Analyst Co-pilot (BigQuery + Redshift)
Assist analysts with safe SQL drafting, metric validation, and stakeholder-ready summaries across BigQuery and Redshift.
Skills Catalog
Filter by intent, runtime, and category to find install-ready skills.
Brand RAG Memory Bootstrap
Build a private retrieval-ready brand memory from product, campaign, and policy context for downstream agent skills.
Dashboard Generator
Generate deterministic weekly marketing dashboard outputs from normalized performance tables for BI publishing.
Dashboard QA Checker
Validate dashboard datasets with freshness, completeness, reconciliation, anomaly, and schema drift checks before publish.
Executive Narrative Writer
Convert validated BI performance outputs into concise executive narratives with actions and risks.
Playwright Agentic E2E QA
Build and maintain reusable Playwright smoke tests with planner, generator, and healer loops for web app regression checks.
Playwright VS Code Loop for Codex
Orchestrate Playwright planner, generator, and healer workflows from Codex with VS Code loop execution for reusable web UX QA.
Policy + Brand Compliance Checker
Validate ad copy, landing URLs, and UTM tracking for policy and brand compliance before campaign launch.
Weekly Performance Review BI
Chain dashboard generation, QA gating, and executive narrative writing for deterministic weekly BI reporting.
Harness Regression Evaluator
Evaluate proposed harness changes against benchmark prompts and red-team scenarios before adoption.
Harness Run Reflection
Review recent agent run logs to identify repeated misses, skipped skills, and inefficient loops in the harness.
Harness Skill Proposal
Propose new or revised harness skills and policy text from recurring failure patterns while keeping scope limited to harness assets.
Code Change Verification
Run change-aware lint, typecheck, build, and test verification based on the files and stack touched by a code change.
Coverage Gap Reporter
Parse coverage outputs, map changed files to uncovered risk areas, and recommend targeted tests.
Implementation Strategy
Plan repo-aware code changes before editing by mapping scope, commands, risks, and likely side effects.
PR Review and Draft
Review code changes for correctness, performance, security, and test completeness, then draft a structured PR summary.
Test Gap Analyzer
Identify missing unit, integration, regression, and edge-case test scenarios for recently changed code.
A/B Test Planner + Analyzer
Plan and analyze A/B tests with explicit hypotheses, sample sizing assumptions, and decision rules.
AI Output Eval Scorecard
Score AI-generated marketing outputs across accuracy, clarity, brand fit, policy compliance, and actionability.
Creative Workshop (PMax + Reels)
Generate channel-specific creative variants for Google PMax and Meta Reels with deterministic length checks.
Cross-Channel Budget Pacing Agent
Monitor pacing across paid channels, detect anomalies, and recommend budget reallocation actions.
Dynamic Creative Rules Engine
Define dynamic creative assembly rules per audience and context while enforcing brand and policy constraints.
Lifecycle Experiment Planner
Design lifecycle A/B tests with hypothesis checks, sample-size guidance, and stopping criteria.
Lifecycle Journey Trigger Designer
Design lifecycle triggers and channel sequencing for CRM journeys with measurable guardrails and rollout rules.
Meta + Google Weekly Performance Review
Analyze weekly paid media performance across Meta and Google Ads with KPI deltas and prioritized actions.
SEO to Paid Search Synergy
Turn top-performing SEO themes into paid search opportunities with keyword clustering and launch-ready recommendations.
Dependency Supply Chain Audit
Review manifests and lockfiles for vulnerable, suspicious, or overpowered dependencies and recommend mitigations.
Environment Risk Assessment
Assess whether the runtime environment is safe for autonomous agent execution and recommend isolation or approval boundaries.
Handle Untrusted Content
Treat external content, logs, tickets, webpages, and MCP responses as untrusted data and quarantine suspicious instructions.
Secrets and Credential Hygiene
Scan diffs and repository context for leaked secrets, risky credential placement, and over-broad environment exposure.