Research

Defines stage-specific research contract for subagent evidence reading and handoff behavior. Use when researcher subagent stage rules are needed. Do not use when the request belongs to shared RLM runtime ownership in `aidd-rlm` or direct stage command execution in `researcher`.

Owns shared flow/state runtime for stage state, progress/tasklist, and stage-result lifecycle. Use when orchestration needs canonical active-stage, progress, tasklist, or stage-result commands. Do not use when the request is about `aidd-docio` action patch mechanics or `status` read-only summaries.

End-to-end pipeline for writing ML/AI research papers — from

WEV Tesseract Skill

Voice Channel UWD Skill

Use when users ask to check a file/hash/URL/IP/domain with VirusTotal, confirm malware reputation, investigate possible false positives, or compare AV detections. Prefer hash-based lookup first and use Exa to find public VirusTotal report links.

Play/Coplay arena theory for autopoietic closure with GF(3) conservation

Framework for measuring learning dynamics in multi-agent systems and communication networks. Provides D (dimensionality), f (feedback fraction), and H₁ (topological cycles) measurements with confidence scoring. Validates across 4 domains (Topobench synthetic, GitHub networks, IES empirical, DuckDB real). Use this skill when measuring learning system characteristics, verifying convergence in multi-agent systems, comparing learning mechanisms across domains, or trading measurement services in a...

NaNoWriMo novel project database. Use when referencing the manuscript, its structure, documents, or searching its content via DuckDB.

Trifurcated Transfer Skill

1. **Triads are atomic**: Cannot create partial triads

Structured critical reasoning across 5 modes. Use when challenging ideas, plans, decisions, or proposals. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions. Triggers: play the fool, devil's advocate, challenge this, stress test, poke holes, what could go wrong, red team, pre-mortem, test my assumptions.

Pandey''s key finding: `L(N,D) = f(gzip(data))` — gzip compressibility predicts optimal compute allocation.

Apply the ScholarEval framework to systematically evaluate scholarly and research work. This skill provides structured evaluation methodology based on peer-reviewed research assessment criteria, enabling comprehensive analysis of academic papers, research proposals, literature reviews, and scholarly

Parallel thread/DuckLake discovery with XOR uniqueness from gay_seed. Finds "say" or MCP usage, cross-refs with all DuckDB sources, launches bounded parallel ops.

Rick Roderick: Philosophy Under Siege

Information Reflow Skill (ERGODIC 0)

qri-valence skill Qualia Research Institute''s Symmetry Theory of Valence (STV) for consciousness research. Maps phenomenal states to bankable assets via XY model topology, BKT transitions, and defect annihilation. Source: smoothbrains.net + QRI wiki. Use for qualia computing, valence gradient optimization, and consciousness-aware system design.

Systematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards, for manuscript and grant review across disciplines.

This skill unifies:

The **Opacity Detector** maps what can and cannot be known in a system, given an observer's structural position and epistemic capabilities.

NotebookLM Enterprise API via Discovery Engine — notebook CRUD, source management, audio overviews, flashcard pipeline integration

Synaptic substrate of biological active inference — long-term potentiation/depression (LTP/LTD) writes priors into synaptic weights = the learning landscape (Deep CANALs). A held vascular latch annealed long enough crystallizes into a neuron prior. Use when modeling consolidation, neuron priors, the inference→learning landscape write-path, or commit-to-disk of a held prediction.

Generate and drill flashcards from NotebookLM Enterprise notebooks via Gemini (Vertex AI), with Emacs UI and babashka backfill pipeline