ワンクリックでManusで任意のスキルを実行

meta-ads-drive-to-meta

スター12

フォーク5

更新日2026年7月16日 14:49

End-to-end orchestrator — take a creative sitting in Google Drive and turn it into a ready-to-launch (PAUSED) Meta/Facebook ad, in one guided flow. Use when the user says "sube este creativo de Drive a Meta y ármame el anuncio", "from Google Drive to Meta Ads", "publica (en pausa) este video/imagen de mi Drive", or wants the whole chain (asset → campaign → ad set → ad) from a Drive file without stitching the sub-skills by hand. It chains meta-ads-asset-upload → meta-ads-campaign-setup → meta-ads-adset-setup → meta-ads-ad-setup, adds the Drive-source resolution + transport decision that make it CONSISTENT, verifies, and (for tests) tears down. Everything is created PAUSED; activation is a human decision.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

portermetricsample

portermetricsample/marketing-skills

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

Meta Ads — Drive → Meta (end-to-end orchestrator)

One job: a file in Google Drive → a PAUSED, ready-to-review Meta ad, reliably, for a non-technical user. This skill does not re-document each step — it sequences the existing skills and owns the two things that make the chain break: getting the Drive bytes into Meta (size/transport decision) and wiring the ids together (account blob, page, creative hash, budget units).

🔒 Safety contract (inherited): everything is created PAUSED; activation is human. account_id for every MCP call = the signed blob from list_accounts, passed verbatim (one wrong character → account_ref signature is invalid). Budgets are minor units (×currency offset) with a per-account minimum the API enforces. See references/pipeline.md.

The chain (what runs, in order)

Resolve account + page — list_accounts (signed blob) + discover the Page id.
Asset from Drive → hash/id — ../asset-upload/ + scripts/drive_to_meta_upload.py.
Campaign (PAUSED) — ../campaign-setup/.
Ad set (PAUSED, targeting + budget) — ../adset-setup/.
Ad (PAUSED, creative = the Drive hash + copy + CTA) — ../ad-setup/.
Verify the ad's creative == the uploaded hash; report ids. (Tests: tear down with campaign_delete.)

The full ordered call sequence, params, and every validated gotcha live in references/pipeline.md — read it before running.

What makes it CONSISTENT (the differentiator)

Transport decision is automatic, not guessed (the #1 source of failures):
- Drive file ≤ 10 MB → pull bytes with the Google-Drive MCP (download_file_content) → transport B: prepare_upload + scripts/drive_to_meta_upload.py (base64 POSTed in code, never streamed through the model).
- Drive file > 10 MB (all real videos) → the Drive MCP cannot download it → transport A: the file must be link-shared and passed as a public url to facebook_ads.video_upload. (Claude does NOT change Drive sharing — the user does; see pipeline.md.)
Currency-aware budget: read the account currency, convert the user's real money to minor units, enforce the account minimum — the user always thinks in "$X/day", never in cents.
Video is async: after video_upload, poll object_read(video_id, fields="status") until ready before ad_create, or Meta rejects the ad.

Inputs (what to collect from the user)

Input	Needed for	Notes
Ad account (name or id)	all	Resolved via `list_accounts` → signed blob.
Drive file (id or name)	asset	An image (JPG/PNG — WebP is rejected) or video (MP4/MOV).
Objective	campaign	`OUTCOME_TRAFFIC` / `LEADS` / `SALES` / `AWARENESS` / `ENGAGEMENT` / `APP_PROMOTION`.
Facebook Page	ad	Auto-discoverable: `object_read(act_…, fields="promote_pages{id,name}")`. Confirm with the user.
Budget (real money/day)	ad set	Converted to minor units; ≥ account minimum.
Geo (≥1 country)	ad set	Meta rejects targeting with no geo.
Copy: message / headline / link / CTA	ad	LEADS also needs a `lead_gen_form_id`.

Operate (happy path, image)

"Sube business-retail.jpg de mi Drive a la cuenta Porter y ármame un anuncio de tráfico a portermetrics.com, $5/día, US, en pausa."

list_accounts(query="Porter") → signed blob. object_read(act_…, "promote_pages{id,name}") → Page.
Drive file ≤10 MB → download_file_content → prepare_upload(image_upload) → python3 scripts/drive_to_meta_upload.py --kind image --from-drive-json --src <dl.json> --account act_… --upload-url <fresh> --filename business-retail.jpg --mime image/jpeg → image_hash.
campaign_create(objective=OUTCOME_TRAFFIC, special_ad_categories=[], status=PAUSED).
adset_create(optimization_goal=LINK_CLICKS, billing_event=IMPRESSIONS, destination_type=WEBSITE, targeting_countries=["US"], daily_budget_amount=<minor≥min>, status=PAUSED).
ad_create(page_id, image_hash, message, headline, link, cta_type=LEARN_MORE, status=PAUSED).
object_read(ad_id, "creative{image_hash},status") → confirm hash matches + PAUSED. Report ids.

Validated end-to-end live 2026-07-16 (account Porter act_794709130739347, COP): Drive JPG → hash 3b21ca91… → campaign → ad set (min budget 3319 COP minor) → ad (creative == hash) → verified PAUSED → deleted. See references/pipeline.md for the video path + edge cases.

Scope / boundary

✅ Orchestrates: Drive source → asset id → campaign → ad set → ad (PAUSED) → verify → (test) teardown.
❌ Does NOT re-implement targeting/objective/creative-format detail — that lives in the sub-skills (campaign-setup, adset-setup, ad-setup, asset-upload). This skill decides the order, the transport, and the id plumbing.
❌ Does NOT activate ads, change Drive sharing, or invent budgets/audiences.

このリポジトリの他の Skills

同じリポジトリ

porter-instagram-dashboard

portermetricsample/marketing-skills

Build a polished, hosted Instagram Insights dashboard for any Instagram account using the PorterMetrics MCP — a 4-page report (Overview, Posts, Stories, Audience) that ships as a live shareable URL. Use this skill WHENEVER the user wants an Instagram / IG analytics dashboard, report, or "insights" page built with Porter / PorterMetrics — even if they only say "make me an Instagram report", "dashboard for my IG account", "replicate this Instagram dashboard", "Porter report for Instagram", or hand you a Porter Instagram report URL to reproduce. It offers a one-call CLONE path that works anywhere (including plain chat, no build tools) plus a full build path, so every run produces a near-identical dashboard. Do NOT hand-roll an Instagram report from scratch when this skill applies.

2026-07-2412

dashboard-builder

portermetricsample/marketing-skills

Build a complete, hosted marketing dashboard on Porter Metrics end-to-end — from intake interview and SUMAS planning, through a brand-approved design kit (Porter brand or white-label extracted from any client website), to a live published report URL with real data. Use when a user with the Porter MCP asks for "a dashboard", "a client report I can share", "a live report for account X", or wants to white-label a report with a client's brand. Connector- agnostic (Google Ads, Meta, GA4, ...) and framework-agnostic (Next.js template is the default path, any static-site stack meeting the Porter contract works).

2026-07-2312

quality-score-trend

portermetricsample/marketing-skills

Track each keyword's Google Ads Quality Score over time and flag the keywords whose QS is DECLINING — the quiet erosion that raises your CPC and drops your rank without any alert firing — then attribute the drop to the component responsible (Expected CTR, Ad Relevance, or Landing Page Experience). Use this skill whenever the user asks about Quality Score trend, QS dropping / falling over time, "why did my Quality Score go down", CPC creeping up for no obvious reason, keywords slipping in rank, or which component (expected CTR / ad relevance / landing page experience) is hurting a keyword — even if they don't say "Quality Score". This skill diagnoses WHERE QS is eroding and WHY (which component) ONLY; the ad-copy fix belongs to the complementary `rsa-strength-copy-diversity-audit` skill, the landing-page fix to `landing-page-cro-audit`, and the point-in-time keyword↔ad↔landing relevance snapshot to `keyword-ad-landing-alignment`.

2026-07-1612

wasted-spend

portermetricsample/marketing-skills

Quantify the TOTAL wasted spend in a Google Ads account and pinpoint the biggest leaks — money spent on search terms, keywords, ad groups, or campaigns that returned ~0 conversions or cost far more per conversion than target. Rolls the leaks up to one dollar number and a % of spend, then lists the top leaks by scope, each with the dollars wasted and a recommended action. Use this skill whenever the user asks how much they're wasting, where the money is leaking, "what spend is doing nothing", zero-conversion keywords/terms, spend with no return, or an account-level waste roll-up — even if they don't say "wasted spend". Quantifies and prioritizes waste ONLY; writing the negatives belongs to `negative-keywords`, reallocating the freed budget to `spend-allocation`, and classifying WHY a term is irrelevant to `search-term-classifier`.

2026-07-1612

pmax-diagnostics

portermetricsample/marketing-skills

Give the advertiser the honest Performance Max read — is each PMax campaign earning its budget against the account's Search baseline (CPA/ROAS), what asset-group-level performance is actually visible, and — explicitly — what Google's API does NOT expose for PMax (search terms, placements, audience detail), so the reader trusts the numbers that ARE real. Use this skill whenever the user asks about Performance Max, PMax, "is my PMax working / worth it", PMax spend, PMax vs Search, asset groups, or the PMax black box — even if they don't say "diagnostics". Judges PMax earning-vs-baseline and the visible asset-group signal ONLY; full search-term mining and placement control are API-limited (named as gaps, not faked), and bid targets belong to the complementary `bid-strategy` skill.

2026-07-1612

google-ads-changelog

portermetricsample/marketing-skills

Build an exhaustive, human-readable Google Ads CHANGE HISTORY / changelog for a Porter-connected account — what changed, when, by whom, translated into plain English (the exact negative keyword, the budget before→after, the tCPA/tROAS, the paused campaign), grouped by day and change type, and overlaid against the daily CPA so you can see which performance moves followed which edits. Use when the user asks "what changed in my Google Ads account", "change history", "changelog", "account audit log", "who changed what", "qué cambios se hicieron en la cuenta", "historial de cambios", or wants to correlate account edits with CPA/performance. Runs on the Porter Metrics MCP (google-ads connector). One account at a time. Google retains only the last 30 days of change history.

2026-07-1612

name

meta-ads-drive-to-meta

description

Meta Ads — Drive → Meta (end-to-end orchestrator)

🔒 Safety contract (inherited): everything is created PAUSED; activation is human. account_id for every MCP call = the signed blob from list_accounts, passed verbatim (one wrong character → account_ref signature is invalid). Budgets are minor units (×currency offset) with a per-account minimum the API enforces. See references/pipeline.md.

The chain (what runs, in order)

Resolve account + page — list_accounts (signed blob) + discover the Page id.
Asset from Drive → hash/id — ../asset-upload/ + scripts/drive_to_meta_upload.py.
Campaign (PAUSED) — ../campaign-setup/.
Ad set (PAUSED, targeting + budget) — ../adset-setup/.
Ad (PAUSED, creative = the Drive hash + copy + CTA) — ../ad-setup/.
Verify the ad's creative == the uploaded hash; report ids. (Tests: tear down with campaign_delete.)

The full ordered call sequence, params, and every validated gotcha live in references/pipeline.md — read it before running.

What makes it CONSISTENT (the differentiator)

Transport decision is automatic, not guessed (the #1 source of failures):
- Drive file ≤ 10 MB → pull bytes with the Google-Drive MCP (download_file_content) → transport B: prepare_upload + scripts/drive_to_meta_upload.py (base64 POSTed in code, never streamed through the model).
- Drive file > 10 MB (all real videos) → the Drive MCP cannot download it → transport A: the file must be link-shared and passed as a public url to facebook_ads.video_upload. (Claude does NOT change Drive sharing — the user does; see pipeline.md.)
Currency-aware budget: read the account currency, convert the user's real money to minor units, enforce the account minimum — the user always thinks in "$X/day", never in cents.
Video is async: after video_upload, poll object_read(video_id, fields="status") until ready before ad_create, or Meta rejects the ad.

Inputs (what to collect from the user)

Input	Needed for	Notes
Ad account (name or id)	all	Resolved via `list_accounts` → signed blob.
Drive file (id or name)	asset	An image (JPG/PNG — WebP is rejected) or video (MP4/MOV).
Objective	campaign	`OUTCOME_TRAFFIC` / `LEADS` / `SALES` / `AWARENESS` / `ENGAGEMENT` / `APP_PROMOTION`.
Facebook Page	ad	Auto-discoverable: `object_read(act_…, fields="promote_pages{id,name}")`. Confirm with the user.
Budget (real money/day)	ad set	Converted to minor units; ≥ account minimum.
Geo (≥1 country)	ad set	Meta rejects targeting with no geo.
Copy: message / headline / link / CTA	ad	LEADS also needs a `lead_gen_form_id`.

Operate (happy path, image)

"Sube business-retail.jpg de mi Drive a la cuenta Porter y ármame un anuncio de tráfico a portermetrics.com, $5/día, US, en pausa."

list_accounts(query="Porter") → signed blob. object_read(act_…, "promote_pages{id,name}") → Page.
Drive file ≤10 MB → download_file_content → prepare_upload(image_upload) → python3 scripts/drive_to_meta_upload.py --kind image --from-drive-json --src <dl.json> --account act_… --upload-url <fresh> --filename business-retail.jpg --mime image/jpeg → image_hash.
campaign_create(objective=OUTCOME_TRAFFIC, special_ad_categories=[], status=PAUSED).
adset_create(optimization_goal=LINK_CLICKS, billing_event=IMPRESSIONS, destination_type=WEBSITE, targeting_countries=["US"], daily_budget_amount=<minor≥min>, status=PAUSED).
ad_create(page_id, image_hash, message, headline, link, cta_type=LEARN_MORE, status=PAUSED).
object_read(ad_id, "creative{image_hash},status") → confirm hash matches + PAUSED. Report ids.

Scope / boundary

✅ Orchestrates: Drive source → asset id → campaign → ad set → ad (PAUSED) → verify → (test) teardown.
❌ Does NOT re-implement targeting/objective/creative-format detail — that lives in the sub-skills (campaign-setup, adset-setup, ad-setup, asset-upload). This skill decides the order, the transport, and the id plumbing.
❌ Does NOT activate ads, change Drive sharing, or invent budgets/audiences.