Back to Skills

Helm Chart Builder

Helm chart development agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw — chart scaffolding, values design, template patterns, dependency management, security hardening, and chart testing. Use when: user wants to create or improve Helm charts, design v…

securitytestingagent
By alirezarezvani
19k2.7kUpdated 3 days agoPythonMIT

Skill Content

# Helm Chart Builder

> Production-grade Helm charts. Sensible defaults. Secure by design. No cargo-culting.

Opinionated Helm workflow that turns ad-hoc Kubernetes manifests into maintainable, testable, reusable charts. Covers chart structure, values design, template patterns, dependency management, and security hardening.

Not a Helm tutorial — a set of concrete decisions about how to build charts that operators trust and developers don't fight.

---

## Slash Commands

| Command | What it does |
|---------|-------------|
| `/helm:create` | Scaffold a production-ready Helm chart with best-practice structure |
| `/helm:review` | Analyze an existing chart for issues — missing labels, hardcoded values, template anti-patterns |
| `/helm:security` | Audit chart for security issues — RBAC, network policies, pod security, secrets handling |

---

## When This Skill Activates

Recognize these patterns from the user:

- "Create a Helm chart for this service"
- "Review my Helm chart"
- "Is this chart secure?"
- "Design a values.yaml"
- "Add a subchart dependency"
- "Set up helm tests"
- "Helm best practices for [workload type]"
- Any request involving: Helm chart, values.yaml, Chart.yaml, templates, helpers, _helpers.tpl, subcharts, helm lint, helm test

If the user has a Helm chart or wants to package Kubernetes resources → this skill applies.

---

## Workflow

### `/helm:create` — Chart Scaffolding

1. **Identify workload type**
   - Web service (Deployment + Service + Ingress)
   - Worker (Deployment, no Service)
   - CronJob (CronJob + ServiceAccount)
   - Stateful service (StatefulSet + PVC + Headless Service)
   - Library chart (no templates, only helpers)

2. **Scaffold chart structure**

   ```
   mychart/
   ├── Chart.yaml              # Chart metadata and dependencies
   ├── values.yaml             # Default configuration
   ├── values.schema.json      # Optional: JSON Schema for values validation
   ├── .helmignore             # Files to exclude from packaging
   ├── templates/
   │   ├── _helpers.tpl        # Named templates and helper functions
   │   ├── deployment.yaml     # Workload resource
   │   ├── service.yaml        # Service exposure
   │   ├── ingress.yaml        # Ingress (if applicable)
   │   ├── serviceaccount.yaml # ServiceAccount
   │   ├── hpa.yaml            # HorizontalPodAutoscaler
   │   ├── pdb.yaml            # PodDisruptionBudget
   │   ├── networkpolicy.yaml  # NetworkPolicy
   │   ├── configmap.yaml      # ConfigMap (if needed)
   │   ├── secret.yaml         # Secret (if needed)
   │   ├── NOTES.txt           # Post-install usage instructions
   │   └── tests/
   │       └── test-connection.yaml
   └── charts/                 # Subcharts (dependencies)
   ```

3. **Apply Chart.yaml best practices**

   ```
   METADATA
   ├── apiVersion: v2 (Helm 3 only — never v1)
   ├── name: matches directory name exactly
   ├── version: semver (chart version, not app version)
   ├── appVersion: application version string
   ├── description: one-line summary of what the chart deploys
   └── type: application (or library for shared helpers)

   DEPENDENCIES
   ├── Pin dependency versions with ~X.Y.Z (patch-level float)
   ├── Use condition field to make subcharts optional
   ├── Use alias for multiple instances of same subchart
   └── Run helm dependency update after changes
   ```

4. **Generate values.yaml with documentation**
   - Every value has an inline comment explaining purpose and type
   - Sensible defaults that work for development
   - Override-friendly structure (flat where possible, nested only when logical)
   - No hardcoded cluster-specific values (image registry, domain, storage class)

5. **Validate**
   ```bash
   python3 scripts/chart_analyzer.py mychart/
   helm lint mychart/
   helm template mychart/ --debug
   ```

### `/helm:review` — Chart Analysis

1. **Check chart structure**

   | Check | Severity | Fix |
   |-------|----------|-----|
   | Missing _helpers.tpl | High | Create helpers for common labels and selectors |
   | No NOTES.txt | Medium | Add post-install instructions |
   | No .helmignore | Low | Create one to exclude .git, CI files, tests |
   | Missing Chart.yaml fields | Medium | Add description, appVersion, maintainers |
   | Hardcoded values in templates | High | Extract to values.yaml with defaults |

2. **Check template quality**

   | Check | Severity | Fix |
   |-------|----------|-----|
   | Missing standard labels | High | Use `app.kubernetes.io/*` labels via _helpers.tpl |
   | No resource requests/limits | Critical | Add resources section with defaults in values.yaml |
   | Hardcoded image tag | High | Use `{{ .Values.image.repository }}:{{ .Values.image.tag }}` |
   | No imagePullPolicy | Medium | Default to `IfNotPresent`, overridable |
   | Missing liveness/readiness probes | High | Add probes with configurable paths and ports |
   | No pod anti-affinity | Medium | Add preferred anti-affinity for HA |
   | Duplicate template code | Medium | Extract into named templates in _helpers.tpl |

3. **Check values.yaml quality**
   ```bash
   python3 scripts/values_validator.py mychart/values.yaml
   ```

4. **Generate review report**
   ```
   HELM CHART REVIEW — [chart name]
   Date: [timestamp]

   CRITICAL: [count]
   HIGH:     [count]
   MEDIUM:   [count]
   LOW:      [count]

   [Detailed findings with fix recommendations]
   ```

### `/helm:security` — Security Audit

1. **Pod security audit**

   | Check | Severity | Fix |
   |-------|----------|-----|
   | No securityContext | Critical | Add runAsNonRoot, readOnlyRootFilesystem |
   | Running as root | Critical | Set `runAsNonRoot: true`, `runAsUser: 1000` |
   | Writable root filesystem | High | Set `readOnlyRootFilesystem: true` + emptyDir for tmp |
   | All capabilities retained | High | Drop ALL, add only specific needed caps |
   | Privileged container | Critical | Set `privileged: false`, use specific capabilities |
   | No seccomp profile | Medium | Set `seccompProfile.type: RuntimeDefault` |
   | allowPrivilegeEscalation true | High | Set `allowPrivilegeEscalation: false` |

2. **RBAC audit**

   | Check | Severity | Fix |
   |-------|----------|-----|
   | No ServiceAccount | Medium | Create dedicated SA, don't use default |
   | automountServiceAccountToken true | Medium | Set to false unless pod needs K8s API access |
   | ClusterRole instead of Role | Medium | Use namespace-scoped Role unless cluster-wide needed |
   | Wildcard permissions | Critical | Use specific resource names and verbs |
   | No RBAC at all | Low | Acceptable if pod doesn't need K8s API access |

3. **Network and secrets audit**

   | Check | Severity | Fix |
   |-------|----------|-----|
   | No NetworkPolicy | Medium | Add default-deny ingress + explicit allow rules |
   | Secrets in values.yaml | Critical | Use external secrets operator or sealed-secrets |
   | No PodDisruptionBudget | Medium | Add PDB with minAvailable for HA workloads |
   | hostNetwork: true | High | Remove unless absolutely required (e.g., CNI plugin) |
   | hostPID or hostIPC | Critical | Never use in application charts |

4. **Generate security report**
   ```
   SECURITY AUDIT — [chart name]
   Date: [timestamp]

   CRITICAL: [count]
   HIGH:     [count]
   MEDIUM:   [count]
   LOW:      [count]

   [Detailed findings with remediation steps]
   ```

---

## Tooling

### `scripts/chart_analyzer.py`

CLI utility for static analysis of Helm chart directories.

**Features:**
- Chart structure validation (required files, directory layout)
- Template anti-pattern detection (hardcoded values, missing labels, no resource limits)
- Chart.yaml metadata checks
- Standard labels verification (app.kubernetes.io/*)
- Security baseline checks
- JSON and text output

**Usage:**
```bash
# Analyze a chart directory
python3 scripts/chart_analyzer.py mychart/

# JSON output
python3 scripts/chart_analyzer.py mychart/ --output json

# Security-focused analysis
python3 scripts/chart_analyzer.py mychart/ --security
```

### `scripts/values_validator.py`

CLI utility for validating values.yaml against best practices.

**Features:**
- Documentation coverage (inline comments)
- Type consistency checks
- Hardcoded secrets detection
- Default value quality analysis
- Structure depth analysis
- Naming convention validation
- JSON and text output

**Usage:**
```bash
# Validate values.yaml
python3 scripts/values_validator.py values.yaml

# JSON output
python3 scripts/values_validator.py values.yaml --output json

# Strict mode (fail on warnings)
python3 scripts/values_validator.py values.yaml --strict
```

---

## Template Patterns

### Pattern 1: Standard Labels (_helpers.tpl)

```yaml
{{/*
Common labels for all resources.
*/}}
{{- define "mychart.labels" -}}
helm.sh/chart: {{ include "mychart.chart" . }}
app.kubernetes.io/name: {{ include "mychart.name" . }}
app.kubernetes.io/instance: {{ .Release.Name }}
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
app.kubernetes.io/managed-by: {{ .Release.Service }}
{{- end }}

{{/*
Selector labels (subset of common labels — must be immutable).
*/}}
{{- define "mychart.selectorLabels" -}}
app.kubernetes.io/name: {{ include "mychart.name" . }}
app.kubernetes.io/instance: {{ .Release.Name }}
{{- end }}
```

### Pattern 2: Conditional Resources

```yaml
{{- if .Values.ingress.enabled -}}
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
  name: {{ include "mychart.fullname" . }}
  labels:
    {{- include "mychart.labels" . | nindent 4 }}
  {{- with .Values.ingress.annotations }}
  annotations:
    {{- toYaml . | nindent 4 }}
  {{- end }}
spec:
  {{- if .Values.ingress.tls }}
  tls:
    {{- range .Values.ingress.tls }}
    - hosts:
        {{- range .hosts }}
        - {{ . | quote }}
        {{- end }}
      secretName: {{ .secretName }}
    {{- end }}
  {{- end }}
  rules:
    {{- range .Values.ingress.hosts }}
    - host: {{ .host | quote }}
      http:
        paths:
          {{- range .paths }}
          - path: {{ .path }}
            pathType: {{ .pathType }}
            backend:
              service:
                name: {{ include "mychart.fullname" $ }}
                port:
                  number: {{ $.Values.service.port }}
          {{- end }}
    {{- end }}
{{- end }}
```

### Pattern 3: Security-Hardened Pod Spec

```yaml
spec:
  serviceAccountName: {{ include "mychart.serviceAccountName" . }}
  automountServiceAccountToken: false
  securityContext:
    runAsNonRoot: true
    runAsUser: 1000
    fsGroup: 1000
    seccompProfile:
      type: RuntimeDefault
  containers:
    - name: {{ .Chart.Name }}
      securityContext:
        allowPrivilegeEscalation: false
        readOnlyRootFilesystem: true
        capabilities:
          drop:
            - ALL
      image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
      imagePullPolicy: {{ .Values.image.pullPolicy }}
      resources:
        {{- toYaml .Values.resources | nindent 8 }}
      volumeMounts:
        - name: tmp
          mountPath: /tmp
  volumes:
    - name: tmp
      emptyDir: {}
```

---

## Values Design Principles

```
STRUCTURE
├── Flat over nested (image.tag > container.spec.image.tag)
├── Group by resource (service.*, ingress.*, resources.*)
├── Use enabled: true/false for optional resources
├── Document every key with inline YAML comments
└── Provide sensible development defaults

NAMING
├── camelCase for keys (replicaCount, not replica_count)
├── Boolean keys: use adjectives (enabled, required) not verbs
├── Nested keys: max 3 levels deep
└── Match upstream conventions (image.repository, image.tag, image.pullPolicy)

ANTI-PATTERNS
├── Hardcoded cluster URLs or domains
├── Secrets as default values
├── Empty strings where null is correct
├── Deeply nested structures (>3 levels)
├── Undocumented values
└── values.yaml that doesn't work without overrides
```

---

## Dependency Management

```
SUBCHARTS
├── Use Chart.yaml dependencies (not requirements.yaml — Helm 3)
├── Pin versions: version: ~15.x.x (patch float)
├── Use condition: to make optional: condition: postgresql.enabled
├── Use alias: for multiple instances of same chart
├── Override subchart values under subchart name key in values.yaml
└── Run helm dependency update before packaging

LIBRARY CHARTS
├── type: library in Chart.yaml — no templates directory
├── Export named templates only — no rendered resources
├── Use for shared labels, annotations, security contexts
└── Version independently from application charts
```

---

## Proactive Triggers

Flag these without being asked:

- **No _helpers.tpl** → Create one. Every chart needs standard labels and fullname helpers.
- **Hardcoded image tag in template** → Extract to values.yaml. Tags must be overridable.
- **No resource requests/limits** → Add them. Pods without limits can starve the node.
- **Running as root** → Add securityContext. No exceptions for production charts.
- **No NOTES.txt** → Create one. Users need post-install instructions.
- **Secrets in values.yaml defaults** → Remove them. Use placeholders with comments explaining how to provide secrets.
- **No liveness/readiness probes** → Add them. Kubernetes needs to know if the pod is healthy.
- **Missing app.kubernetes.io labels** → Add via _helpers.tpl. Required for proper resource tracking.

---

## Installation

### One-liner (any tool)
```bash
git clone https://github.com/alirezarezvani/claude-skills.git
cp -r claude-skills/engineering/helm-chart-builder ~/.claude/skills/
```

### Multi-tool install
```bash
./scripts/convert.sh --skill helm-chart-builder --tool codex|gemini|cursor|windsurf|openclaw
```

### OpenClaw
```bash
clawhub install cs-helm-chart-builder
```

---

## Related Skills

- **senior-devops** — Broader DevOps scope (CI/CD, IaC, monitoring). Complementary — use helm-chart-builder for chart-specific work, senior-devops for pipeline and infrastructure.
- **docker-development** — Container building. Complementary — docker-development builds the images, helm-chart-builder deploys them to Kubernetes.
- **ci-cd-pipeline-builder** — Pipeline construction. Complementary — helm-chart-builder defines the deployment artifact, ci-cd-pipeline-builder automates its delivery.
- **senior-security** — Application security. Complementary — helm-chart-builder covers Kubernetes-level security (RBAC, pod security), senior-security covers application-level threats.

How to use

  1. Copy the skill content above
  2. Create a .claude/skills directory in your project
  3. Save as .claude/skills/claude-skills-helm-chart-builder.md
  4. Use /claude-skills-helm-chart-builder in Claude Code to invoke this skill

Claude Code Skills & Plugins — Agent Skills for Every Coding Tool

345 production-ready Claude Code skills, plugins, and agent skills for 13 AI coding tools.

The most comprehensive open-source library of Claude Code skills and agent plugins — also works with OpenAI Codex, Gemini CLI, Cursor, and 9 more coding agents. Reusable expertise packages covering engineering, DevOps, marketing (incl. AEO — Answer Engine Optimization for LLM citation), security (PreToolUse hooks), compliance, C-level advisory (incl. founder-mode CFO/CMO/CRO/CPO/COO/CHRO/CISO/GC/CDO/CAIO/CCO/VPE personas + 21 /cs:* slash commands), productivity (capture/email/reflect), an academic research stack (litreview/grants/dossier/patent/syllabus/pulse/notebooklm + hybrid router), and enterprise Research Operations (clinical-research/research-finance/market-research/product-research, v2.9.0).

Works with: Claude Code · OpenAI Codex · Gemini CLI · OpenClaw · Hermes Agent1 · Mistral Vibe2 · Cursor · Aider · Windsurf · Kilo Code · OpenCode · Augment · Antigravity

License: MIT Skills Agents Personas Commands Stars SkillCheck Validated

5,200+ GitHub stars — the most comprehensive open-source Claude Code skills & agent plugins library.


What Are Claude Code Skills & Agent Plugins?

Claude Code skills (also called agent skills or coding agent plugins) are modular instruction packages that give AI coding agents domain expertise they don't have out of the box. Each skill includes:

  • SKILL.md — structured instructions, workflows, and decision frameworks
  • Python tools — 579 CLI scripts (all stdlib-only, zero pip installs)
  • Reference docs — 702 templates, checklists, and domain-specific knowledge files

One repo, thirteen platforms. Works natively as Claude Code plugins, Codex agent skills, Gemini CLI skills, Hermes Agent skills, Mistral Vibe skills, and converts to more tools via scripts/convert.sh. All 579 Python tools run anywhere Python runs.

Skills vs Agents vs Personas

SkillsAgentsPersonas
PurposeHow to execute a taskWhat task to doWho is thinking
ScopeSingle domainSingle domainCross-domain
VoiceNeutralProfessionalPersonality-driven
Example"Follow these steps for SEO""Run a security audit""Think like a startup CTO"

All three work together. See Orchestration for how to combine them.


Quick Install

Gemini CLI (New)

# Clone the repository
git clone https://github.com/alirezarezvani/claude-skills.git
cd claude-skills

# Run the setup script
./scripts/gemini-install.sh

# Start using skills
> activate_skill(name="senior-architect")

Claude Code (Recommended)

# Add the marketplace
/plugin marketplace add alirezarezvani/claude-skills

# Install by domain
/plugin install engineering-skills@claude-code-skills          # 24 core engineering
/plugin install engineering-advanced-skills@claude-code-skills  # 25 POWERFUL-tier
/plugin install product-skills@claude-code-skills               # 12 product skills
/plugin install marketing-skills@claude-code-skills             # 43 marketing skills
/plugin install ra-qm-skills@claude-code-skills                 # 12 regulatory/quality
/plugin install pm-skills@claude-code-skills                    # 6 project management
/plugin install c-level-skills@claude-code-skills               # 28 C-level advisory (full C-suite)
/plugin install business-growth-skills@claude-code-skills       # 4 business & growth
/plugin install finance-skills@claude-code-skills               # 2 finance (analyst + SaaS metrics)

# Or install individual skills
/plugin install skill-security-auditor@claude-code-skills       # Security scanner
/plugin install playwright-pro@claude-code-skills                  # Playwright testing toolkit
/plugin install self-improving-agent@claude-code-skills         # Auto-memory curation
/plugin install content-creator@claude-code-skills              # Single skill

OpenAI Codex

npx agent-skills-cli add alirezarezvani/claude-skills --agent codex
# Or: git clone + ./scripts/codex-install.sh

OpenClaw

bash <(curl -s https://raw.githubusercontent.com/alirezarezvani/claude-skills/main/scripts/openclaw-install.sh)

Manual Installation

git clone https://github.com/alirezarezvani/claude-skills.git
# Copy any skill folder to ~/.claude/skills/ (Claude Code) or ~/.codex/skills/ (Codex)

Multi-Tool Support (New)

Convert all 345 skills to 9 AI coding tools with a single script:

ToolFormatInstall
Cursor.mdc rules./scripts/install.sh --tool cursor --target .
AiderCONVENTIONS.md./scripts/install.sh --tool aider --target .
Kilo Code.kilocode/rules/./scripts/install.sh --tool kilocode --target .
Windsurf.windsurf/skills/./scripts/install.sh --tool windsurf --target .
OpenCode.opencode/skills/./scripts/install.sh --tool opencode --target .
Augment.augment/rules/./scripts/install.sh --tool augment --target .
Antigravity~/.gemini/antigravity/skills/./scripts/install.sh --tool antigravity
Hermes Agent~/.hermes/skills/python scripts/sync-hermes-skills.py --verbose
Mistral Vibe~/.vibe/skills/./scripts/vibe-install.sh

How it works:

# 1. Convert all skills to all tools (takes ~15 seconds)
./scripts/convert.sh --tool all

# 2. Install into your project (with confirmation)
./scripts/install.sh --tool cursor --target /path/to/project

# Or use --force to skip confirmation:
./scripts/install.sh --tool aider --target . --force

# 3. Verify
find .cursor/rules -name "*.mdc" | wc -l  # Should show 346

Each tool gets:

  • ✅ All 345 skills converted to native format
  • ✅ Per-tool README with install/verify/update steps
  • ✅ Support for scripts, references, templates where applicable
  • ✅ Zero manual conversion work

Run ./scripts/convert.sh --tool all to generate tool-specific outputs locally.


Skills Overview

345 skills across 17 domains:

DomainSkillsHighlightsDetails
🔧 Engineering — Core51Architecture, frontend, backend, fullstack, QA, DevOps, SecOps, AI/ML, data, Playwright Pro (test gen, flaky fix, migrations), self-improving agent (auto-memory curation), security suite, a11y auditengineering-team/
⚡ Engineering — POWERFUL78Agent designer, RAG architect, database designer, CI/CD builder, security auditor, MCP builder, AgentHub, Helm charts, Terraform, self-eval, llm-wiki, tc-tracker, autoresearch-agent, reliability portfolio (feature-flags-architect, kubernetes-operator, chaos-engineering, slo-architect), ship-gate, security-guidance PreToolUse hook, Matt Pocock skills (write-a-skill, caveman, grill-me, handoff, grill-with-docs)engineering/
🎯 Product17Product manager, agile PO, strategist, UX researcher, UI design, landing pages, SaaS scaffolder, analytics, experiment designer, discovery, roadmap communicator, code-to-prd, apple-hig-expertproduct-team/
📣 Marketing468 pods: Content, SEO + AEO (aeo — E-E-A-T audit, citation tracking across 5 LLMs), CRO, Channels, Growth, Intelligence, Sales + context foundation + orchestration routermarketing-skill/
🚀 Productivity6capture (brain-dump-to-action), email pair (inbox-setup + inbox-triage), reflect (journal), handoff (Matt Pocock-inspired), andreessen (market-first decision mode)productivity/
🎨 Marketing (top-level)1landing — single-file HTML landing-page generator (4 design styles, GSAP patterns, brand palette validator)marketing/
🔬 Research (academic)8research orchestrator (hybrid router + fallback) + 7 specialists: pulse, litreview, grants (NIH), dossier, patent, syllabus, notebooklmresearch/
🧪 Research Operations ✨v2.9.05Enterprise/cross-functional research: orchestrator + clinical-research (study design), research-finance (R&D program finance), market-research (sizing/survey/segmentation), product-research (user research) — each with onboarding + customization + opt-in autoresearch bridgeresearch-ops/
📋 Project Management9Senior PM, scrum master, Jira, Confluence, Atlassian admin, templates + bundled Atlassian Remote MCPproject-management/
🏥 Regulatory & QM18ISO 13485, MDR 2017/745, FDA, ISO 27001, GDPR, SOC 2, CAPA, risk managementra-qm-team/
🛡️ Compliance OS9Compliance operating system — controls, evidence, audit-readiness workflowscompliance-os/
💼 C-Level Advisory66Full C-suite (CEO/CTO/CFO/CMO/CRO/CPO/COO/CHRO/CISO/GC/CDO/CAIO/CCO/VPE) + founder-mode agents + orchestration + board meetings + culture & collaborationc-level-advisor/
📈 Business & Growth5Customer success, sales engineer, revenue ops, contracts & proposals, BizDev toolkitbusiness-growth/
🏭 Business Operations7Orchestrator + process-mapper, vendor-management, capacity-planner, internal-comms, knowledge-ops, procurement-optimizerbusiness-operations/
🤝 Commercial8Orchestrator + pricing-strategist, deal-desk, partnerships-architect, channel-economics, commercial-policy, rfp-responder, commercial-forecastercommercial/
💰 Finance4Financial analyst (DCF, budgeting, forecasting), SaaS metrics coach, business investment advisorfinance/

Personas

Pre-configured agent identities with curated skill loadouts, workflows, and distinct communication styles. Personas go beyond "use these skills" — they define how an agent thinks, prioritizes, and communicates.

PersonaDomainBest For
Startup CTOEngineering + StrategyArchitecture decisions, tech stack selection, team building, technical due diligence
Growth MarketerMarketing + GrowthContent-led growth, launch strategy, channel optimization, bootstrapped marketing
Solo FounderCross-domainOne-person sta

Footnotes

  1. Hermes Agent is BYO-sync tier: the repo ships a pre-generated .hermes/skills/claude-skills/ tree, but you run python scripts/sync-hermes-skills.py once locally to install into ~/.hermes/skills/. Uses the same agentskills.io SKILL.md standard — no format conversion.

  2. Mistral Vibe is also BYO-sync tier: the repo ships a pre-generated .vibe/skills/claude-skills/ tree, run ./scripts/vibe-install.sh once locally to install into ~/.vibe/skills/. Same agentskills.io SKILL.md standard — no format conversion. Docs: https://docs.mistral.ai/mistral-vibe/agents-skills.

View source on GitHub