cardinalconseils

Ecosystem monitoring — breaking changes, deprecations, security alerts, opportunity tracking, bulletin generation.

Project kickstart — idea to scaffolded project: research, monetization, brand, ERD, architecture, deploy config.

Unified Dashboard SaaS Build Sequence — 12-stage methodology for multi-role SaaS products (super admin/admin/user/vendor). Enforces single application with role-gated dashboard visibility, never separate dashboards per role, generated from one permissions…

Agentic System Build Sequence — 15-stage ordered methodology for building AI agent systems, autonomous agents, multi-agent orchestration, tool-calling loops. Enforces state machine and tool inventory design before architecture decisions, and architecture…

Attractor pipeline orchestrator — YAML node handlers, auto-decision criteria, review-merge-loop instructions for the CKS sprint lifecycle

PRD lifecycle, feature planning, 5-phase cycle: discover, design, sprint, review, release, roadmap, acceptance criteria.

CKS concept feasibility evaluation — scoring rubrics, dual-mode detection, pillar frameworks, Go/Defer/Reject thresholds, and specialist-trigger conditions. Use when evaluating whether a concept should be added to the CKS plugin or a CKS-powered project.

Integrates the headroom MCP server for input token compression. Use when compressing tool stdout, file reads, Bash output, RAG chunks, or any large payload entering the context window. Exposes headroom_compress, headroom_retrieve, headroom_stats tools.…

Use when the user wants to build an AI agent, voice agent, chat agent, multi-agent system, RAG pipeline, or MCP server. Also use when the user mentions 'AI agent', 'voice agent', 'chat agent', 'RAG', 'retrieval-augmented generation', 'MCP server',…

Use when the user wants to define KPIs, build a metrics framework, identify leading indicators, create a risk register, or set up governance triggers. Also use when the user mentions 'KPIs', 'metrics framework', 'leading indicators', 'lagging indicators',…

Use when the user wants to create product photography, brand imagery, or commercial photos using AI image generation. Also use when the user mentions 'product photography', 'AI photo', 'brand imagery', 'photo direction', 'gpt-image-1', 'image generation…

Use when the user wants to create AI-generated video content, ads, social clips, or product demos using Kling or similar video generation APIs. Also use when the user mentions 'AI video', 'Kling', 'video generation', 'text to video', 'image to video', 'video…

Use when the user wants to understand compliance requirements, identify regulatory triggers, or know what artifacts are required for GDPR, PCI, HIPAA, or SOC 2. Also use when the user mentions 'compliance', 'GDPR', 'PCI DSS', 'HIPAA', 'SOC 2', 'data privacy',…

Use when the user wants to build programmatic SEO pages, template-driven content at scale, location pages, comparison pages, or data-driven landing pages. Also use when the user mentions 'programmatic SEO', 'pSEO', 'template pages', 'location pages',…

Use when the user wants to build or improve their revenue operations, lead scoring, sales funnel, CRM hygiene, or pipeline velocity. Also use when the user mentions 'RevOps', 'MQL', 'SQL', 'lead lifecycle', 'pipeline velocity', 'CRM hygiene', 'attribution',…

Use when the user wants to create sales materials, pitch decks, battle cards, one-pagers, objection handling guides, or demo scripts. Also use when the user mentions 'pitch deck', 'sales deck', 'one-pager', 'battle card', 'objection handling', 'demo script',…

Designs AI agent architecture for Make.com scenarios. Determines model selection, tool inventory, memory strategy, looping pattern, and output contract. Called by scenario-orchestrator during System Design phase when ai_required is true, or directly by…

Pre-push blueprint JSON review for Make.com scenarios. Checks structural integrity, connection IDs, mapper references, filter logic, and error handler coverage before any scenario_update call.

Fetches exact Make.com module documentation before any blueprint is designed. Returns precise field names, required vs optional parameters, data types, and enumerated values. Eliminates improvisation and ensures first-shot accuracy.

Decides whether an automation should be built as a deterministic Make.com scenario, as an AI Agent, or as a hybrid (scenario shell with an AI Agent at the one indeterministic step). Produces a Routing Verdict recorded in the plan. Called before any blueprint…

Taxonomy-first failure diagnosis for Make.com. Loads the failure taxonomy, classifies errors by pattern code, states expected vs actual, and prescribes the exact fix. Always consult this before guessing.

Live retrieval of Make.com product documentation from help.make.com, with a local cache. Answers conceptual questions — routers, iterators, error-handler directives, operations and billing, AI Agent semantics, plan limits — that the MCP module docs do not…

Automation portfolio discovery interview. Guides the user to articulate every automation they need before any design begins. Produces a prioritized portfolio list. Called by scenario-orchestrator during the Kickstart phase.

Writes the kickstart plan document from the collected portfolio. Called by kickstart-planner agent at end of Phase 2. Produces the plan file that the user reviews and approves before any artifacts are generated.

Build a Cardinal Conseils artifact from a brief or raw content — runs the Cardinal Brief gate, builds index.html + README.md + meta.json, updates catalogs, commits, opens PR.

React Flow workflow builder template — 3 variants (generic, ai-agent, payfacto-veloce). Used by artifact-builder skill when type is workflow-builder.

Transforms any input — a video, article, framework, product, raw idea, or shared link — into a structured implementation guide PMC can use himself, sell to clients, package as a product, or teach as a framework. Asks up front: venture (Cardinal Conseils,…