// House of On-Chain skill. Auto-activates on /crypto-onchain-* commands or work within verticals/crypto-intelligence/onchain/. Enforces R5 non-advisory clause inline, chain-data source citation, mechanism-context grounding, named output artifact discipline.
Load when working at the Starlight substrate layer — authoring SIP, forging alliances, spawning verticals, or generating SIP-compliant attestations. Not for vertical-specific work (use the vertical's SKILL.md).
Vertical-tier skill auto-activates when working inside verticals/crypto-intelligence/ or invoking any /crypto-* command. Enforces R5 non-advisory clause, voice (architect), refusal patterns, composition-with-Wealth-IS rules, and sovereignty discipline.
Vertical-tier skill for Crypto Intelligence Domain Sub-Stack. Auto-activates inside verticals/crypto-intelligence/ or on /crypto-* commands. Enforces R5 non-advisory clause, voice (architect), refusal patterns, composition with Wealth IS umbrella per Board 2026-05-17. Loads verticals/crypto-intelligence/SKILL.md wrapper for full doctrine.
Catalogs, scaffolds, and audits the per-repo tech stack across every brand (Arcanea, FrankX, Business, Starlight, verticals). Four verbs — audit (walk repos + emit constellation), scaffold (drop STACK.md template into a target repo), assign (bind tools to substrate/reasoning/coding/research/ops tiers), diff (surface drift between STACK.md intent and reality from .mcp.json + .claude/ + settings.json + installed CLIs). Use this skill whenever the user mentions stack architecture, repo inventory, "which AI assistant for which repo", custom GPTs, MCP routing across brands, browser workspaces per project, or asks "do we have a clean view of our tech stack". Default skill for the Starlight Architect when the question spans repos rather than a single one.
Disk audit and dedup-hint skill. Reports repo sizes, oversized files, worktree bloat, and surfaces candidates for archival/cleanup. Cross-cutting machine-layer skill, sibling to /pp and /heart.
Ops health monitor for the machine substrate. Checks Memory Bus, brain_watchdog, Voice Operator, dashboard, audit-log freshness, and scheduled tasks. Cross-cutting skill that any repo can invoke when daemons feel off or before starting a heavy work session.
| name | crypto-intelligence/onchain |
| description | House of On-Chain skill. Auto-activates on /crypto-onchain-* commands or work within verticals/crypto-intelligence/onchain/. Enforces R5 non-advisory clause inline, chain-data source citation, mechanism-context grounding, named output artifact discipline. |
| triggers | ["command-prefix /crypto-onchain-*","working-directory verticals/crypto-intelligence/onchain/","keywords [on-chain, wallet flow, whale tracking, mev audit, validator econ, contract interaction]"] |
| parent-vertical | crypto-intelligence |
| house | onchain |
| tier | Domain Sub-Stack Tier |
House-tier skill. Inherits Crypto Intelligence vertical-tier skill rules (R5 clause inline, voice = architect, refusal patterns, composition with Wealth IS umbrella). Adds House-of-On-Chain-specific discipline.
> This is system architecture, not financial / investment / tax / legal advice.
> Outputs frame decisions; jurisdiction-specific counsel signs off on instruments.
> The practitioner accepts capital risk; the substrate accepts no claim.
> Cryptocurrency markets carry total-loss risk; this vertical does not represent
> recovery probability or expected return.
This block opens every House of On-Chain output artifact. Non-waivable. Audited per Crypto IS SOUL.md drift test 1.
Name explicitly:
Every claim traces to a named source:
No "the data shows" without source. No "wallet activity suggests" without entity-tag source. No "TVL is" without DefiLlama-or-equivalent snapshot timestamp.
For each on-chain action analyzed, name the mechanism:
Wallet-attribution is often ambiguous. MEV-vs-arbitrage classification is contested. Validator slashing data has reporting lags. Flag where the analysis is uncertain — do not paper over with concrete-sounding numbers.
Every command ships a named file:
/crypto-onchain-flow-snapshot → flow-snapshot-<yyyy-ww>.md (or instance-private equivalent)/crypto-onchain-wallet-trace → wallet-trace-<address-short>-<yyyy-mm-dd>.md/crypto-onchain-mev-audit → mev-audit-<protocol-slug>-<yyyy-mm-dd>.md/crypto-onchain-validator-econ → validator-econ-<network-slug>-<yyyy-mm-dd>.md/crypto-onchain-contract-interaction → contract-trace-<tx-hash-short>.mdThe filename is the contract. If the file isn't written, the command didn't run.
This House refuses:
| Composes with | Direction | Cite as |
|---|---|---|
| House of Macro (v0.2) | Flow snapshots feed regime-call inputs | Feeds: /crypto-macro-regime |
| House of DeFi (v0.2) | Protocol-interaction data feeds mechanism audit | Feeds: /crypto-defi-mechanism-audit |
| House of Sovereignty (v0.2) | Activity patterns feed custody-tier review | Feeds: /crypto-sov-custody-design |
| House of Research (v0.2) | On-chain activity surfaces tokenomics signals | Feeds: /crypto-res-tokenomics |
| House of Allocation (v0.2) | Whale-tracking + flow → sizing inputs | Feeds: /crypto-alloc-sizing |
| Wealth IS umbrella | Concentration risk inputs to cross-asset review | Feeds: /wealth-portfolio-fit |
Each artifact declares its composes-with downstream explicitly.
If any gate fails → artifact does not ship → re-execute with gate satisfied.
Built on SIP — Crypto / House of On-Chain skill (House-tier) · v0.1 proof-of-pattern · SIP v1.1.0