output-meta-project-context

What this skill does

# Output.ai Framework - Complete Project Context

## What is Output.ai?

Output.ai provides infrastructure for building production-grade AI workflows: fact checkers, content generators, data extractors, research assistants, and multi-step agents. Built on Temporal, it guarantees **durable execution** - if execution fails mid-run, it resumes from the last successful step.

## Core Philosophy

**Separation of orchestration from I/O:**
- **Workflows** orchestrate execution (must be deterministic - no I/O)
- **Steps/Evaluators** handle all I/O operations (HTTP, LLM, database calls)

This separation enables automatic retries, resumption, and debugging.

## Component Taxonomy

| Component | Purpose | Key Rule |
|-----------|---------|----------|
| **Workflow** | Orchestrates step execution | Must be deterministic (no I/O, no Date.now(), no Math.random()) |
| **Step** | Handles all I/O operations | Where HTTP, LLM, DB calls happen |
| **Evaluator** | Quality assessment | Returns confidence-scored results for validation loops |
| **Scenario** | Test input data | JSON files matching workflow's inputSchema |
| **Prompt** | LLM templates | Liquid.js templating with YAML frontmatter config |
| **Eval Test** | Offline quality testing | Dataset-driven verification with `verify()` from `@outputai/evals` |

## Project Structure

```
config/
├── credentials.yml.enc          # Global encrypted credentials
├── credentials.key              # Global decryption key (DO NOT COMMIT)
└── credentials/                 # Environment-specific credentials
    ├── production.yml.enc
    └── production.key
src/
├── shared/                      # Shared code across workflows
│   ├── clients/                 # API clients (e.g., jina.ts, stripe.ts)
│   └── utils/                   # Utility functions (e.g., string.ts)
└── workflows/                   # Workflow definitions
    └── {workflow_name}/
        ├── workflow.ts          # Orchestration logic (deterministic)
        ├── steps.ts             # I/O operations
        ├── types.ts             # Zod schemas (input, output, internal)
        ├── evaluators.ts        # Quality checks (optional)
        ├── utils.ts             # Local utilities (optional)
        ├── credentials.yml.enc  # Workflow-specific credentials (optional)
        ├── prompts/             # LLM templates (optional)
        │   └── [email protected]
        ├── scenarios/           # Test inputs (optional)
        │   └── happy_path.json
        └── tests/               # Offline eval tests (optional)
            ├── datasets/        # YAML test datasets
            │   └── happy_path.yml
            └── evals/           # Eval evaluators and workflow
                ├── evaluators.ts
                └── workflow.ts
```

## Code Reuse Rules

**Shared directory** (`src/shared/`):
- `shared/clients/` - API clients using `@outputai/http` for external services
- `shared/utils/` - Helper functions and utilities

**Allowed imports:**
- Workflows/steps can import from `../../shared/clients/*.js` and `../../shared/utils/*.js`
- Workflows/steps can import from local files (`./types.js`, `./utils.js`)

**Forbidden:**
- Importing from sibling workflow folders (`../other_workflow/steps.js`)
- Steps importing other steps (activity isolation requirement)

## Critical Rules

| Rule | Correct | Incorrect |
|------|---------|-----------|
| Zod import | `import { z } from '@outputai/core'` | `import { z } from 'zod'` |
| HTTP client | `import { httpClient } from '@outputai/http'` | `import axios from 'axios'` |
| Credentials | `import { credentials } from '@outputai/credentials'` | `process.env.SECRET` |
| LLM calls | `import { generateText, Output } from '@outputai/llm'` | Direct provider SDK |
| ES imports | `import { fn } from './file.js'` | `import { fn } from './file'` |
| Workflow I/O | Call steps for any I/O | Direct fetch/http in workflow |

**Determinism violations (never in workflows):**
- `Date.now()`, `new Date()`
- `Math.random()`, `crypto.randomUUID()`
- Direct HTTP/fetch calls
- File system operations
- Environment variable reads

---

## Available Tools Inventory

### Agents

| Agent | Purpose |
|-------|---------|
| `workflow-planner` | Designs workflow architecture, creates implementation blueprints |
| `workflow-debugger` | Analyzes workflow execution traces, identifies issues |
| `workflow-quality` | Reviews code quality, validates implementations |
| `workflow-prompt-writer` | Creates and optimizes LLM prompt templates |
| `workflow-context-fetcher` | Gathers documentation and existing patterns |

### Commands

| Command | Purpose | When to Use |
|---------|---------|-------------|
| `/output-plan-workflow` | Plan workflow architecture | **ALWAYS FIRST** - creates implementation blueprint |
| `/output-build-workflow` | Build/implement workflows | After planning, or for modifications |
| `/output-debug-workflow` | Debug workflow issues | When workflows fail or behave unexpectedly |

### Skills

#### Workflow Operations
| Skill | Purpose |
|-------|---------|
| `output-workflow-run` | Synchronous workflow execution (waits for result) |
| `output-workflow-start` | Asynchronous workflow execution (returns ID) |
| `output-workflow-list` | List available workflows |
| `output-workflow-status` | Check async workflow status |
| `output-workflow-result` | Get async workflow result |
| `output-workflow-reset` | Rerun a workflow from after a completed step |

#### Monitoring & Debugging
| Skill | Purpose |
|-------|---------|
| `output-workflow-stop` | Stop running workflow |
| `output-workflow-trace` | Trace workflow execution |
| `output-workflow-runs-list` | List workflow run history |
| `output-dev-workflow-cost` | Calculate cost of a workflow run |
| `output-services-check` | Verify Output services status |

#### Error Diagnosis
| Skill | Catches |
|-------|---------|
| `output-error-zod-import` | Wrong zod import source |
| `output-error-nondeterminism` | Date.now, Math.random in workflows |
| `output-error-try-catch` | Missing error handling in steps |
| `output-error-missing-schemas` | Incomplete Zod schema exports |
| `output-error-direct-io` | I/O operations in workflow files |
| `output-error-http-client` | Using axios instead of @outputai/http |

#### Meta/Lifecycle
| Skill | Purpose |
|-------|---------|
| `output-meta-pre-flight` | Pre-operation validation checks |
| `output-meta-post-flight` | Post-operation verification |
| `output-meta-project-context` | Load full project context (this skill) |

#### Development
| Skill | Purpose |
|-------|---------|
| `output-dev-folder-structure` | Project and workflow directory layout |
| `output-dev-workflow-function` | Writing deterministic workflow files |
| `output-dev-step-function` | Writing step functions for I/O |
| `output-dev-types-file` | Zod schema definitions |
| `output-dev-evaluator-function` | Quality assessment functions |
| `output-dev-eval-testing` | Offline eval tests with `@outputai/evals` |
| `output-dev-prompt-file` | LLM prompt templates with Liquid.js |
| `output-dev-model-selection` | Pick a current LLM model via the AI Gateway listing |
| `output-dev-upgrade-prompt-models` | Bulk-upgrade `model:` fields across `.prompt` files |
| `output-dev-scenario-file` | Test input JSON files |
| `output-dev-http-client-create` | Shared HTTP API client patterns |
| `output-dev-create-skeleton` | Generate workflow skeleton |

#### Credentials
| Skill | Purpose |
|-------|---------|
| `output-dev-credentials` | Full credentials system reference (API, scopes, merging, custom providers) |
| `output-credentials-init` | Initialize encrypted credentials files for the first time |
| `output-credentials-edit` | View and edit credential values with `show`/`get`/`edit` commands |
| `output-credentials-env-vars` | Wire credentials to env vars using the `credential:` convention |

---

## CLI Quick Reference

```bash
# Development
npx output dev                              # Start dev environment

# List &