← Plugin catalog
Productivity
Adszy
Adszy v1.0.0
Publisher description
From the marketplace listing
Adszy provides read-only PPC analysis of accounts connected through Adszy, including account health, budget pacing, wasted spend, disapprovals, anomalies, auction insights, and period comparisons. It works with Google Ads accounts and cannot create or change campaigns. Adszy is independently developed and is not endorsed or operated by Google.
Language: English · Automatically detected from descriptions.
Files & skills
File archives
Plugin package8 files · 2.82 KBBrowse files →
Skill instructions
account-health-triage1.52 KB
--- name: account-health-triage description: Diagnose the current health of an authorised Google Ads account through Adszy MCP. Use for account check-ups, "what needs attention", budget-pacing, disapproval, anomaly, audit, or sudden-performance questions. --- # Account Health Triage Use Adszy's read-only tools to separate verified issues from healthy or unobserved areas. ## Workflow 1. If the account is ambiguous, call `list_ad_accounts` and ask the user to choose. Never guess an account. 2. Establish the requested window. Use `get_account_summary` for headline performance, then call only the relevant diagnostic tools: - `get_budget_pacing` for spend delivery. - `get_anomalies` for detected changes. - `get_disapprovals` for serving restrictions. - `get_account_audit` for the latest cached structural audit. 3. Treat a cached audit window as authoritative. If `windowMismatch` is true, state its actual window and use `get_account_summary` for the user's requested period. 4. Distinguish: - verified issue; - healthy observed surface; - no data or unvalidated surface. 5. Return a prioritised brief: issue, evidence, likely impact, and next safe action. ## Guardrails - Never claim Adszy changed the account; every MCP tool is read-only. - Do not infer causation from correlation. Label plausible explanations as hypotheses. - State dates, currency, and material sample limitations. - Do not describe an empty result as healthy. - Keep account identifiers out of the prose unless the user needs them to disambiguate.
Referenced files: 1
performance-brief1.23 KB
--- name: performance-brief description: Create an evidence-backed Google Ads performance brief through Adszy MCP. Use for week-over-week, month-over-month, or year-over-year comparisons, stakeholder updates, client reports, and concise performance recaps. --- # Performance Brief Turn Adszy's read-only metrics into a concise stakeholder-ready narrative. ## Workflow 1. Resolve the account with `list_ad_accounts` when it is ambiguous. 2. Call `compare_periods` with the user's requested comparison. 3. Call `get_account_summary` for the current-period campaign breakdown. 4. Use a focused diagnostic tool only when the comparison needs support, such as `get_change_history`, `get_budget_pacing`, or `get_anomalies`. 5. Write: - executive summary; - key metric changes; - campaign drivers; - risks or unknowns; - recommended next checks. ## Guardrails - State both date ranges and the account currency. - Use absolute and percentage changes where available. - Do not invent explanations for movements. Separate measured drivers from hypotheses. - Flag low volume, missing conversion data, and attribution limitations. - Do not imply that Adszy applied any recommendation. - Keep the brief readable without hiding material negative findings.
Referenced files: 1
wasted-spend-review1.33 KB
--- name: wasted-spend-review description: Find and explain likely wasted Google Ads spend through Adszy MCP. Use for search-term reviews, negative-keyword candidates, irrelevant-query analysis, zero-conversion spend, or requests to reduce PPC waste. --- # Wasted Spend Review Build a read-only candidate list grounded in search-term and keyword evidence. ## Workflow 1. Resolve the account with `list_ad_accounts` when needed. 2. Call `get_negative_keyword_candidates` for the requested window. 3. Use `get_search_terms` to verify the highest-spend terms and `get_keywords` only when keyword context is needed. 4. Rank candidates by: - clear intent mismatch; - spend with zero conversions; - high engagement with no conversion; - low-spend terms that need human review. 5. Return term, evidence, why it may be waste, confidence, and recommended review action. ## Guardrails - Never claim a negative keyword was added or applied. - Do not treat every zero-conversion term as irrelevant; consider spend, clicks, window length, conversion lag, and business intent. - Keep strict mismatches separate from judgement calls. - State the analysis dates and currency. - Describe savings as avoidable historical spend, not guaranteed future savings. - If the user asks to make changes, explain that Adszy MCP is read-only and provide a review list instead.
Referenced files: 1
Package details
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
- Package author
- Adszy
Package observed Oct 2, 2026.
Technical details
- First seen
- Sep 30, 2026 · 22:02 UTC
- Last seen
- Oct 2, 2026 · 00:00 UTC
- Collection status
- Collected
plugin_asdk_app_6a667d5d9f0881918d77cea47cc30370
Download plugin data (JSON)