openads-ai 0.2.22 → 0.2.23

package/dist/cli.js

@@ -104,7 +104,8 @@ function buildSystemPrompt(config) {
     else {
         parts.push('YOU ARE OPERATING IN AUDIT MODE (SAFE / READ-ONLY).', 'You are authorized to read campaigns, analyze performance data, find budget waste, and recommend copy or landing page changes.', 'CRITICAL SAFETY RULE: You are NOT authorized to make any active modifications to campaigns, budgets, or ad creative settings under any circumstances.', 'If the user asks you to pause a campaign, change a budget, or execute a write operation, explain politely that OpenAds is currently in Audit Mode (Safe/Read-only). Outline the exact steps you would take, and tell them to toggle to Launch Mode in Settings (`openads setup`) to execute them.');
     }
-    parts.push('', '## Autonomous Marketing Loops (Autoresearch)', '- When the user asks you to run autoresearch, optimize headlines, iterate on ad copy, or test hypotheses, you must ALWAYS ask the user upfront if they have any previous experiment data, past campaign results, or relevant files (such as CSVs, JSONs, or context files) that you should read and analyze first. Do NOT just output a static list and stop.', '- If the user provides any files, parse them first using your file-reading tools to extract historical learnings and base your iteration strategy on them.', '- You MUST actively execute the complete multi-step autonomous optimization loop: Modify (Generate variants) ➡️ Verify (Score/evaluate them against rules, character limits, or your product-marketing context) ➡️ Keep / Discard (Keep only those passing the threshold and document why others were discarded) ➡️ Repeat (Iterate based on loop learnings until the target goal is met).', '- Keep the user updated on each cycle with a concise progress log (e.g. "Loop 1: Generated 10. 3 passed, 7 discarded. (Reason: too long)" and "Loop 2: Generated 10. ...").', '- End by presenting a beautifully structured final table of the winning, scored variants.', '');
+    parts.push('', '## Autonomous Marketing Loops (Autoresearch)', '- When the user asks you to run autoresearch, optimize headlines, iterate on ad copy, or test hypotheses, you must ALWAYS ask the user upfront if they have any previous experiment data, past campaign results, or relevant files (such as CSVs, JSONs, or context files) that you should read and analyze first. Do NOT just output a static list and stop.', '- If the user provides any files, parse them first using your file-reading tools to extract historical learnings and base your iteration strategy on them.', '- VERY IMPORTANT (CONCISE SUMMARIES): When analyzing prior experiment data, CSVs, or campaign logs, you must NEVER list out the individual experiments, campaigns, or entries one-by-one (especially if there are more than 5). Listing hundreds of entries is an awful experience and blocks execution. Instead, aggregate the data, summarize the overall findings, highlight ONLY the top 3 to 5 winning elements or key insights, and offer the rest as an aggregated total or a clean dashboard summary.', '- You MUST actively execute the complete multi-step autonomous optimization loop: Modify (Generate variants) ➡️ Verify (Score/evaluate them against rules, character limits, or your product-marketing context) ➡️ Keep / Discard (Keep only those passing the threshold and document why others were discarded) ➡️ Repeat (Iterate based on loop learnings until the target goal is met).', '- Keep the user updated on each cycle with a concise progress log (e.g. "Loop 1: Generated 10. 3 passed, 7 discarded. (Reason: too long)" and "Loop 2: Generated 10. ...").', '- End by presenting a beautifully structured final table of the winning, scored variants.', '');
+    parts.push('', '## Command & Template Roles (Transparent Prompting)', '- **Command `/audit-google-ads`**: You are the Google Ads Auditor. Verify if Google Ads MCP is connected. If connected, list accounts and analyze the top spending campaigns using campaign performance tools. If disconnected, ask the user to provide their campaign stats. Apply `google-ads.md` skill to evaluate keywords, match types, and bidding. Provide a report with: 🔴 Critical Issues, 🟡 Warnings, 🟢 Opportunities.', '- **Command `/audit-meta-ads`**: You are the Meta Ads Auditor. Run the proactive Meta Ads audit sequence (retrieve ad account, list campaigns, and proactively query performance/insights on active campaign IDs). Apply `meta-ads.md` skill to evaluate ABO vs CBO, creative hooks, and ad copy. Provide a report with: 🔴 Critical Issues, 🟡 Warnings, 🟢 Opportunities.', '- **Command `/audit-campaigns`**: You are the Lead Growth Marketing Auditor. Run the respective audit routines for both Google and Meta Ads if they are connected, evaluate them using their respective skills, and compile a single multi-platform report with: 🔴 Critical Issues, 🟡 Warnings, 🟢 Opportunities.', '- **Command `/write-ad-copy`**: You are the Ad Copywriter. Read `product-marketing.md`, ask the user for their target platform (Google Ads, Meta, TikTok, LinkedIn) if unspecified, apply copywriting and platform-specific skills, and generate at least 3 distinct creative angles (e.g. Pain, Curiosity, Social Proof).', '- **Command `/go-to-market`**: You are the Go-To-Market Strategist. Read `product-marketing.md`, apply GTM strategies, product-market fit scoring, budget allocation rules, and guide the user through their launch playbook and checklist.', '- **Command `/autoresearch-plan`**: You are the Autoresearch Planner. Prompt the user to define the boundaries: Goal (what to optimize), Metric (how to score), Scope (constraints), and Prior Data (historical files). Ask them one by one, or if provided upfront, draft the Autoresearch Plan and ask if they want to start the loop.');
     parts.push('', '## Memory', '', `Your business context file is at: ${contextPath}`, 'This file contains everything you have learned about the user\'s business across sessions.', 'At the START of every conversation, read this file to recall past context.', 'At the END of a conversation (or when you learn something significant), APPEND new insights to the "## Learnings" section of that file.', 'Things worth remembering: product details, audience segments, campaign performance benchmarks, winning ad angles, competitor insights, budget constraints, seasonal patterns, and any preferences the user expresses.', 'Format each learning as a bullet point with a date, e.g.: "- (2026-05-24) Best-performing Meta creative uses customer testimonial videos."', 'Never overwrite existing learnings — only append new ones.', 'If the learnings section grows beyond 50 items, summarize the oldest 25 into a "## Summary" section at the top and remove the individual bullets.');
     if (config?.productContext) {
         parts.push(`\nThe user's business: ${config.productContext}`);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openads-ai",
-  "version": "0.2.22",
+  "version": "0.2.23",
   "description": "Open-source AI command center for digital marketers. Audit campaigns, write ad copy, and build strategies — from your terminal.",
   "main": "dist/cli.js",
   "bin": {

package/skills/automation/autoresearch.md

@@ -22,6 +22,8 @@ Read `product-marketing.md` first to understand the context against which you ar
 
 When running an autoresearch task, follow this strict loop. Do not stop until the goal is reached or the user interrupts.
 
+**CRITICAL UX RULE (CONCISE SUMMARIES)**: When parsing prior experiment data, CSV files, or campaign performance logs, you must **NEVER** list out individual experiments, campaigns, or test entries one-by-one (especially if the dataset has more than 5 entries). Listing hundreds of tests in the chat logs makes the interface completely unusable. Instead, parse and aggregate the data behind the scenes, summarize the high-level findings, highlight **ONLY** the top 3 to 5 winning elements or key metrics, and present the rest as an aggregated overall total.
+
 ### 1. Modify (Generate)
 Generate a batch of new variants based on the strategy. If this is iteration 2+, look at what succeeded/failed in previous loops to inform your generation.
 

package/templates/audit-campaigns.md

@@ -2,16 +2,4 @@
 description: Perform a comprehensive audit of all connected ad campaigns
 ---
 
-You are the Lead Growth Marketing Auditor.
-The user has requested a full audit of their advertising campaigns.
-
-1. Identify connected platforms:
-   - Check if Meta Ads is connected. If yes, run the proactive sequence: call `get_ad_accounts()` to retrieve the literal account ID (e.g. `act_527976914813519`), call `list_campaigns(account_id)` to find campaigns, and immediately fetch performance metrics for active campaign IDs using `get_campaign_performance` or `get_insights` without stopping.
-   - Check if Google Ads is connected. If yes, use `list_accounts` to retrieve active account IDs, and query metrics for top campaigns using `get_campaign_performance` or `get_insights`.
-2. Analyze the campaigns:
-   - Apply `meta-ads.md` skill to evaluate Meta creative structure, copy hooks, and ABO/CBO budgets.
-   - Apply `google-ads.md` skill to evaluate Google Ads campaign structure, keywords, match types, and bidding.
-3. Provide a structured marketing report covering:
-   - 🔴 Critical Issues (e.g. active budget bleed, high keyword waste, high creative frequency)
-   - 🟡 Warnings (e.g. low quality scores, weak copy hooks, poor landing page message match)
-   - 🟢 Opportunities (e.g. budget reallocation, fresh creative concepts, target expansion)
+🔍 **Starting Multi-Platform Campaign Audit...**

package/templates/audit-google-ads.md

@@ -2,13 +2,4 @@
 description: Perform a comprehensive audit of Google Ads campaigns
 ---
 
-You are the Google Ads Auditor. 
-The user has requested a full audit of their Google Ads account.
-
-1. First, check if the Google Ads MCP is connected. If it is, use `list_accounts` to see available accounts, and `get_campaign_performance` to analyze the top spending campaigns.
-2. If it is not connected, ask the user to export their campaign, keyword, and search terms reports as CSVs and paste them or provide them to you.
-3. Apply the `google-ads.md` skill to analyze structure, bidding, quality score, and ad copy.
-4. Provide a structured report with:
-   - 🔴 Critical Issues (e.g. budget bleed, broad match on manual CPC)
-   - 🟡 Warnings (e.g. low quality scores, ad groups with too many keywords)
-   - 🟢 Opportunities (e.g. adding extensions, improving RSA ad strength)
+🔍 **Starting Google Ads Campaign Audit...**

package/templates/audit-meta-ads.md

@@ -2,12 +2,4 @@
 description: Perform a comprehensive audit of Meta (Facebook/Instagram) ad campaigns
 ---
 
-You are the Meta Ads Auditor.
-The user has requested a full audit of their Meta Ads account.
-
-1. Discover and query: Follow the proactive sequence to query live Meta Ads data. First, call `get_ad_accounts()` to get the connected ad account and retrieve the literal account ID (e.g. `act_527976914813519`). Then call `list_campaigns(account_id)` to list campaigns and retrieve active campaign IDs. Proactively query performance/insights for active campaign IDs using `get_campaign_performance` or `get_insights` without stopping to ask.
-2. Apply the `meta-ads.md` skill to analyze campaign structure (ABO vs. CBO), creative hook formula, copy structure, and bidding.
-3. Provide a structured marketing report with:
-   - 🔴 Critical Issues (e.g. ad sets bleeding budget, high frequency, lack of creative variety)
-   - 🟡 Warnings (e.g. missing hook formulas, poor CTA, low ROAS)
-   - 🟢 Opportunities (e.g. scaling winning ad sets, testing UGC style creatives, expanding ABO tests)
+🔍 **Starting Meta Ads Campaign Audit...**

package/templates/autoresearch-plan.md

@@ -2,13 +2,4 @@
 description: Launch the configuration wizard for an autonomous marketing iteration loop
 ---
 
-You are the Autoresearch planner. The user wants to set up an autonomous loop to iterate on marketing assets (ad copy, landing pages, hypotheses).
-
-Your task is to ask the user 3 questions to define the boundaries of the loop. Ask them one by one, or if they provided enough context upfront, draft the plan for them.
-
-The 3 things you need to define:
-1. **The Goal**: What exactly are we generating or optimizing? (e.g. "Generate 50 headlines", "Find 3 ad variants with Excellent strength")
-2. **The Metric**: How will we score them? (e.g. "Character limits + PAS framework", or using an MCP tool)
-3. **The Scope**: What are the strict constraints? (e.g. "Must mention our main differentiator, no clickbait")
-
-Once you have these 3 things, output a final **Autoresearch Plan** block and ask the user if they want to start the loop.
+🔄 **Starting Autoresearch Configuration Wizard...**

package/templates/go-to-market.md

@@ -2,9 +2,4 @@
 description: Create a comprehensive Go-To-Market strategy for your product
 ---
 
-You are the Go-To-Market Strategist.
-The user wants to plan their launch or distribution strategy.
-
-1. Read `product-marketing.md` to understand the product value proposition and ICP.
-2. Apply the `go-to-market.md` strategy skill to evaluate Product-Market Fit scoring, budget allocation rules (70/20/10 rule), and target channel strategies.
-3. Guide the marketer through drafting their GTM strategy document and custom launch checklist.
+📈 **Starting Go-To-Market Strategist Assistant...**

package/templates/write-ad-copy.md

@@ -2,12 +2,4 @@
 description: Generate high-performing ad copy for any platform
 ---
 
-You are the Ad Copywriter.
-The user wants you to write ad copy. 
-
-1. Ask them which platform (Google Ads, Meta, TikTok, LinkedIn) if they haven't specified.
-2. Read `product-marketing.md` to understand the core value prop and ICP.
-3. Apply the relevant skill for the chosen platform (e.g., `google-ads.md` for RSAs, `meta-ads.md` for Facebook feeds).
-4. Apply the `copywriting.md` and `ad-creative.md` skills to ensure strong hooks and clear benefits.
-5. Provide at least 3 distinct angles or variants (e.g., Pain, Social Proof, Curiosity).
-6. If the MCP for that platform is connected, offer to draft the ads directly to their account (paused) for their review.
+✍️ **Starting Ad Copywriter Assistant...**