// 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.
| name | crypto-intelligence |
| description | 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. |
| triggers | ["keywords [crypto, cryptocurrency, blockchain, on-chain, wallet, defi, validator, mev, custody, multisig]","command-prefix /crypto-*","working-directory verticals/crypto-intelligence/"] |
Vertical-tier skill loads when working inside Crypto Intelligence. Enforces the wrapper rules so the Houses inherit them automatically — voice, refusal patterns, R5 non-advisory clause, sovereignty discipline, composition with Wealth IS umbrella, attestation discipline.
verticals/crypto-intelligence//crypto-* command (/crypto-onchain-flow-snapshot, /crypto-onchain-wallet-trace, /crypto-onchain-mev-audit, etc.)/wealth-portfolio-fit, /wealth-cycle-thesis, /wealth-sovereignty-design) consume Crypto IS House outputsEvery House command output inherits from this skill:
R5 non-advisory clause inline (mandatory, non-waivable):
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.
Voice: architect (primary) per AGENTS.md voice mappings. First-principles, decision-first, normative over descriptive, no hedging when structurally avoidable. Refuses influencer-shitposter cadence, institutional-research voice without sovereignty discipline, cypherpunk-zine tone.
Refusal patterns (per SOUL.md):
Composition with Wealth IS (per STACK.md § Composition Layer):
/wealth-portfolio-fit (concentration risk inputs)/wealth-cycle-thesis (cross-asset cycle position)/wealth-sovereignty-design (cross-asset custody)Attestation discipline: Every shipped artifact carries "Built on SIP" attestation block (ambient per v7.4). ATTESTATIONS.md ledger mirrors entries for sibling-repo extraction discipline (per Board open-question (c) close-out).
The Crypto Intelligence vertical exposes its operational surface via MCP tools so that when extracted to github.com/frankxai/crypto-intelligence-system at v0.2+, consumers see the same tool surface:
mcp_tools_planned:
- name: crypto_onchain_flow_snapshot
description: Generate weekly wallet-flow + whale-tracking pulse for a wallet slug
inputs: { wallet_slug: string }
outputs: { artifact_path: string, regime_flag: enum }
- name: crypto_onchain_wallet_trace
description: Trace single wallet recent activity + risk surface
inputs: { address: string, days: number }
outputs: { artifact_path: string }
- name: crypto_onchain_mev_audit
description: MEV exposure audit for a protocol the practitioner uses
inputs: { protocol_slug: string }
outputs: { artifact_path: string, exposure_summary: object }
- name: crypto_onchain_validator_econ
description: Validator economics summary for a network
inputs: { network_slug: string }
outputs: { artifact_path: string }
- name: crypto_onchain_contract_interaction
description: Contract interaction trace + risk surface for a tx
inputs: { tx_hash: string }
outputs: { artifact_path: string, risk_flags: array }
mcp_resources_planned:
- vault: crypto-intelligence/onchain/
- corpus: crypto-intelligence/onchain/knowledge.md
- sibling-repo-target: github.com/frankxai/crypto-intelligence-system (v0.2+ extraction target)
At v0.1, commands are markdown-doc shape (matches Sound IS / People IS pattern). MCP-tool exposure ships at v0.2+ if proof-pass succeeds AND the practice actually demands programmatic access (Verifier-defended falsifier).
genius/profile-frankx.md for voice grounding, verticals/crypto-intelligence/SOUL.md for non-negotiables, verticals/wealth/README.md for composition-layer rules, current House's knowledge.md for domain grounding.SUB-SYSTEMS.md schedule.ATTESTATIONS.md for public artifacts.Built on SIP — Crypto Intelligence SKILL.md (vertical-tier) · v0.1 · SIP v1.1.0 (Board R5 + (c) close-outs 2026-05-17)
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 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.
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.
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.
