# UGC flow Human Guide

## What This Is For
Use When The user wants a UGC-style product, app, service, testimonial, or creator video pipeline. It gives the agent a clearer input/output frame for UGC flow: what context to ask for, what decisions to make, and what usable artifact to return.

Use this as a human-readable version of the UGC flow agent skill. It is meant for marketers, operators, founders, and other non-coders who want the workflow without reading agent-specific implementation instructions.

## When To Use This
- Use this when you need a repeatable process for UGC flow.
- Use this when the task needs judgment, examples, constraints, or a clear output format rather than a one-off prompt.
- Use this when you want to hand an AI assistant enough context to produce a usable marketing artifact.

## When Not To Use This
- Do not use this when you only need a quick factual answer.
- Do not use this when the work depends on private data you cannot share with the assistant.
- Do not use this as a replacement for legal, compliance, financial, or medical review.

## What You Need Before Starting
- The goal or business outcome you want.
- The audience, customer segment, or market context.
- Any source material the assistant should respect, such as notes, briefs, examples, URLs, or brand guidance.
- Constraints such as tone, length, channel, deadline, region, or approval requirements.
- A clear definition of what a good final answer should look like.

## Step-By-Step Workflow
1. State the job clearly: "Use the UGC flow guide to help me with..."
2. Add context: audience, goal, offer, channel, source material, and constraints.
3. Ask the assistant to identify missing inputs before producing the final output.
4. Have the assistant follow the skill-specific guidance below.
5. Review the result against the final checklist and ask for revisions where needed.

## Skill-Specific Guidance
- The user wants a UGC-style product, app, service, testimonial, or creator
- The job spans multiple steps: product analysis, creator/persona logic,
- The request needs a standard production line instead of one isolated runner.
- The user only needs one image, voice take, or simple clip. Use
- The user only needs transcription, subtitles, or video analysis. Use
- A provider-ready request already exists. Use the relevant runner.
- `product_analysis`: collect product facts, core promise, proof points,
- `creator_logic`: define creator type, audience fit, native behavior, tone,
- `board`: use `reference-decode`, `reference-contract-builder`, and
- `clip`: use `image-generation`, `audio-generation`, and `video-generation`
- `montage`: use `editing-decision-engine` for cut logic, B-roll roles, and
- `qa`: use `creative-qa` and `prompt-preflight-qa` before execution and after

## Decision Points And Nuance
The original skill emphasizes: Use When, Do Not Use When, Core Boundary, Standard Pipeline, Required Checkpoints, Routing Table, Output Shape, Stop Conditions, Public Command Boundary.

Use these questions to steer the work:
- What is the intended audience or buyer?
- What source material must be preserved?
- What should the assistant optimize for: clarity, persuasion, accuracy, speed, creativity, or conversion?
- What examples represent the desired quality bar?
- What should the assistant avoid?

## Common Mistakes
- constraints, and claims that must not be invented.
- Stop when required user intent, source evidence, or owned input artifacts are
- Do not let runners make creative or claim decisions.
- Do not call private provider/runtime paths or unpublished local tools.

## Copy-And-Paste Prompt
```text
Use the UGC flow human guide.

My goal:
[Describe the business outcome]

Audience:
[Describe who this is for]

Context and source material:
[Paste notes, examples, links, or existing copy]

Constraints:
[Tone, length, channel, timeline, must-include items, must-avoid items]

Before producing the final output, ask me for any missing information that would materially improve the result.
```

## Final Checklist
- [ ] The output matches the original goal.
- [ ] The audience and context are reflected in the answer.
- [ ] Important constraints and source material were preserved.
- [ ] The assistant made the relevant decisions explicit.
- [ ] The final artifact is ready to use, review, or hand to the next person.

## Source
This guide was generated from the postplusai/postplus-skills skill entry for `ugc-flow`.

## Source Skill Notes
These notes preserve the nuance from the original skill. Use them as supporting reference when the workflow above feels too generic.

# UGC Flow

## Use When
- The user wants a UGC-style product, app, service, testimonial, or creator
  video pipeline.
- The job spans multiple steps: product analysis, creator/persona logic,
  storyboard, image or video clip generation, montage, subtitles, and QA.
- The request needs a standard production line instead of one isolated runner.

## Do Not Use When
- The user only needs one image, voice take, or simple clip. Use
  `image-generation`, `audio-generation`, or `video-generation`.
- The user only needs transcription, subtitles, or video analysis. Use
  `media-router`.
- A provider-ready request already exists. Use the relevant runner.

## Core Boundary
This is a workflow skill. It coordinates public skills and checkpoints; it does
not call providers or submit generation jobs.

## Standard Pipeline

1. `product_analysis`: collect product facts, core promise, proof points,
   constraints, and claims that must not be invented.
2. `creator_logic`: define creator type, audience fit, native behavior, tone,
   and what the creator is allowed to claim.
3. `board`: use `reference-decode`, `reference-contract-builder`, and
   `storyboard-grid-writer` when references or panel logic matter.
4. `clip`: use `image-generation`, `audio-generation`, and `video-generation`
   to produce controller handoffs.
5. `montage`: use `editing-decision-engine` for cut logic, B-roll roles, and
   subtitle or beat placement.
6. `qa`: use `creative-qa` and `prompt-preflight-qa` before execution and after
   generated assets return.

## Required Checkpoints
- product facts and source basis
- creator/persona rule
- viewer question and hook mechanism
- reference contract with binding, inspiration-only, and excluded references
- storyboard or beat plan
- image/audio/video controller handoffs
- runner-ready requests only after strategy is locked
- QA verdict and rerun notes

## Routing Table

| Need | Handoff |
| --- | --- |
| Product or market evidence | Instagram/Meta research or strategy skill appropriate to the product |
| Creator discovery | `instagram-creator-discovery` |
| Benchmark-to-brief | `benchmark-to-brief` |
| Reference decode or boundary | `reference-decode`, `reference-contract-builder` |
| Storyboard grid | `storyboard-grid-writer` |
| Image assets | `image-generation` |
| Voice or dub | `audio-generation` |
| Clips or talking-head video | `video-generation` |
| Cut logic and montage | `editing-decision-engine` |
| Final creative review | `creative-qa` |

## Output Shape
Return a workflow packet:

- `productionGoal`
- `sourceBasis`
- `creatorLogic`
- `referencePolicy`
- `storyboardOrBeatPlan`
- `generationHandoffs`
- `montagePlan`
- `qaPlan`
- `openQuestions`

## Stop Conditions
- Stop when required user intent, source evidence, or owned input artifacts are
  missing and guessing would change the result.
- Do not let runners make creative or claim decisions.
- If an owned CLI or script command fails, report the exact error and stop. Do
  not bypass the failure with metadata-only answers, readiness probing, local
  payload rewrites, fallback providers, or unpublished tools.