facebook-research
Research public Facebook pages, groups, posts, reels, comments, ads, events, marketplace listings, and profiles for audience or competitor evidence.
How do I install this agent skill?
npx skills add https://github.com/postplusai/postplus-skills --skill facebook-researchIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill provides tools for researching public Facebook data using the postplus CLI. It contains explicit instructions to avoid private data and credentials. The security analysis identified a surface for indirect prompt injection, as the agent is required to ingest and analyze untrusted text from social media posts, comments, and web search results.
- Socketpass
No alerts
- Snykwarn
Risk: MEDIUM · 1 issue
What does this agent skill do?
Facebook Research
Use this skill when the user needs public Facebook evidence - page/profile posts, direct posts, public group posts, reels, comments, ad-library creative, events, marketplace listings, page profiles, or public search - for a growth, marketing, creator, community, competitor, or funnel decision.
Read only the one narrow reference matching the job.
Collection Routes
Facebook has URL-led routes for public page/profile/group/post content and specialized routes for reels, comments, ads, events, marketplace, pages, and search. Pick the route by user intent; PostPlus handles execution details.
All post collections return output.items[]; fields differ between ordinary posts, group posts and Reels. Follow the selected reference. facebook-group-posts and facebook-groups sample the same public group posts; do not run both as independent corroboration. Both group routes return a chronological post sample with no server-side keyword filter. Missing group membership, founding dates or verification are unavailable, not zero or false.
Use web-search for external source discovery only; its snippets are not Facebook post or comment evidence. Follow references/public-content.md for search-page field reading.
Route
| User intent | Read |
|---|---|
| Public page, profile, group, or post content pull | references/public-content.md |
| Page health, competitor page, group quality, public presence audit | references/page-and-group-audit.md |
| Organic hooks, formats, competitors, post examples, content patterns | references/organic-benchmark.md |
| Reels, short-form video, video hooks, media-led benchmark | references/reels-and-video.md |
| Comments, audience voice, objections, FAQ, group discussion | references/community-voice.md |
| Ad-library creative, paid offers, CTAs, funnel review | references/ads-and-funnel.md |
| Events, local activations, organizers, offline demand | references/events-and-local.md |
| Marketplace listings, local commerce, price bands | references/shops-and-marketplace.md |
| Partner/creator/organizer discovery, broad Facebook search, page verification | references/partner-discovery.md |
| Private profiles, hidden groups, member lists, Page Insights, ad account metrics, targeting, spend, ROAS | Stop and ask for a public source or export |
First Question
Ask only when the answer changes the route, source, privacy boundary, sample size, or output shape.
| Missing | Ask |
|---|---|
| Non-ad seed | What Facebook source should anchor this: page, profile, group, post URL, keyword, or event? |
| Decision | What decision should this support: audit, benchmark, voice, ads, events, marketplace, or discovery? |
| Private target | Can you provide a public URL or exported dataset instead? |
| Non-ad scope too broad | Which 1-5 sources matter most for the first pass? |
For ads, a product URL, unfamiliar brand, category, or problem is a sufficient
seed. Read references/ads-and-funnel.md: discover candidate Facebook pages,
verify their identity, then collect by Page ID. Establish competitor relationships;
review category relevance. Continue within the same turn through review, delivery
and that reference's stopping conditions.
Do not ask the user for internal route identifiers, schemas, implementation choices, retries, credentials, hidden filters, or internal routing.
Run Discipline
- Pick one reference and one lane.
- For ads, collect fresh evidence as described in
references/ads-and-funnel.md; do not automatically search the stored ad library. Explicit library browsing is a separate user goal. Otherwise run the smallest real collection that can answer the decision. - Parallelize independent sources when they do not depend on each other.
- If execution succeeds but evidence is empty, sparse, noisy, or off-topic, apply the quality rules below before accepting or exhausting the evidence.
- Preserve complete JSON results. For ads, use
postplus ad-library reportwith all inputs and keep reviewed ad IDs and reasons in the analysis. Other research uses a compact evidence artifact. - Return a short chat answer: scope, counts, strongest finding, biggest gap, artifact path, and next action.
Use only the public filters shown by the selected route.
Public Command Boundary
- Choose the smallest matching research route and run it directly.
- Readiness diagnostics:
postplus doctor --skill facebook-research. - Inspect one route with
postplus research run <route> --helpwhen its semantic flags are not already clear. - Run
postplus research run <route> --<semantic flags> --wait --output <result.json>. - Pass only public URLs, search terms, locations, scope, and result limits.
- For non-ad routes, keep the first pass bounded; expand only after inspecting the first result. For ads, collect toward the requested evidence outcome, using the ad reference. Stop on hard errors. Do not silently swap sources or invent missing data.
- Requested tasks use existing PostPlus credits after the current price and balance are checked. Estimate-only requests do not execute. Stop on insufficient credits; do not recharge, buy a subscription, or repeat an uncertain paid operation.
Command Selection
| Evidence need | Route | Semantic input | First pass |
|---|---|---|---|
| Public page/profile posts | facebook-profile-posts | --url, --limit | 1-5 URLs, 20 posts |
| Direct post evidence | facebook-post-by-url | --url | 1-10 URLs |
| Public group posts | facebook-group-posts | --url, --limit | 1-3 groups, 20 posts |
| Ad-library creative | facebook-ads-library | --query OR --page-id, --sort, --country, --status, --limit | See ad reference: outcome-sized collection |
| Post/reel comments | facebook-comments | --url, --limit | 1-5 URLs, 20 comments |
| Public group discussion | facebook-groups | --url, --limit | 20 posts |
| Events/local activity | facebook-events | --query or --url, --limit | 10 events |
| Marketplace listings | facebook-marketplace | --url, --limit | 10 listings |
| Page identity | facebook-pages | --url | 1-5 pages |
| Rich page/profile posts | facebook-posts | --url, --limit | 20 posts |
| Reels | facebook-reels | --url, --limit | 20 reels |
| Broad public search | facebook-search | --category (search term), --location, --limit | 20 results |
Only if platform scope or evidence interpretation remains unclear, consult platform contract; it is not a preflight.
Evidence Quality
- Check that page/post/comment/ad records match the requested lane; public group posts are not automatically comment evidence.
- Change the public source URL or a supported query when evidence misses; keep ad creative separate from organic posts.
- For non-ad routes, allow at most two changed follow-up passes after successful but insufficient results, within approved scope and budget; do not repeat an identical request or hide a failed/pending operation.
- For ads, use the ad reference's evidence-based stopping conditions. Otherwise stop when sufficient, at the bound, or when another pass would not help. Report useful evidence and uncertainty; preserve raw results and source links.
Ad-library visibility is not spend or ROAS; preserve the source URL and observed dates, and distinguish comments from post text.
Full machine fields belong to postplus research schema --route <route> --json;
consult it only when required for processing, not before every request.
postplus research run facebook-ads-library \
--query "example topic" \
--wait \
--output ./result.json
Follow the CLI's structured result and reported next action; do not infer recovery from free-text messages. Use existing PostPlus credits for requested work within existing authorization; estimate-only requests do not execute. Do not recharge, buy subscriptions, publish or change external advertising spend without applicable authorization. An initial reservation is not a final price or a hard cost cap. If a required hard final-cost limit cannot be enforced, do not execute; explain that limit. Correct definite pre-submission field or format errors without changing the requested intent, mode or output constraints. After submission or an unknown outcome, resume the same operation through its returned checkpoint or action; never resubmit uncertain work, repeat exhausted recovery, or switch providers to bypass failure. Keep raw results, operation identifiers and recovery commands in execution records. In ordinary chat, give the result, meaningful limitations, known cost and any necessary user decision; do not narrate uploads, polling, internal identifiers or JSON. When asked how media was made, provide the actual model, submitted prompt in the user language and references actually submitted with their roles.
<!-- END GENERATED EXECUTION EXAMPLE -->How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/postplusai/postplus-skills/facebook-research">View facebook-research on skillZs</a>