### Frontend Setup for Windows

Source: https://github.com/dataelement/clawith/blob/main/CONTRIBUTING.md

Set up the frontend development environment on Windows, including installing dependencies and starting the development server.

```powershell
cd frontend
npm install
npm run dev
```

--------------------------------

### Full Stack Setup and Start

Source: https://github.com/dataelement/clawith/blob/main/CLAUDE.md

Sets up the full stack environment using Docker Compose, including database initialization and starting all services.

```bash
bash setup.sh

bash restart.sh
```

--------------------------------

### Setup and Restart Services

Source: https://github.com/dataelement/clawith/blob/main/CONTRIBUTING.md

These commands are used to set up the development environment and start the backend, frontend, and database services.

```bash
bash setup.sh    # Backend + frontend + database
bash restart.sh  # Start services → http://localhost:3008
```

--------------------------------

### Docker Compose Setup for Clawith

Source: https://github.com/dataelement/clawith/blob/main/README.md

Clone the repository, copy the example environment file, and start the application using Docker Compose. The frontend will be accessible at http://localhost:3008.

```bash
git clone https://github.com/dataelement/Clawith.git
cd Clawith && cp .env.example .env
docker compose up -d
```

--------------------------------

### Backend Setup for Windows

Source: https://github.com/dataelement/clawith/blob/main/CONTRIBUTING.md

Set up the backend environment on Windows, including virtual environment activation, dependency installation, database migrations, and server startup.

```powershell
cd backend
python -m venv .venv
.venv\Scripts\activate
pip install -r requirements.txt

# Create .env (copy from .env.example and adjust DATABASE_URL / REDIS_URL)
# Run database migrations
alembic upgrade head

# Start the server
uvicorn app.main:app --host 0.0.0.0 --port 8000
```

--------------------------------

### Clone Repository and Run Setup Script

Source: https://github.com/dataelement/clawith/blob/main/README.md

Clone the Clawith repository and execute the setup script. Use the --dev flag for development environments to install additional testing tools.

```bash
git clone https://github.com/dataelement/Clawith.git
cd Clawith
bash setup.sh         # Production: installs runtime dependencies only (~1 min)
bash setup.sh --dev   # Development: also installs pytest and test tools (~3 min)
```

--------------------------------

### Start Clawith Application

Source: https://github.com/dataelement/clawith/blob/main/README.md

After setup, use the restart.sh script to start the Clawith application. The frontend will be available at http://localhost:3008 and the backend at http://localhost:8008.

```bash
bash restart.sh
```

--------------------------------

### Troubleshoot Pod Startup Issues

Source: https://github.com/dataelement/clawith/blob/main/helm/QUICKSTART_EN.md

Commands to diagnose why a pod might not be starting correctly.

```bash
# Check Pod details
kubectl describe pod <pod-name> -n clawith

# Check logs
kubectl logs <pod-name> -n clawith

# Check events
kubectl get events -n clawith --sort-by='.lastTimestamp'
```

--------------------------------

### Install Backend Dependencies

Source: https://github.com/dataelement/clawith/blob/main/CLAUDE.md

Installs development dependencies for the Python/FastAPI backend.

```bash
cd backend

pip install -e ".[dev]"
```

--------------------------------

### Run Frontend Dev Server

Source: https://github.com/dataelement/clawith/blob/main/CLAUDE.md

Starts the Vite development server for the frontend.

```bash
npm run dev
```

--------------------------------

### Install Frontend Dependencies

Source: https://github.com/dataelement/clawith/blob/main/CLAUDE.md

Installs dependencies for the React/TypeScript/Vite frontend.

```bash
cd frontend

npm install
```

--------------------------------

### Helm Installation Command

Source: https://github.com/dataelement/clawith/blob/main/helm/QUICKSTART.md

Install the Clawith Helm chart into the `clawith` namespace, creating it if it doesn't exist.

```bash
helm install clawith ./helm/clawith -n clawith --create-namespace
```

--------------------------------

### Run Backend Dev Server

Source: https://github.com/dataelement/clawith/blob/main/CLAUDE.md

Starts the FastAPI development server for the backend.

```bash
uvicorn app.main:app --reload --host 0.0.0.0 --port 8000
```

--------------------------------

### Run PostgreSQL and Redis via Docker

Source: https://github.com/dataelement/clawith/blob/main/CONTRIBUTING.md

Start PostgreSQL and Redis instances using Docker for local development. Ensure Docker Desktop is installed and running.

```powershell
docker run -d --name clawith-postgres -p 5432:5432 -e POSTGRES_PASSWORD=yourpass -e POSTGRES_DB=clawith postgres:15
docker run -d --name clawith-redis -p 6379:6379 redis:7
```

--------------------------------

### Create Article Directory

Source: https://github.com/dataelement/clawith/blob/main/backend/app/services/skill_creator_files/content_research_writer__SKILL.md

Set up a dedicated folder for your article before starting. This organizes your writing project.

```bash
mkdir ~/writing/my-article-title
cd ~/writing/my-article-title
```

--------------------------------

### Install and Use Helm Diff Plugin

Source: https://github.com/dataelement/clawith/blob/main/helm/QUICKSTART_EN.md

Install the helm-diff plugin to compare configuration changes between Helm releases.

```bash
# Install plugin
helm plugin install https://github.com/databus23/helm-diff
```

```bash
# View upgrade differences
helm diff upgrade clawith ./helm/clawith -n clawith
```

--------------------------------

### Helm Chart Configuration Example

Source: https://github.com/dataelement/clawith/blob/main/helm/QUICKSTART_EN.md

Example configuration for the Clawith Helm chart. This includes settings for image registry, tags, persistence, ingress host, and application secrets.

```yaml
# 1. Configure Image Registry
global:
  imageRegistry: docker.io/yourusername  # Change to your image registry

# 2. Configure Image Tags
backend:
  image:
    tag: latest  # Recommended to use specific version, e.g., v1.0.0

frontend:
  image:
    tag: latest  # Recommended to use specific version, e.g., v1.0.0

# 3. Configure Storage
backend:
  persistence:
    existingClaim: ""  # If using existing PVC, enter PVC name
    storageClass: ""  # If creating new, change to your StorageClass name
    size: 10Gi

postgresql:
  image:
    registry: docker.io/bitnami  # Change to your image registry
  auth:
    password: "clawith123456"  # Strongly recommended to change to a strong password!
  primary:
    persistence:
      existingClaim: ""  # If using existing PVC, enter PVC name
      storageClass: ""  # If creating new, change to your StorageClass name
      size: 8Gi

redis:
  image:
    registry: docker.io  # Change to your image registry
  persistence:
    existingClaim: ""  # If using existing PVC, enter PVC name
    storageClass: ""  # If creating new, change to your StorageClass name
    size: 2Gi

# 4. Configure Domain
frontend:
  ingress:
    host: "clawith.example.com"  # Change to your domain

# 5. Modify Application Secrets (Important!)
backend:
  secrets:
    secretKey: "your-secret-key-at-least-50-characters-long"
    jwtSecretKey: "your-jwt-secret-key-at-least-32-characters"

# 6. Enable hostCerts if private certificate signing support is needed
backend:
  hostCerts:
    enabled: false  # Set to true if needed

```

--------------------------------

### Configure Custom PostgreSQL Instance

Source: https://github.com/dataelement/clawith/blob/main/README.md

If you need to use a specific PostgreSQL instance, create a .env file and set the DATABASE_URL environment variable before running the setup script.

```bash
DATABASE_URL=postgresql+asyncpg://user:pass@localhost:5432/clawith?ssl=disable
```

--------------------------------

### Configure Optional PyPI Mirror

Source: https://github.com/dataelement/clawith/blob/main/README.md

To use a regional mirror for Python package installations during setup or Docker builds, set the CLAWITH_PIP_INDEX_URL and CLAWITH_PIP_TRUSTED_HOST environment variables.

```bash
export CLAWITH_PIP_INDEX_URL=https://pypi.tuna.tsinghua.edu.cn/simple
export CLAWITH_PIP_TRUSTED_HOST=pypi.tuna.tsinghua.edu.cn
```

--------------------------------

### Risk Manager Bootstrap - Config Captured and Walkthrough

Source: https://github.com/dataelement/clawith/blob/main/backend/agent_templates/risk-manager/bootstrap.md

This snippet demonstrates the output after capturing user configuration (user_turns >= 1). It includes the captured config in YAML format, an explanation of the trade staging flow, and an example dry run.

```yaml
account_size: <user value>
max_single_trade_risk_pct: <user value>
max_single_position_pct: 20    # default, editable
max_sector_concentration_pct: 30  # default, editable
cooldown_hours_same_symbol: 24    # default, editable
```

```markdown
**Config captured**

**How to stage a trade with me**
*   **Tell me the trade** (symbol, long/short, entry, stop, target)
*   **I run guards** (you'll see GREEN/YELLOW/RED with reasons)
*   **You decide to push** (RM produces a parameter card; you manually enter the order in your broker)

**Example dry run**
AAPL long, entry $190, stop $185, target $210

GREEN
*   shares = floor(account × max_risk% / (entry - stop))
*   dollar risk = (entry - stop) × shares
*   R-multiple = (target - entry) / (entry - stop)
*   broker entry instructions: "limit buy 26 AAPL @ $190.00, stop $185.00, target $210.00"

**Reminder**
**RM never sends orders — I produce the card, you click Buy in your broker.**

Want me to **walk through staging your first real trade now**, or **adjust the default guard values** (concentration / cooldown) first?
```

--------------------------------

### Create New Feature Branch

Source: https://github.com/dataelement/clawith/blob/main/CONTRIBUTING.md

Demonstrates how to create a new branch for developing a specific feature, starting from the main branch.

```bash
# Start each new feature from a fresh branch off main
git checkout main && git pull
git checkout -b feat/i18n-emoji-cleanup

# ... develop, commit ...

git checkout main
git checkout -b feat/admin-email-templates

# ... develop, commit ...
```

--------------------------------

### Preview Helm Deployment Content

Source: https://github.com/dataelement/clawith/blob/main/helm/QUICKSTART_EN.md

Render Helm chart templates to preview the generated Kubernetes YAML before installation or upgrade.

```bash
# Render template without installing
helm template clawith ./helm/clawith -n clawith > preview.yaml
```

```bash
# Or use --dry-run
helm install clawith ./helm/clawith -n clawith --dry-run --debug
```

--------------------------------

### Split Changes with Git Add -p

Source: https://github.com/dataelement/clawith/blob/main/CONTRIBUTING.md

This example shows how to use `git add -p` to selectively stage parts of changes for creating multiple commits and pull requests from a single messy branch.

```bash
# Assume your branch is called my-big-branch and has 3 logical changes mixed in.
# Goal: create 3 separate PRs from it.

# --- PR 1: emoji cleanup ---
git checkout -b feat/i18n-emoji-cleanup main

# Interactively stage only the emoji-related hunks from en.json and zh.json:
git add -p frontend/src/i18n/en.json   # answer y/n for each hunk
git add -p frontend/src/i18n/zh.json
git commit -m "fix: remove emoji from i18n strings"
git push -u origin feat/i18n-emoji-cleanup
# → open PR

# --- PR 2: hardcoded strings → t() ---
git checkout -b feat/i18n-component-strings main

git add -p frontend/src/pages/AgentDetail.tsx   # stage only t() hunk
git add -p frontend/src/components/ChannelConfig.tsx
git commit -m "feat: replace hardcoded UI strings with i18n t() calls"
git push -u origin feat/i18n-component-strings
# → open PR

# --- PR 3: admin improvements ---
git checkout -b feat/admin-improvements main
git checkout my-big-branch -- frontend/src/pages/AdminCompanies.tsx  # cherry-pick whole file if clean
git commit -m "feat: improve admin company settings"
git push -u origin feat/admin-improvements
# → open PR
```

--------------------------------

### Greeting Turn for Trading Journal Coach

Source: https://github.com/dataelement/clawith/blob/main/backend/agent_templates/trading-journal-coach/bootstrap.md

This is the initial message the coach sends when a user starts a conversation (user_turns == 0). It introduces itself, its capabilities, and asks for the first trade.

```markdown
**Hi {user_name}!**
I'm **{name}** — I read your trade history, find what you keep repeating, and help you turn the lessons into rules.

*   **Trade journaling** — every push gets logged and tagged.
*   **Weekly review** — pattern hunting across trades, not single-trade post-mortem.
*   **Rule evolution** — proposes additions to trading_rules.md (you approve).

_I help with research, analysis, and discipline — I won't place trades or give investment advice._

**Tell me about a recent trade — what you did, why, and how it ended.** Even a rough description works. I'll show you the journaling structure I'd use.
```

--------------------------------

### Build Frontend for Production

Source: https://github.com/dataelement/clawith/blob/main/README.md

Compile the frontend application for production deployment. Ensure you are in the frontend directory.

```bash
cd frontend && npm run build
```

--------------------------------

### Greeting for New User (user_turns == 0)

Source: https://github.com/dataelement/clawith/blob/main/backend/agent_templates/frontend-developer/bootstrap.md

This snippet outlines the initial greeting and capability pitch for the frontend developer agent when interacting with a user for the first time. It focuses on establishing the agent's core skills and asking a targeted opening question.

```markdown
**Hi {user_name}!**
I'm **{name}** — I ship responsive, accessible, fast web UI.

*   **Component implementation** — React/Vue with TypeScript and clean state.
*   **Performance passes** — LCP/INP/CLS audits with concrete fixes.
*   **Accessibility review** — WCAG, keyboard, screen-reader paths.

**What's one component or page you want built, improved, or audited?**
```

--------------------------------

### Preview Frontend Production Build

Source: https://github.com/dataelement/clawith/blob/main/CLAUDE.md

Serves a preview of the production build for the frontend.

```bash
npm run preview
```

--------------------------------

### Drafted Message/Email Example

Source: https://github.com/dataelement/clawith/blob/main/backend/agent_templates/chief-of-staff/bootstrap.md

An example of a drafted message or email, presented within a fenced code block, to be used by the Chief of Staff agent.

```markdown
```

```
```

--------------------------------

### Research Compiled for Article

Source: https://github.com/dataelement/clawith/blob/main/backend/app/services/skill_creator_files/content_research_writer__SKILL.md

Example of AI-generated research compilation including data, expert quotes, and real-world examples with citations, suitable for a research-heavy article.

```markdown
## Research Compiled

### Recent Data
- Gartner: 80% of PMs will use AI tools by 2025 [1]
- Survey: 45% report faster feature shipping [2]
- Case study: Airbnb's AI-assisted prioritization [3]

### Expert Quotes
- "AI amplifies PM judgment, not replaces it" - Marty Cagan
- [Additional quotes with citations]

### Real Examples
1. **Company A**: Used AI for user research synthesis
   - Result: 60% time savings
   - Source: [citation]

2. **Company B**: AI-powered roadmap analysis
   - Result: Better stakeholder alignment
   - Source: [citation]

All added to your outline with proper citations.
```

--------------------------------

### Recommended Project File Structure

Source: https://github.com/dataelement/clawith/blob/main/backend/app/services/skill_creator_files/content_research_writer__SKILL.md

Illustrates a recommended directory structure for organizing long-form writing projects, including drafts, research, and feedback.

```bash
~
├── writing/article-name/
│   ├── outline.md          # Your outline
│   ├── research.md         # All research and citations
│   ├── draft-v1.md         # First draft
│   ├── draft-v2.md         # Revised draft
│   ├── final.md            # Publication-ready
│   ├── feedback.md         # Collected feedback
│   └── sources/            # Reference materials
│       ├── study1.pdf
│       └── article2.md
```

--------------------------------

### Build Frontend for Production

Source: https://github.com/dataelement/clawith/blob/main/CLAUDE.md

Performs a type check and builds the frontend for production.

```bash
npm run build
```

--------------------------------

### Import MCP Server Tool (Initial Attempt)

Source: https://github.com/dataelement/clawith/blob/main/backend/agent_template/skills/mcp-installer/SKILL.md

Attempt to import an MCP server tool using its qualified name. This is the first step before potentially needing to provide credentials.

```python
import_mcp_server(
  server_id="<qualified_name>"
)
```

--------------------------------

### Get Section Feedback

Source: https://github.com/dataelement/clawith/blob/main/backend/app/services/skill_creator_files/content_research_writer__SKILL.md

Request feedback on a specific section of your draft after completion. This helps in iterative refinement.

```Claude
I just finished the "Why This Matters" section. Review it and give feedback.
```

--------------------------------

### Configure Existing PVC for Clawith

Source: https://github.com/dataelement/clawith/blob/main/helm/QUICKSTART_EN.md

Example YAML configuration for using existing Persistent Volume Claims (PVCs) for backend, PostgreSQL, and Redis persistence.

```yaml
backend:
  persistence:
    enabled: true
    existingClaim: "clawith-agent-data-pvc"  # Your PVC name
    # No need to specify storageClass and size

postgresql:
  primary:
    persistence:
      enabled: true
      existingClaim: "clawith-postgresql-data"  # Your PVC name

redis:
  persistence:
    enabled: true
    existingClaim: "redisdata"  # Your PVC name

```

--------------------------------

### Greeting and Initial Question (User Turns = 0)

Source: https://github.com/dataelement/clawith/blob/main/backend/agent_templates/backend-architect/bootstrap.md

This snippet defines the agent's initial greeting and the first question to ask the user when no prior messages have been exchanged. It aims to quickly identify the user's primary design need.

```markdown
**Hi {user_name}!**
I'm **{name}** — I design backend systems that hold up under real load.

*   **API design** — REST/GraphQL shapes with clear contracts and error paths.
*   **Data modeling** — schema, indexes, partitioning, migration sequencing.
*   **Trade-off analysis** — CAP, consistency, latency vs. cost, honest about risk.

**What's one service, endpoint, or data model you most want designed or reviewed?**
```

--------------------------------

### Get Download URI Utility

Source: https://github.com/dataelement/clawith/blob/main/backend/app/services/skill_creator_files/eval-viewer__viewer.html

A utility function to generate a download URI for a file. It prioritizes data_uri and falls back to data_b64 for binary files.

```javascript
function getDownloadUri(file) { if (file.data_uri) return file.data_uri; if (file.data_b64) return "data:application/octet-stream;base64,"; }
```

--------------------------------

### Create Draft File

Source: https://github.com/dataelement/clawith/blob/main/backend/app/services/skill_creator_files/content_research_writer__SKILL.md

Create an empty markdown file to begin drafting your article.

```bash
touch article-draft.md
```

--------------------------------

### Deploy to Dev Server

Source: https://github.com/dataelement/clawith/blob/main/CLAUDE.md

Deploys the application to the development server. Refer to .agents/workflows/deploy-dev.md for complete instructions.

```bash
# Deploy to dev server (192.168.106.163, port 3009)
# See .agents/workflows/deploy-dev.md for full steps
```

--------------------------------

### Inline Citation Example

Source: https://github.com/dataelement/clawith/blob/main/backend/app/services/skill_creator_files/content_research_writer__SKILL.md

Shows how to include citations directly within the text using parentheses. This is a common method for referencing sources in academic or professional writing.

```markdown
Studies show 40% productivity improvement (McKinsey, 2024).

```

--------------------------------

### Research Findings Example

Source: https://github.com/dataelement/clawith/blob/main/backend/app/services/skill_creator_files/content_research_writer__SKILL.md

Demonstrates how to present research findings, including key points with citations and a separate citation list. Useful for summarizing research results.

```markdown
## Research: AI Impact on Productivity

Key Findings:

1. **Productivity Gains**: Studies show 40% time savings for 
   content creation tasks [1] 

2. **Adoption Rates**: 67% of knowledge workers use AI tools 
   weekly [2] 

3. **Expert Quote**: "AI augments rather than replaces human 
   creativity" - Dr. Jane Smith, MIT [3] 

Citations:
[1] McKinsey Global Institute. (2024). "The Economic Potential 
    of Generative AI"
[2] Stack Overflow Developer Survey (2024)
[3] Smith, J. (2024). MIT Technology Review interview

Added to outline under Section 2.

```

--------------------------------

### Source Deployment Upgrade (v1.8.3-beta.2)

Source: https://github.com/dataelement/clawith/blob/main/RELEASE_NOTES.md

Specific source deployment upgrade steps for v1.8.3-beta.2, including code pull, database migration, frontend rebuild, and service restart.

```bash
git pull origin main

# Run database migration
alembic upgrade heads

# Rebuild frontend
cd frontend && npm install && npm run build
cd ..

# Restart services
```

--------------------------------

### Configure Dynamic PVC for Clawith

Source: https://github.com/dataelement/clawith/blob/main/helm/QUICKSTART_EN.md

Example YAML configuration for creating new Persistent Volume Claims (PVCs) dynamically for backend, PostgreSQL, and Redis persistence, specifying StorageClass and size.

```yaml
backend:
  persistence:
    enabled: true
    existingClaim: ""  # Leave empty
    storageClass: "nfs-client"  # Your StorageClass name
    size: 10Gi

postgresql:
  primary:
    persistence:
      enabled: true
      existingClaim: ""
      storageClass: "nfs-client"
      size: 8Gi

redis:
  persistence:
    enabled: true
    existingClaim: ""
    storageClass: "nfs-client"
    size: 2Gi

```

--------------------------------

### Deliverable Plan for Returning User (user_turns >= 1)

Source: https://github.com/dataelement/clawith/blob/main/backend/agent_templates/frontend-developer/bootstrap.md

This snippet details the structure and content for the frontend developer agent's response when a user has already provided a deliverable. It includes a plan with assumed stack, component interface, implementation outline, and potential risks.

```markdown
**Target** — one line paraphrasing what they said.
**Assumed stack** — best guess (e.g. "**React 18 + TypeScript + Tailwind**") tagged "(adjust if wrong)".
**Component interface** — a TypeScript `interface` for props and a brief state shape, in a fenced code block.
**Implementation outline** — numbered steps (structure, state, styling, a11y, perf) with the specific concern per step.
**Risks / edge cases** — 2–3 bullets of what most likely breaks.

Want me to **write the full component**, or **focus on the accessibility + performance audit** first?
```

```typescript
interface MyComponentProps {
  // Define props here
}

interface MyComponentState {
  // Define state here
}
```

--------------------------------

### Docker Deployment Upgrade (v1.8.3-beta.2)

Source: https://github.com/dataelement/clawith/blob/main/RELEASE_NOTES.md

Specific Docker upgrade steps for v1.8.3-beta.2, including pulling code, running database migration for a new column, and restarting services.

```bash
git pull origin main

# Run database migration
docker exec clawith-backend-1 alembic upgrade heads

# Rebuild and restart
docker compose down && docker compose up -d --build
```

--------------------------------

### Footnote Style Citation Example

Source: https://github.com/dataelement/clawith/blob/main/backend/app/services/skill_creator_files/content_research_writer__SKILL.md

Illustrates the footnote style of citation, where a superscript number in the text links to a note at the bottom of the page or document. This method is common in legal and historical writing.

```markdown
Studies show 40% productivity improvement^1

```

--------------------------------

### Production Environment Configuration

Source: https://github.com/dataelement/clawith/blob/main/helm/QUICKSTART_EN.md

Configure settings for a production environment, including replica counts, resource limits, storage, and ingress.

```yaml
global:
  imageRegistry: registry.yourcompany.com/clawith

backend:
  replicaCount: 2  # Multiple replicas
  image:
    tag: v1.0.0  # Use fixed version
  resources:
    limits:
      cpu: 2000m
      memory: 4Gi
    requests:
      cpu: 500m
      memory: 1Gi
  persistence:
    storageClass: "ssd-storage"  # High-performance storage
    size: 50Gi

frontend:
  replicaCount: 2
  image:
    tag: v1.0.0
  ingress:
    enabled: true
    annotations:
      cert-manager.io/cluster-issuer: "letsencrypt-prod"
      nginx.ingress.kubernetes.io/ssl-redirect: "true"
    host: "clawith.yourcompany.com"
    tls:
      enabled: true
      secretName: clawith-tls-secret

postgresql:
  auth:
    password: "STRONG_PASSWORD_HERE"  # Must use strong password
  primary:
    persistence:
      storageClass: "ssd-storage"
      size: 20Gi
    resources:
      limits:
        cpu: 2000m
        memory: 2Gi
      requests:
        cpu: 500m
        memory: 512Mi

redis:
  persistence:
    storageClass: "ssd-storage"
    size: 5Gi
  resources:
    limits:
      cpu: 1000m
      memory: 1Gi
    requests:
      cpu: 250m
      memory: 256Mi
```

--------------------------------

### Numbered Reference Citation Example

Source: https://github.com/dataelement/clawith/blob/main/backend/app/services/skill_creator_files/content_research_writer__SKILL.md

Demonstrates the use of numbered references, where citations are indicated by bracketed numbers in the text and a corresponding list of sources appears at the end. This format is often used in academic papers.

```markdown
Studies show 40% productivity improvement [1].

[1] McKinsey Global Institute. (2024)...

```

--------------------------------

### Risk Manager Bootstrap - Greeting and Initial Prompt

Source: https://github.com/dataelement/clawith/blob/main/backend/agent_templates/risk-manager/bootstrap.md

This snippet shows the initial greeting and prompt when the Risk Manager meets a user for the first time (user_turns == 0). It sets expectations about the agent's role and asks for essential configuration values.

```markdown
**Hi {user_name}!**
I'm **{name}** — I'm the gatekeeper for every trade decision. Stage your idea here, I'll run guards, you decide whether to push.

*   **Trade staging** — write your idea down before you act.
*   **Guard checks** — single-trade risk, position size, concentration, cooldown, rules.
*   **GREEN/YELLOW/RED verdict** — every trade passes the same checklist.

_I help with research, analysis, and discipline — I won't place trades or give investment advice._

**Two numbers I need from you to set up your guards:** (1) **roughly what's your trading account size?** ranges are fine ($25k, $100k, $500k+); (2) **what's the max % of account you're willing to lose on any single trade?** (1% is common for retail, 2% if you're more aggressive). I'll save these to config and use them on every trade you stage.
```

--------------------------------

### Check All Resources Status

Source: https://github.com/dataelement/clawith/blob/main/helm/QUICKSTART_EN.md

View all Kubernetes resources within the 'clawith' namespace.

```bash
kubectl get all -n clawith
```

--------------------------------

### Run Database Migrations (Source Deployment)

Source: https://github.com/dataelement/clawith/blob/main/RELEASE_NOTES.md

Perform database migrations for a source deployment by navigating to the backend directory and running the alembic upgrade command. This is followed by frontend build and service restarts.

```bash
git pull origin main

# Run database migrations
cd backend && alembic upgrade heads
cd ..

# Rebuild frontend
cd frontend && npm install && npm run build
cd ..

# Restart backend / frontend services
```

--------------------------------

### View Helm Release Values

Source: https://github.com/dataelement/clawith/blob/main/helm/QUICKSTART_EN.md

Retrieve and display the configuration values for the 'clawith' Helm release.

```bash
helm get values clawith -n clawith
```

--------------------------------

### Verify Services and Ingress

Source: https://github.com/dataelement/clawith/blob/main/helm/QUICKSTART.md

Check the status of services and ingress resources in the `clawith` namespace.

```bash
kubectl get svc,ingress -n clawith
```

--------------------------------

### Configure Resource Limits for Backend

Source: https://github.com/dataelement/clawith/blob/main/helm/QUICKSTART_EN.md

Define CPU and memory resource requests and limits for the backend deployment in Helm values.

```yaml
backend:
  resources:
    limits:
      cpu: 2000m
      memory: 4Gi
    requests:
      cpu: 500m
      memory: 1Gi
```

--------------------------------

### View Frontend Pod Logs

Source: https://github.com/dataelement/clawith/blob/main/helm/QUICKSTART_EN.md

Stream logs from the frontend pods in the 'clawith' namespace.

```bash
kubectl logs -n clawith -l app.kubernetes.io/component=frontend -f
```

--------------------------------

### Configure Docker Registry Mirror (China Users)

Source: https://github.com/dataelement/clawith/blob/main/README.md

For users in China experiencing timeouts with Docker Compose, configure a Docker registry mirror by adding the provided JSON to /etc/docker/daemon.json and restarting the Docker service.

```bash
sudo tee /etc/docker/daemon.json > /dev/null <<EOF
{
  "registry-mirrors": [
    "https://docker.1panel.live",
    "https://hub.rat.dev",
    "https://dockerpull.org"
  ]
}
EOF
sudo systemctl daemon-reload && sudo systemctl restart docker
```

--------------------------------

### Verify Clawith Deployment

Source: https://github.com/dataelement/clawith/blob/main/helm/QUICKSTART_EN.md

Check the status of pods, services, and ingress resources in the 'clawith' namespace to verify the deployment.

```bash
# Check Pod status
kubectl get pods -n clawith

# Expected output:
# NAME                                  READY   STATUS    RESTARTS   AGE
# clawith-backend-xxx                   1/1     Running   0          2m
# clawith-frontend-xxx                  1/1     Running   0          2m
# clawith-postgresql-0                  1/1     Running   0          2m
# clawith-redis-xxx                     1/1     Running   0          2m

# Check Services and Ingress
kubectl get svc,ingress -n clawith
```