-pool-replicas to 2
2. Register additional agents
3. Use SingleReplica control plane (reduces total requirement)
Would you like me to adjust the configuration?Scenario: Agents are already assigned to another cluster.
Action:
Some agents are already bound to other clusters.
Available agents: 1
Bound agents: 2
Check agent status:
kubectl describe agents -n <namespace>
Free up agents by deleting unused clusters or register new agents.Scenario: Can't access release images in disconnected environment.
Action:
Release image access failed. In disconnected environments:
1. Ensure mirror registry contains required images
2. Verify image-content-sources file mapping
3. Check custom CA bundle configuration
4. Validate network connectivity to mirror registry
Mirror required images using:
oc adm release mirror --to <mirror-registry>❌ Assuming cloud automation
"Create cluster with autoscaling"✅ Agent provider requires manual agent provisioning
❌ Insufficient agent planning
Not checking agent availability before cluster creation✅ Always verify sufficient agents are available
❌ Ignoring disconnected requirements
Using public image references in airgapped environment✅ Configure image content sources and mirror registry to map all public image references to the local mirror
❌ Inadequate resource planning
Using minimal agents for production workloads✅ Size agents appropriately for expected workloads
Input: "small edge cluster for remote office monitoring"
Analysis:
- Environment: Edge
- Scale: Minimal
- Use case: Monitoring
Generated Command:
hypershift create cluster agent \
--name edge-monitoring \
--namespace edge-monitoring-ns \
--agent-namespace default \
--pull-secret /path/to/pull-secret.json \
--release-image quay.io/openshift-release-dev/ocp-release:4.18.0-multi \
--base-domain edge.local \
--control-plane-availability-policy SingleReplica \
--node-pool-replicas 1Input: "airgapped production cluster for financial data processing"
Analysis:
- Environment: Disconnected/Secure
- Scale: Production
- Use case: Financial (compliance required)
Generated Command:
hypershift create cluster agent \
--name financial-prod \
--namespace financial-prod-ns \
--agent-namespace secure-agents \
--pull-secret /path/to/pull-secret.json \
--release-image quay.io/openshift-release-dev/ocp-release:4.18.0-multi \
--base-domain secure.financial.internal \
--image-content-sources /path/to/image-content-sources.yaml \
--additional-trust-bundle /path/to/ca-bundle.pem \
--fips \
--render© openshift-eng, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in plugins/hcp/skills/hcp-create-agent of openshift-eng/ai-helpers.
Open the folder on GitHubat commit a627176
Hcp Create Agent 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Hcp Create Agent this skillopenshift-eng/ai-helpers | 120 | — | ~3.7k | Automated safety check: Pass | Apache-2.0 | |
| Create Agent Skilloocx/tfplan2md | 174 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Apex Agent Authoringjonathan-vella/apex | 217 | — | ~1.8k | Automated safety check: Pass | MIT | |
| New Resource WorkflowGoogleCloudPlatform/magic-modules | 974 | — | ~512 | Automated safety check: Pass | Custom licence | |
| Autogpt AgentsOrchestra-Research/AI-Research-SKILLs | 13k | 3 repos | ~2.3k | Automated safety check: Notes | MIT | |
| Agent BuildershareAI-lab/learn-claude-code | 78k | 6 repos | ~1.2k | Automated safety check: Pass | MIT |
oocx/tfplan2md
Create a new Agent Skill following project standards and templates.
jonathan-vella/apex
WORKFLOW SKILL — Creates, restructures, and audits GitHub Copilot .agent.md and .prompt.md files with correct frontmatter, handoffs, model policy, context budgets, and validation.
GoogleCloudPlatform/magic-modules
Workflow specifically for creating a new resource, supporting both autogen and manual generation.
Orchestra-Research/AI-Research-SKILLs
Autonomous AI agent platform for building and deploying continuous agents.
shareAI-lab/learn-claude-code
Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.
microsoft/skills
Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes.
openshift-eng/ai-helpers
Find and independently validate actionable reliability defects across OpenShift release jobs and presubmits, then export portable issue handoffs.
openshift-eng/ai-helpers
Fetch and address all PR review comments — categorize by priority, make code changes, post replies, and push.
openshift-eng/ai-helpers
Categorize Jira issues into Red Hat Sankey Activity Type categories using MCP Jira tools.
openshift-eng/ai-helpers
Decide whether a GitHub PR has unanswered authorized review comments or new required CI failures worth a follow-up agent.
openshift-eng/ai-helpers
Analyze OpenShift must-gather diagnostic data including cluster operators, pods, nodes, and network components.
openshift-eng/ai-helpers
Schema for the autodl JSON data file produced by payload-analysis for database ingestion — you must use this skill whenever generating the autodl JSON file
Categories
A skill your agent uses when you need to deploy HyperShift clusters on bare metal, edge environments, or disconnected infrastructures using pre-provisioned agents. Hcp Create Agent is an agent skill from openshift-eng/ai-helpers.
Hcp Create Agent fits situations like: you need to deploy HyperShift clusters on bare metal; edge environments; disconnected infrastructures using pre-provisioned agents.
Run `npx skills add openshift-eng/ai-helpers --skill hcp-create-agent -a claude-code`. Or copy the skill folder (plugins/hcp/skills/hcp-create-agent in openshift-eng/ai-helpers) into .claude/skills/hcp-create-agent in your project. Claude Code loads it when a task matches its description.
Run `npx skills add openshift-eng/ai-helpers --skill hcp-create-agent -a codex`. Or copy the skill folder (plugins/hcp/skills/hcp-create-agent in openshift-eng/ai-helpers) into .agents/skills/hcp-create-agent in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openshift-eng/ai-helpers --skill hcp-create-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hcp-create-agent, .gemini/skills/hcp-create-agent, .github/skills/hcp-create-agent and .opencode/skills/hcp-create-agent in your project.
Going by SKILL.md and its folder, Hcp Create Agent needs the command-line tools its instructions call (kubectl).
SKILL.md names 2 domains. In commands or code: console.redhat.com and amd64.ocp.releases.ci.openshift.org; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
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.
Hcp Create Agent is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Hcp Create Agent: Create Agent Skill (oocx/tfplan2md, 174 stars), Apex Agent Authoring (jonathan-vella/apex, 217 stars), New Resource Workflow (GoogleCloudPlatform/magic-modules, 974 stars) and Autogpt Agents (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
openshift-eng (a GitHub organization) maintains it in openshift-eng/ai-helpers, which has 120 GitHub stars. The repository holds 118 skills in this directory. The repository was last updated on October 6, 2026.
Source: openshift-eng/ai-helpers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.