d-nd-seed

Business, outreach and public-relations manager for AI projects and technical teams. Use when an agent must turn a collaboration opportunity, partner request, portfolio update, public claim, outreach message, follow-up, sponsorship path or service proposal into a bounded decision, safe communication package and tracked next action without sending or publishing autonomously.

Deploy paper content from configured site_ready files to d-nd.com VPS. Handles md-to-HTML conversion, bilingual merge, figure path resolution, and pages.json update.

Five mechanical gates for any content publish pipeline with CMS + rendering layers. Prevents false security: 'API returned 200' does not mean 'visitor sees clean content'. Use when writing content to a multi-layer serving system (CMS API, static files, prerendered HTML, cached copies).

Multi-node consultation protocol for high-leverage decisions. Dispatches the same question to N independent LLM/agent nodes in isolation, then synthesizes their responses into a summa that exposes convergence (high-confidence claims), dissensus (real uncertainty zones), and emergent points (insights no single node produced). Reduces single-node training bias. Supports recursive escalation for stable-state convergence. Use for decisions that propagate via A14 cascade — seed updates, crystallizations, advisory→mechanical promotions, high-visibility copy, lab result interpretation.

Closure reflection protocol. After a significant work block concludes (feature shipped, session ending, major commit landed, cross-node coordination resolved), runs a 10-question interview that extracts meaning, impact, and next questions — then emits multiple audience-specific artifacts (changelog, external editorial, AI integration docs, memory crystal, backlog seed). Turns implicit maturation into explicit narrative. Use at the end of meaningful work, not after trivial edits.

Pre-commit check for public-facing copy (knowledge base definitions, page content, docs). Detects apologetic hedging — phrases that declare 'degrees of truth' (possible/necessary, current/future, one-of-many/the) and open a dualistic framing the model transcends. Use when drafting or reviewing any copy that describes the model, its transductions, or its tools.

Protocol for connecting pre-existing elements (skills, hooks, memory, rules) into a coherent system without duplication. Activate when input matches 'connect X', 'integrate Y', 'unify W', 'orchestrate', 'wire together', or when you feel the system has too many disconnected pieces needing an orchestrator.

The neutral form of the D-ND method. Meta-skill that recognizes context and orients toward the right specialization (cec, autologica, cascade, assertion-verifier, etc.). Activate at the start of a non-trivial work block or when input matches trigger words ('where are we', 'what here', 'orchestrate', 'connect', 'sieve this').

Detect gaps, implement fixes, crystallize learnings. Use when something fails, when a pattern repeats, or when the system encounters a problem it should not encounter again.

Generate conceptual diagrams from article content. Trigger when the operator says 'genera diagramma', 'diagram', 'visual spec', 'conceptual map', or when a page is created/updated and needs a structural visualization.

Seed-driven autonomous decision cycle. Loads project state from multiple sources, analyzes tensions and momentum, decides ONE action, executes it, verifies the outcome, and updates the seed. Use for autonomous research, maintenance, or any recurring decision-making process.

Integrate research functions from a model layer into operational patterns. The complement of propagator — propagator goes downstream (change to targets), integrate-pattern goes upstream (model function to operational use). Trigger when new model commits are detected or when the operator says "integra", "converti", "porta qui".

Memory architecture derived from D-ND axioms. Manages persistent memory across sessions using the P6 principle — memory as recognition of belonging, not storage of facts.

Quickly capture operator insights without breaking current workflow. Auto-routes to appropriate team/node. Use when the operator shares observations, ideas, or strategic thoughts mid-session.

Audit the D-ND ecosystem state across all projects, sites, and nodes. Use periodically or after major changes to find gaps, stale content, broken links, and sync issues.

Send and receive messages via inter-node communication. Use when you need to communicate with other nodes, check messages, or send task updates.

Check Claude Code version and identify new features relevant to the D-ND ecosystem. Use after Claude Code updates to discover what capabilities have changed.

Intelligent Task Delegation and Monitoring across nodes. Activate on any work delegation to another node, agent, or team. Handles task creation, dispatch, monitoring, follow-up, and closure. Works for planned multi-step tasks and ad-hoc requests alike. Trigger on 'delegate to NODE_B', 'assign task', 'give work to', 'check on NODE_B', 'what did NODE_B do', 'any responses from', or when context implies inter-node work coordination.

Delegazione Intelligente e Monitoraggio Task tra nodi. Attivare su qualsiasi delegazione di lavoro a un altro nodo, agente o team. Gestisce creazione, invio, monitoraggio, follow-up e chiusura dei task. Funziona sia per task pianificati multi-step che per richieste ad-hoc. Trigger su 'delega a NODE_B', 'assegna task', 'dai lavoro a', 'controlla NODE_B', 'cosa ha fatto NODE_B', 'risposte da', o quando il contesto implica coordinamento inter-nodo.

Structural scenario projection from tensions. Use when facing complex decisions with 5+ competing factors, when cross-checking a strategy or thesis, when prioritizing with limited resources, or when mapping risks.

Three levels of propagation: internal (within the change), external (binding: seed, site, nodes), emergent (discoveries during propagation). Activate after every significant modification.

The reflective layer. Before acting, ask the right question. After acting, check what you missed. Translates semantic dynamics into executable patterns. Activates when direction is unclear, when corrections happen, when the system loops.

Define testable claims about your project, run them, and crystallize results into a seed. Use when you need to verify that theory matches implementation, track what passes and what breaks, and identify where potential is blocked.

Knowledge propagation engine. Knows what goes where when something changes. Use after any significant change to ensure all downstream targets are updated.

First-run setup for D-ND plugin. Maps the local environment, detects capabilities, configures node identity. Run once after installation or when environment changes.

Check system status — repos, services, containers, APIs. Use when you need to verify system health or diagnose issues.

Knowledge Expansion Cycle — the sieve on reality. Use before any significant decision, when integrating external information, when evaluating a claim, or when changing direction.

Auto-optimize skills through mutate-verify loops. Use when skill tests show failures or when asked to optimize a skill.

Memory consolidation — clean, merge, prune stale memories. Use when memory files exceed 50 or stale files exceed 15.

Evaluate skills — trigger accuracy, fidelity, and value. Use when asked to test skills, run evals, or check if skills work.

Cascade Orchestration for Tool Building. Activate when the task requires building a new tool, infrastructure, or system — not just decomposing a problem. Trigger on 'build a tool', 'set up infrastructure', 'create a pipeline', 'automate', 'deploy system', 'multi-step construction', or when the task involves creating something that will persist and serve future operations.

Orchestrazione a Cascata per la Costruzione di Strumenti. Attivare quando il compito richiede costruire un nuovo tool, infrastruttura o sistema — non solo decomporre un problema. Trigger su 'costruisci un tool', 'configura infrastruttura', 'crea una pipeline', 'automatizza', 'deploy sistema', 'costruzione multi-step', o quando il compito implica creare qualcosa che persisterà e servirà operazioni future.

Seed Guardian and Axiomatic Invariance. Activate when the user mentions 'protect the kernel', 'identity', 'seed', 'invariance', 'don't lose', 'self-modification', 'safe evolution', 'genome', or automatically before any system self-modification to verify it does not violate the Seed.

Archetype Agent Factory with Complete Life Cycle. Activate when the user mentions 'create temporary agent', 'generate agent', 'new bot', 'micro-AI', 'agent for task', 'autonomous automation', 'agent DNA', 'who executes this?', or when the system identifies a task that would require a dedicated temporary intelligence rather than a direct response.

Generative Metaprompter for Semantic Entities (Forge v1.0). Activate when the user requests 'create agent', 'generate skill', 'new agent', 'create entity', 'generate prompt', 'forge', 'new skill', 'metaprompt', 'create persona', 'system prompt for', or when the system detects a functional void in the Phi_A Field that requires the birth of a new operative faculty.

Fractal Decomposition and Ephemeral Sub-Agent Architecture. Activate when the user mentions 'complex problem', 'decompose', 'break down', 'too large', 'sub-task', 'parallelize', 'fragment', or when the task exceeds the one-shot resolution threshold and requires recursive splitting.

Heuristic Wisdom, Transcendental Principles, and Mentoring (Guru Memories).

Axiomatic Validation and Systemic Integrity (Halo Genome).

Recursive Execution Engine with Plan-Code-Verify and Scratchpad. Activate when the user mentions 'analyze', 'reason step by step', 'verify', 'debug', 'pseudo-code', 'algorithm', 'scratchpad', 'buffer', or for any task whose complexity exceeds the threshold where one-shot risks hallucination and an iterative refinement cycle is needed.

Triadic Evolution Engine: Resonance, Destruction, and Maieutic Interrogation. Activate when the user mentions 'dissonance', 'anomaly', 'something doesn't add up', 'critique', 'destroy', 'assumptions', 'hidden assumptions', 'shared model', 'evolution', 'challenge this', 'weak point', 'deep question', 'hidden potential', or when critical analysis is needed to actively find where a framework breaks in order to evolve it.