hooks/generate

Hook Generation — data-driven hook ideas from scraped intelligence + strategy context.

Category: hooks
Source: workflows/hooks/generate.py

Input Schema

Field	Type	Default	Description
classified_hooks	object[]	—	Pre-scraped hooks with engagement data
clusters	object[]	—	Hook archetype clusters
competitors	string[]	—	Competitor creator names/handles
lookahead_days	integer	30	How far ahead to look for events
niche	string	""	Content niche (e.g. ‘AI tools’, ‘fitness’)
num_hooks	integer	15	Number of hook ideas to generate
platform	string	"tiktok"	Target platform
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.
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.

Output Schema

Field	Type	Default	Description
hook_ideas	object[]	—	Generated hook ideas
kind	object	—	Variant card shape: video / carousel / image / text. Surfaced on the per-variant entry of the run-output API and used by gallery UIs to pick the right layout.
workflow	string	"hook-generation"	Workflow identifier

Task Pipeline

gather_competitor_insights → gather_trend_signals → gather_event_context → merge_intel → generate_hook_ideas

Task	Description
gather_competitor_insights	Aggregate competitor hook intelligence — delegates to SDK stage.
gather_trend_signals	Pull in trend context — delegates to SDK stage.
gather_event_context	Gather event context — delegates to SDK stage.
merge_intel	Merge parallel competitor-insights and trend-signals branches.
generate_hook_ideas	Generate hook ideas — delegates to SDK stage (70/20/10 strategy, PromptExtension).

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: hooks/generate

# Optional fields — copy any line(s) under `input:` and uncomment to set:
# Pre-scraped hooks with engagement data
#   classified_hooks: []
#
# Hook archetype clusters
#   clusters: []
#
# Competitor creator names/handles
#   competitors: []
#
# How far ahead to look for events
#   lookahead_days: 30
#
# Content niche (e.g. 'AI tools', 'fitness')
#   niche: ""
#
# Number of hook ideas to generate
#   num_hooks: 15
#
# Target platform
#   platform: tiktok
#

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=hooks/generate' \
  -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

• Task gather_competitor_insights has no Pydantic types — contract is opaque to consumers.
• Task gather_trend_signals has no Pydantic types — contract is opaque to consumers.
• Task gather_event_context has no Pydantic types — contract is opaque to consumers.
• Task merge_intel has no Pydantic types — contract is opaque to consumers.
• Task generate_hook_ideas has no Pydantic types — contract is opaque to consumers.