global/platform-adapt

Cross-platform text adaptation — one hook/concept → platform-native text for each target platform.

Category: global
Source: workflows/content/platform_adapt.py

Input Schema

Field	Type	Default	Description
brand_voice	string	""
hook	string	""
hook_text	object	—
mode	string	"caption"
niche	string	""
platforms	any[]	—
regenerate	object	—	When set, this run is a regeneration. Workflows may read direction / keep / extra_instructions to modulate prompts; the engine persists parent_run_id and parent_variant_index as run lineage columns.
target_audience	string	""
tone_mode	string	"aggressive"
topic	string	""
variants	integer	1	Number of independent variant executions (1–10). When > 1, the engine runs the workflow N times with different sampling, producing N outputs.
visual_description	string	""

Output Schema

No schema defined.

Task Pipeline

adapt_for_platforms → validate_and_refine

Task	Description
adapt_for_platforms	Adapt a hook/concept into platform-native text for each target platform.
validate_and_refine	Validate generated posts against platform constraints and iteratively refine.

Run-spec example

Save the YAML below as my-run.yaml, edit the values, and run with the CLI or POST it to the API. Required fields are uncommented; optional knobs are documented above the input: block — copy any line under input: and uncomment to set.

workflow: global/platform-adapt

# Optional fields — copy any line(s) under `input:` and uncomment to set:
#   brand_voice: ""
#
#   hook: ""
#
#   hook_text: null
#
#   mode: caption
#
#   niche: ""
#
#   platforms: []
#
#   target_audience: ""
#
#   tone_mode: aggressive
#
#   topic: ""
#
#   visual_description: ""
#

input: {}

Run it locally:

fab-workflow --from-file my-run.yaml

Or submit over the wire — the same file is the request body:

curl -X POST 'https://gofabric.dev/v1/workflows/runs?name=global/platform-adapt' \
  -H 'Authorization: Bearer fab_xxx' \
  -H 'content-type: application/yaml' \
  --data-binary @my-run.yaml

Every workflow also accepts the universal WorkflowInput fields — variants (1–10 fan-out) and regenerate (creative-direction hints with run lineage). See Run-specs (YAML / TOML / JSON) for the full top-level shape (metadata, priority, bundle, parent, etc.).

Warnings

• Last user task validate_and_refine has no Pydantic return type — workflow output schema is null. Declare a WorkflowOutput subclass and pass it to Flow(output=…) for a strict contract.