Kubernetes Helm chart development with values.yaml, templates, and subchart patterns. Triggers on helm, chart, kubernetes, values.yaml.
Builds Kubernetes Helm charts with Bitnami-style values structure, template helpers, and subchart patterns. Triggers on helm, chart, kubernetes, or values.yaml keywords.
/plugin marketplace add settlemint/agent-marketplace/plugin install devtools@settlemintThis skill inherits all available tools. When active, it can use any tool Claude has access to.
<mcp_first> CRITICAL: Use OctoCode to research external chart capabilities before implementing workarounds.
MCPSearch({ query: "select:mcp__plugin_devtools_octocode__githubSearchCode" })
// Research external chart values
mcp__octocode__githubGetFileContent({
owner: "bitnami",
repo: "charts",
path: "bitnami/postgresql/values.yaml",
matchString: "primary",
mainResearchGoal: "Understand Bitnami chart patterns",
researchGoal: "Find PostgreSQL configuration options",
reasoning: "Need to configure external chart correctly"
})
</mcp_first>
<quick_start> Chart structure:
my-chart/
├── Chart.yaml # Chart metadata
├── values.yaml # Default configuration
├── templates/
│ ├── _helpers.tpl # Template helpers
│ ├── deployment.yaml
│ ├── service.yaml
│ └── configmap.yaml
└── charts/ # Subcharts (optional)
Values annotation (required for readme-generator):
# -- (string) Image repository
image:
# -- (string) Image registry
registry: docker.io
# -- (string) Image name
repository: my-app
# -- (string) Image tag
tag: latest
# -- (int) Number of replicas
replicaCount: 1
# -- (bool) Enable debug mode
debug: false
Template helper:
{{/* Generate labels */}}
{{- define "mychart.labels" -}}
app.kubernetes.io/name: {{ include "mychart.name" . }}
app.kubernetes.io/instance: {{ .Release.Name }}
{{- end }}
</quick_start>
<constraints> **Banned:** - Hardcoded values in templates — use `.Values` - Changing label selectors after deployment - Secrets in values.yaml — use `existingSecret` pattern - Missing `# -- (type)` annotations - Template files over 200 linesRequired:
# -- (type) description annotationapp.kubernetes.io/*)existingSecret for secretsNaming: Charts=kebab-case, Templates=<resource>.yaml, Values=camelCase
</constraints>
<external_charts> Always research external chart capabilities before workarounds:
values.yamlmcp__octocode__githubGetFileContent({
owner: "grafana",
repo: "helm-charts",
path: "charts/grafana/values.yaml",
matchString: "rbac",
mainResearchGoal: "Find Grafana RBAC options",
researchGoal: "Check if namespace-scoped RBAC is supported",
reasoning: "Avoid custom workaround if chart supports it natively"
})
</external_charts>
<commands> ```bash helm lint ./my-chart # Lint chart helm template my-chart ./my-chart --debug # Render templates helm dependency update ./my-chart # Update dependencies helm install my-release ./my-chart # Install ``` </commands><success_criteria>
# -- (type) annotations.Values references (no hardcoding)existingSecret pattern for secretshelm lint passes with 0 warningsThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.