Rapp pipeline

Skill kody-w/rapp-skills/rapp-pipeline

Run RAPP (Rapid Agent Prototyping Platform) pipeline to generate AI agents from transcripts. Use when building agents, generating Copilot Studio solutions, or deploying to Microsoft AI stack.From its SKILL.md

Install

npx -y skills add kody-w/rapp-skills --skill rapp-pipeline

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

11.9 KB, ~6.5k tokens by cl100k_base, as published. Nobody here has run it

RAPP Pipeline Skill

This skill runs the RAPP pipeline to generate production-ready AI agents from business transcripts.

Available Commands

Full Pipeline (Transcript to Agent)

python3 -m rapp_cli pipeline <project_id> [options]

Options:

-t, --transcript PATH - Path to transcript file
-c, --customer TEXT - Customer name
-o, --output PATH - Output directory
--json-output - Output results as JSON (for parsing)

Copilot Studio + Azure DevOps

python3 -m rapp_cli copilot-studio <project_id> [options]

Options:

-t, --transcript PATH - Path to transcript file
-c, --customer TEXT - Customer name
-p, --publisher TEXT - Solution publisher prefix
-e, --environments TEXT - Target environments (comma-separated)
--json-output - Output results as JSON

Project Management

# List all projects
python3 -m rapp_cli list-projects --json-output

# Show project details
python3 -m rapp_cli show-project <project_id> --json-output

# Create new project
python3 -m rapp_cli new <project_name>

Quality Gates

python3 -m rapp_cli quality-gate <project_id> --gate QG1

Gates: QG1 (Transcript), QG2 (Customer), QG3 (Code), QG4-QG5 (Demo), QG6 (Deployment)

Reports

python3 -m rapp_cli report <project_id> --report-type discovery

Types: discovery, mvp, code, qg1-qg6, executive_summary

Workflow

Create Project
```
python3 -m rapp_cli new my-project
```
Add Transcript (save to rapp_projects/{project}/inputs/transcript.txt)

Run Pipeline

# Basic agent generation
python3 -m rapp_cli pipeline my-project --customer "Contoso" --json-output

# Full Microsoft AI stack
python3 -m rapp_cli copilot-studio my-project --customer "Contoso" --json-output

Check Output

python3 -m rapp_cli show-project my-project --json-output

Output Locations

Agents: rapp_projects/{project}/outputs/{agent_id}_agent.py
Demos: rapp_projects/{project}/outputs/{agent_id}_demo.json
HTML Tester: rapp_projects/{project}/outputs/agent_tester.html
Copilot Studio: rapp_projects/{project}/copilot_studio/
Azure DevOps: rapp_projects/{project}/azure_devops/

Working Directory

Always run commands from: ~/.rapp/src

Example: End-to-End Automation

cd ~/.rapp/src

# 1. Create project
python3 -m rapp_cli new contoso-agent

# 2. Create transcript (or use existing)
cat > rapp_ai/rapp_projects/contoso-agent/inputs/transcript.txt << 'EOF'
[Discovery call transcript content here]
EOF

# 3. Run full pipeline
python3 -m rapp_cli copilot-studio contoso-agent \
  --customer "Contoso Financial" \
  --publisher contoso \
  --environments "dev,test,prod" \
  --json-output

# 4. Verify outputs
python3 -m rapp_cli show-project contoso-agent --json-output

Parameters

The typed contract this capability answers to (JSON Schema — the deterministic layer):

{
  "properties": {
    "project_id": {
      "description": "Derived from `<project_id>` used in the documented command at line 9.",
      "type": "string"
    },
    "project_name": {
      "description": "Derived from `<project_name>` used in the documented command at line 39.",
      "type": "string"
    }
  },
  "required": [],
  "type": "object"
}

Deterministic steps

Lifted verbatim from the procedure above by toaster.py toast. Run them in order, substituting the typed parameters; do not paraphrase:

python3 -m rapp_cli pipeline <project_id> [options]
python3 -m rapp_cli copilot-studio <project_id> [options]
python3 -m rapp_cli list-projects --json-output
python3 -m rapp_cli show-project <project_id> --json-output
python3 -m rapp_cli new <project_name>
python3 -m rapp_cli quality-gate <project_id> --gate QG1
python3 -m rapp_cli report <project_id> --report-type discovery
python3 -m rapp_cli new my-project
python3 -m rapp_cli pipeline my-project --customer "Contoso" --json-output
python3 -m rapp_cli copilot-studio my-project --customer "Contoso" --json-output
python3 -m rapp_cli show-project my-project --json-output
cd ~/.rapp/src
python3 -m rapp_cli new contoso-agent
python3 -m rapp_cli copilot-studio contoso-agent \
python3 -m rapp_cli show-project contoso-agent --json-output

What ships with it: 1 file

16.1 KB alongside SKILL.md, 1 of them executable

rapp_pipeline_agent.pyruns16.1 KB