canopy

Apple Search Ads (ASA) deep analysis for mobile app advertisers. Evaluates campaign structure, bid health, Creative Sets, MMP attribution, budget pacing, TAP coverage (Today/Search/Product Pages), and goal CPA benchmarks by country. Triggers on: "Apple Search Ads", "ASA", "App Store ads", "Apple ads", "Search Ads", "iOS app ads"

Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, and Microsoft Ads accounts. Generates health score per platform and aggregate score. Triggers on: "audit", "full ad check", "analyze my ads", "account health check", "PPC audit", "ad account audit"

Budget allocation and bidding strategy review across all ad platforms. Evaluates spend distribution, bidding strategy appropriateness, scaling readiness, and identifies campaigns to kill or scale. Uses 70/20/10 rule, 3x Kill Rule, and 20% scaling rule. Triggers on: "budget allocation", "bidding strategy", "ad spend", "ROAS target", "media budget", "scaling", "kill list"

Competitor ad intelligence analysis across Google, Meta, LinkedIn, TikTok, and Microsoft. Analyzes competitor ad copy, creative strategy, keyword targeting, estimated spend, and identifies competitive gaps and opportunities. Triggers on: "competitor ads", "ad spy", "competitive analysis", "competitor PPC", "ad intelligence", "competitor research"

Campaign concept and copy brief generator for paid advertising. Reads brand-profile.json and optional audit results to produce structured campaign concepts, messaging pillars, and copy briefs. Outputs campaign-brief.md. Run after /ads dna and before /ads generate. Triggers on: "create campaign", "campaign brief", "ad concepts", "write ad copy", "campaign strategy", "ad messaging", "creative brief", "generate concepts"

Cross-platform creative quality audit covering ad copy, video, image, and format diversity across all platforms. Detects creative fatigue, evaluates platform-native compliance, and provides production priorities. Triggers on: "creative audit", "ad creative", "creative fatigue", "ad copy review", "ad design", "creative review", "creative health"

Brand DNA extractor for paid advertising. Scans a website URL to extract visual identity, tone of voice, color palette, typography, and imagery style. Outputs brand-profile.json. Run before /ads create or /ads generate for brand-consistent creative. Triggers on: "brand DNA", "brand profile", "extract brand", "brand identity", "brand colors", "analyze brand", "brand style guide", "brand voice"

AI image generation for paid ad creatives. Reads campaign-brief.md and brand-profile.json to produce platform-sized ad images using Gemini (default) or a configured provider. Requires GOOGLE_API_KEY or ADS_IMAGE_PROVIDER + matching key. Triggers on: "generate ads", "create images", "make ad creatives", "generate visuals", "create ad images", "generate campaign images", "make the images", "generate from brief"

Google Ads deep analysis covering Search, Performance Max, Display, YouTube, and Demand Gen campaigns. Evaluates 74 checks across conversion tracking, wasted spend, account structure, keywords, ads, and settings. Triggers on: "Google Ads", "Google PPC", "search ads", "PMax", "Performance Max", "Google campaign", "Google audit"

Landing page quality assessment for paid advertising campaigns. Evaluates message match, page speed, mobile experience, trust signals, form optimization, and conversion rate potential. Triggers on: "landing page", "post-click experience", "landing page audit", "conversion rate", "landing page optimization", "LP audit"

LinkedIn Ads deep analysis for B2B advertising. Evaluates 25 checks across technical setup, audience targeting, creative quality, lead gen forms, and bidding strategy. Includes Thought Leader Ads, ABM, and predictive audiences. Triggers on: "LinkedIn Ads", "B2B ads", "sponsored content", "lead gen forms", "InMail", "LinkedIn campaign", "LinkedIn audit"

Meta Ads deep analysis covering Facebook and Instagram advertising. Evaluates 46 checks across Pixel/CAPI health, creative diversity and fatigue, account structure, and audience targeting. Includes Advantage+ assessment. Triggers on: "Meta Ads", "Facebook Ads", "Instagram Ads", "Advantage+", "Meta campaign", "Meta audit", "FB ads"

Microsoft/Bing Ads deep analysis covering search, Performance Max, Audience Network, and Copilot integration. Evaluates 20 checks with focus on Google import validation, unique Microsoft features, and cost advantage assessment. Triggers on: "Microsoft Ads", "Bing Ads", "Bing PPC", "Copilot ads", "Microsoft campaign", "Bing audit"

Product photography enhancement for ad creatives using AI image generation. Takes a product image and generates 5 professional photography styles for ad use: Studio, Floating, Ingredient, In Use, and Lifestyle. Requires GOOGLE_API_KEY or configured ADS_IMAGE_PROVIDER. Triggers on: "product photo", "product photography", "photoshoot", "enhance product image", "product shoot", "product photos for ads", "studio shot", "lifestyle photo"

Strategic paid advertising planning with industry-specific templates. Covers platform selection, campaign architecture, budget planning, creative strategy, and phased implementation roadmap. Triggers on: "ad plan", "ad strategy", "campaign planning", "media plan", "PPC strategy", "advertising plan", "media strategy"

TikTok Ads deep analysis covering creative quality, tracking, bidding, campaign structure, and TikTok Shop. Evaluates 25 checks with emphasis on creative-first strategy, safe zone compliance, and Smart+ campaigns. Triggers on: "TikTok Ads", "TikTok marketing", "TikTok Shop", "Spark Ads", "Smart+", "TikTok campaign", "TikTok audit"

YouTube Ads specific analysis covering campaign types, creative quality, audience targeting, and measurement. Evaluates video ad performance across skippable, non-skippable, bumper, Shorts, and Demand Gen formats. Triggers on: "YouTube Ads", "video ads", "pre-roll", "bumper ads", "YouTube campaign", "Shorts ads", "YouTube audit"

Evaluate retrieval and generation quality in RAG pipelines. Separate scoring for retrieval (recall, precision, MRR) and generation (faithfulness, relevance, completeness). End-to-end pipeline assessment with bottleneck identification. Triggers on: "eval rag", "rag evaluation", "retrieval evaluation", "rag quality", "rag metrics"

Design binary pass/fail LLM-as-Judge evaluators. Structured prompt engineering for evaluation: criteria definition, rubric construction, few-shot calibration, and bias mitigation. Produces a ready-to-deploy judge prompt with scoring instructions. Triggers on: "judge prompt", "llm judge", "evaluator prompt", "scoring prompt", "grading rubric"

Generate diverse synthetic test inputs via dimension-based tuple generation. Defines variation dimensions, enumerates combinations, filters for relevance, and produces labeled test cases. For LLM eval pipelines, training data augmentation, and stress testing. Triggers on: "synthetic data", "generate test data", "test inputs", "data generation", "augment data"

Calibrate LLM-as-Judge evaluators against human labels. Computes TPR, TNR, precision, recall, F1, and Cohen's kappa. Detects systematic biases and recommends prompt corrections. Produces a calibration report with confidence intervals. Triggers on: "validate evaluator", "calibrate judge", "judge accuracy", "evaluator validation", "judge metrics"

Guided analysis of LLM traces to categorize and pattern-match failures. Reads execution traces, classifies failure modes, detects recurring patterns, and produces actionable taxonomy of errors. For diagnosing why an LLM system fails and where to focus improvement effort. Triggers on: "error analysis", "analyze failures", "failure patterns", "trace analysis", "debug eval"

Audit an LLM evaluation pipeline for correctness, coverage, and reliability. 6 diagnostic areas with structured Check/Finding output. Produces prioritized findings by severity and recommends next skills to run. Catches common eval pitfalls before they corrupt your metrics. Triggers on: "eval audit", "audit evals", "evaluation audit", "check eval pipeline", "eval health"

Create animation-rich HTML presentations from scratch or convert PowerPoint. Progressive disclosure pipeline: content discovery, style discovery, generation. Zero-dependency single HTML file output. Anti-AI-slop guardrails for natural, professional presentations. Triggers on: "slides", "presentation", "slide deck", "create slides", "convert pptx", "html presentation"

Transform any GUI application into an agent-controllable CLI. 7-phase pipeline: analyze the GUI, design CLI commands, implement adapters, plan tests, write tests, document, and publish. Produces a standalone CLI tool that wraps GUI functionality for automation. Triggers on: "cli anything", "gui to cli", "make cli", "wrap gui", "automate application"

Build custom annotation UIs for human review of agent traces, LLM outputs, and labeled data. Generates a self-contained HTML interface for reviewing, labeling, comparing, and exporting judgments. For calibrating evals, auditing agent behavior, and building gold-standard datasets. Triggers on: "review interface", "annotation ui", "labeling interface", "review ui", "human review"

Autonomous iterative improvement loop. Agent modifies code, verifies against metrics, keeps improvements or reverts failures, and repeats. Uses git as memory — each change is committed, measured, and kept or discarded. Runs until a target metric is hit or max iterations reached. Triggers on: "autoresearch", "auto improve", "iterative improvement", "autonomous loop", "hill climb"

Branch code review with structured scoring against project guidelines. Produces categorized findings with severity levels and LLM-generated fix prompts. Quality gate: only posts review to PR if score meets threshold. Triggers on: "code review", "review branch", "review PR", "review changes", "score code"

Guided spec creation through 9 phases from discovery to testing strategy. Supports spec types: library, feature, change. Produces a complete specification document with requirements, architecture, constraints, and YAML test data. Interactive or autonomous modes. Triggers on: "create spec", "write spec", "spec out", "specification", "design document"

Authorize agent payments via Machine Payments Protocol (MPP). Handles microtransactions, API purchases, service subscriptions within budget governance. Triggered by pay, purchase, buy, transaction, payment, MPP, commerce.

Generate structured documents from composition templates. Combines reference templates with live data to produce reviewable output artifacts. Triggered by compose, document, generate report, create brief, write proposal.

Language Agent Tree Search - Monte Carlo planning - 92.7% on HumanEval

Self-learning system based on SICA, VIGIL, and Mem0 patterns. Auto-triggers after task completion. Captures patterns, consolidates memory, generates skills, recovers from errors.

Self-improving prompts through meta-level optimization

Optimize token usage through prompt caching and compression

Thought-Action-Observation loop for transparent reasoning

Self-correction via critique loop - 18.5 percentage point improvement

Sample multiple paths, select most consistent - +17.9% on GSM8K

Parallel generation through skeleton-first approach for 2x speedup

Multi-path reasoning with evaluation and backtracking - 74% success on complex tasks