facebook-research
Facebook Research
Follow shared public skill rules in:
postplus-sharedpublic skill rules
Use this skill when the request is about Facebook account or content research.
This skill is for:
- sampling public follower or following surfaces from a Facebook page or profile
- collecting public page or profile follow-graph items when Facebook exposes them
- collecting one or more public Facebook page, group, or direct post URLs
- discovering a small Facebook post set from a broad query
- normalizing Facebook post metrics into local artifacts
- writing local raw payloads, normalized datasets, and short markdown summaries
This skill is not for:
- LinkedIn collection
- YouTube collection
- TikTok, Instagram, or X workflows
- publishing, deleting, or scheduling posts
- guaranteeing a complete private follower list when Facebook does not expose it publicly
Before Collection Boundary
Before running collection, tell the user that Facebook results are public samples from exposed surfaces, not a complete follower export. If the user's goal requires private or exhaustive audience data, stop and ask for a different source of truth before collecting.
PostPlus Cloud Boundary
This skill depends on host-managed collection capability for the corresponding collection paths.
In the PostPlus runtime:
- do not probe or print provider secrets
- do not ask the user to export them inside chat
- if a collection path returns a stable capability/network hard error, stop immediately instead of trying alternate shell commands
Default Collection Path
Use the hosted follower collection path by default:
- default collection mode: public follower or following items from a page or profile URL
- use for public follower or following item collection from a page or profile URL
- tested input shape:
startUrls = [{ "url": "https://www.facebook.com/<page-or-profile>" }]resultsLimitfollowType = "follower"orfollowType = "following"
- current observed output fields include:
facebookUrlfollowTypetitleurlsubtitle_textimage
- this is the default hosted path for Facebook audience-surface research on the public skill surface
Supported Facebook Targets
- public page/profile URL -> follower or following items through hosted collection
- public page/profile URL -> recent posts through hosted content collection
- public group URL -> recent posts
- direct public post URL -> one post
Failure Posture
- fail if the request includes non-Facebook platforms
- fail if no Facebook public URLs can be discovered
- fail if hosted content collection returns malformed items without stable URL or id fields
- fail if hosted follower collection returns no publicly visible follower or following items
- keep raw responses for debugging
Recommended Workflow
- If the user wants account audience research, start with follower collection using the PostPlus Cloud collection service.
- If the user wants content research, use the hosted content collection scripts below.
- If the user wants both, collect follower or following items first, then collect post evidence from the same page or profile.
Do not treat Facebook follower-surface results as a guaranteed full audience export.
Public Skill Execution Contract
- keep collection briefs, raw datasets, normalized outputs, and summary caches
under
<work-folder>/.postplus/facebook-research/ - keep only final user-facing summaries or shortlist exports outside
.postplus/ - compile a small page, post, or discovery brief before the expensive collection step
- start with a bounded first pass:
- one page or profile
- one public post plan
- one summary pass
Public Post Implementation
Read before implementation:
skills/20-research/facebook-research/references/normalized-schema.md
Use these entrypoints:
skills/20-research/facebook-research/scripts/run_facebook_post_collection.mjs
Hosted Collection Note
Use the shared hosted collection runner for actor calls:
${CLAUDE_SKILL_DIR}/_postplus_shared/00-core/shared-collection/scripts/collection_actor_run.mjs
More from postplusai/postplus-skills
audio-transcription
Transcribe local or remote audio into durable text and timestamp artifacts using hosted Whisper models. Use this when the job is speech-to-text from audio files and you need request/response persistence, optional timestamps, and subtitle-ready outputs.
98google-trends-research
Research Google Trends search-intent signals for topic discovery, keyword momentum, regional interest, and rising queries without treating search trends as the same thing as platform content heat or marketplace demand.
92tiktok-research
Research TikTok metadata, creators, comments, trends, and benchmark data for organic platform analysis.
90social-media-publisher
Prepare and, after explicit approval, publish social posts through the PostPlus platform-owned social publishing workspace.
90video-transcription
Transcribe video files directly into timed transcripts and subtitle-ready artifacts using hosted Whisper video-to-text. Use this when the input is a video and the goal is speech extraction, caption generation, or edit-prep timing.
90seedance-submitter
Use when preparing, submitting, polling, or debugging Seedance 2.0 video generation jobs from product images, storyboard images, UGC scripts, voiceover copy, or promptPlan request JSON. Use for splitting scripts into render segments, uploading references, creating request JSON, submitting jobs through the PostPlus Cloud service, polling predictions, and handing off local render paths.
90