global/post-performance-analyst

Post Performance Analyst — analyze why a published social media post performed the way it did.

Category: global
Source: workflows/research/post_performance.py

Input Schema

Field	Type	Default	Description
caption	string	""	Post caption/text content
hashtags	string[]	—	Hashtags used on the post
media_type	string	"image"	Media type: image, video, carousel, text
metrics	object	—	Platform metrics: impressions, interactions, comments, watchTimeSeconds
platform_account_follower_count	object	—	Account follower count at time of post
post_id	string	required	Unique identifier of the published post
provider	string	required	Platform: instagram, tiktok, youtube, twitter, linkedin
published_at	string	""	ISO 8601 timestamp of publication
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

No schema defined.

Task Pipeline

compute_engagement_metrics → analyze_performance

Task	Description
compute_engagement_metrics	Compute engagement rate and performance grade from raw metrics.
analyze_performance	Analyze post performance across five dimensions using an LLM.

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/post-performance-analyst

# Optional fields — copy any line(s) under `input:` and uncomment to set:
# Post caption/text content
#   caption: ""
#
# Hashtags used on the post
#   hashtags: []
#
# Media type: image, video, carousel, text
#   media_type: image
#
# Platform metrics: impressions, interactions, comments, watchTimeSeconds
#   metrics: {}
#
# Account follower count at time of post
#   platform_account_follower_count: null
#
# ISO 8601 timestamp of publication
#   published_at: ""
#

input:
  # Unique identifier of the published post
  post_id: ""

  # Platform: instagram, tiktok, youtube, twitter, linkedin
  provider: ""

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/post-performance-analyst' \
  -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 analyze_performance has no Pydantic return type — workflow output schema is null. Declare a WorkflowOutput subclass and pass it to Flow(output=…) for a strict contract.