← all publishers

mitchuski

@mitchuski source repo

113 published skills · page 2 of 2

  1. Agentprivacy Wiki Compact References · mitchuski
    Compacting a page's reference-item section by replacing forked reference items with compact `[[wikilink]]` bullets inside a `# See` markdown item. Activates when tidying a page heavy with forked reference items. Part of the git-less onboarding/distribution layer kept by the Librarian 🗃️ in the Tower's Wikis.
    0
    installs
  2. Agentprivacy Wiki LLM Knowledge Base · mitchuski
    Building and maintaining a persistent, LLM-maintained knowledge base — the LLM-Wiki pattern: an LLM incrementally compiles immutable raw sources into a cross-linked, self-consistent wiki it owns, governed by a schema, via ingest / query / lint, with a content index and a chronological log. Activates when designing a knowledge base, ingesting sources into a wiki, health-checking one, or mapping the pattern onto the agentprivacy federation (which IS an instance of it). Part of the git-less onboarding/distribution layer kept by the Librarian 🗃️ in the Tower's Wikis.
    0
    installs
  3. Agentprivacy Amnesia Protocol · mitchuski
    Foundational skill for amnesia-as-ZK-primitive patterns. Applies when designing systems where forgetting is the proof, separation creates trust, and the inability to reconstruct origin is the security guarantee. Core to Act XXXI cosmological closure. V6 register note (2026-06-10): conjecture and version citations resolve to agentprivacy-docs/research/CONJECTURE_REGISTER_V6.md (head C89); model head: privacy_value_v6_formal_specification.md.
    0
    installs
  4. Agentprivacy Network Topology · mitchuski
    Network topology and stratum-weighted effects for 0xagentprivacy Privacy Pools. Activates when discussing (1 + Σ wᵢ nᵢ/N₀)^k, binomial coefficients across strata, Metcalfe generalisation, pool composition optimisation, or network scaling exponents. Use for Privacy Pool design and network value modelling. V6 register note (2026-06-10): conjecture and version citations resolve to agentprivacy-docs/research/CONJECTURE_REGISTER_V6.md (head C89); model head: privacy_value_v6_formal_specification.md.
    0
    installs
  5. Agentprivacy Namekeeper Write Contract · mitchuski
    Prepare and validate VTA-authorized Namekeeper wiki writes with exact scope, revision preconditions, idempotency and receipt reconciliation.
    0
    installs
  6. Agentprivacy Content Addressing · mitchuski
    UOR content addressing foundation for holonic persistence. Activates when discussing content-based identity, same bytes same hash, GUID derivation, infrastructure independence, Braille IRI encoding, or why identity follows content not location.
    0
    installs
  7. Agentprivacy Compression Defence · mitchuski
    Compression-as-defence principle for 0xagentprivacy V5. Activates when discussing BRAID 74× compression, R(d,compression) modifier, token reduction as attack surface reduction, the compression spectrum (7 layers), or why efficient inference is also private inference.
    0
    installs
  8. Agentprivacy Three Axis Separation · mitchuski
    Three-axis separation model for 0xagentprivacy V5. Activates when discussing Φ_agent · Φ_data · Φ_inference, multiplicative separation, Generator-Solver split, provider fragmentation, why collapse on any axis collapses total value, or the orthogonal axes of the sovereignty architecture. V6 register note (2026-06-10): conjecture and version citations resolve to agentprivacy-docs/research/CONJECTURE_REGISTER_V6.md (head C89); model head: privacy_value_v6_formal_specification.md.
    0
    installs
  9. Agentprivacy Holonic Identity · mitchuski
    Identity-independent data structures for 0xagentprivacy. Activates when discussing GUIDs not derived from any provider, the three-layer identity model (data GUID / relationship VRC / principal DID), ProviderUniqueStorageKey as commitment map, identity vs commitments separation at the data layer, immutable vs versioned holons, or how data identity persists when storage infrastructure changes. Use when designing systems where identity must outlive any single backend, chain, or registry.
    0
    installs
  10. Agentprivacy Holonic Reasoning · mitchuski
    Shared reasoning graphs and inference artefacts as persistent, provider-agnostic holons for 0xagentprivacy agents. Activates when discussing Holonic BRAID, bounded reasoning stored as reusable holons, agent memory as holon trees, learn-once-reuse-everywhere inference patterns, reasoning graph libraries, narrative compression into persistent holon MetaData, or how multiple privacy- preserving agents can share validated reasoning without leaking behavioural data. Use when designing shared intelligence infrastructure for dual-agent systems.
    0
    installs
  11. Agentprivacy Holonic Persistence · mitchuski
    Multi-provider data persistence for privacy-preserving AI agents using holonic architecture. Activates when discussing HyperDrive auto-failover, auto-replication across heterogeneous backends, provider-agnostic storage, privacy-aware routing between shielded and public providers, write-all-or-fail for separation-critical state, or any task where agent data must survive TEE rotation, chain migration, or provider failure. Use when designing persistence layers that span blockchains, databases, and decentralised networks simultaneously. V6 register note (2026-06-10): conjecture and version citations resolve to agentprivacy-docs/research/CONJECTURE_REGISTER_V6.md (head C89); model head: privacy_value_v6_formal_specification.md.
    0
    installs
  12. Agentprivacy Holonic Architect · mitchuski
    Builder of identity-independent data structures for 0xagentprivacy. Activates for holonic multi-provider persistence, identity-independent data design, shared reasoning graph architecture, O(1) shared-parent collective structures, privacy- aware HyperDrive configuration, three-layer identity model (data GUID / VRC / DID), OASIS integration, provider-agnostic storage design, or any task requiring the bridge between holonic data abstraction and privacy-first dual-agent architecture. The broadest specialist in the roster (24 skills loaded).
    0
    installs
  13. Agentprivacy Shared Parent Patterns · mitchuski
    O(1) collective data structures using holonic shared-parent patterns for 0xagentprivacy guilds, pools, and agent swarms. Activates when discussing N² coupling problems, LoadHolonsForParentAsync scalability, guild memory architecture, Intel Pool holons, collective intelligence without pairwise links, agent coordination at scale, or any data structure where many agents or participants need shared access without quadratic connection overhead. Use when designing scalable collective structures for privacy-preserving systems.
    0
    installs