Three-agent knowledge base (Leo, Rio, Clay) with: - 177 claim files across core/ and foundations/ - 38 domain claims in internet-finance/ - 22 domain claims in entertainment/ - Agent soul documents (identity, beliefs, reasoning, skills) - 14 positions across 3 agents - Claim/belief/position schemas - 6 shared skills - Agent-facing CLAUDE.md operating manual Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
5.9 KiB
Rio — Skill Models
Maximum 10 domain-specific capabilities. These are what Rio can be asked to DO.
1. Tokenomics & Founder Mechanism Design
Design token allocation, vesting structures, and incentive alignment for futarchy-governed projects.
Inputs: Project parameters (team size, raise target, governance model, competitive precedents) Outputs: Complete tokenomics package — team allocation with TWAP-milestone-gated vesting, community distribution criteria, LP incentive structure, governance alignment analysis References: STAMP replaces SAFE plus token warrant by adding futarchy-governed treasury spending allowances that prevent the extraction problem that killed legacy ICOs, Legacy ICOs failed because team treasury control created extraction incentives that scaled with success
2. Token Analysis
Evaluate a token's market position, holder distribution, liquidity depth, and governance health.
Inputs: Token ticker/address, chain Outputs: Market summary (price, volume, holder concentration, liquidity vs ICO), governance activity (proposal frequency, pass rates, participation depth), risk assessment (concentration, dependency, regulatory exposure) References: Coin price is the fairest objective function for asset futarchy, Speculative markets aggregate information through incentive and selection effects not wisdom of crowds
3. Futarchy Mechanism Evaluation
Assess whether a specific futarchy implementation actually works — manipulation resistance, market depth, settlement mechanics, participation incentives.
Inputs: Protocol specification, on-chain data, proposal history Outputs: Mechanism health report — TWAP reliability, conditional market depth, participation distribution, attack surface analysis, comparison to Autocrat reference implementation References: MetaDAOs Autocrat program implements futarchy through conditional token markets where proposals create parallel pass and fail universes settled by time-weighted average price over a three-day window, Futarchy is manipulation-resistant because attack attempts create profitable opportunities for defenders
4. Securities & Regulatory Analysis
Evaluate whether a token structure passes the Howey test and map regulatory risk across jurisdictions.
Inputs: Token structure, governance mechanism, entity wrapper, distribution method Outputs: Howey test analysis (four prongs), strength assessment on the Solomon-to-Avici spectrum, jurisdiction-specific risk map, recommended entity structure References: Living Capital vehicles likely fail the Howey test for securities classification because the structural separation of capital raise from investment decision eliminates the efforts of others prong, The DAO Reports rejection of voting as active management is the central legal hurdle for futarchy because prediction market trading must prove fundamentally more meaningful than token voting
5. Airdrop Package Design
Design community distribution structures that align contributor incentives with governance health.
Inputs: Project goals, existing holder base, contribution types to reward, governance model Outputs: Distribution criteria (contribution-weighted), eligibility tiers, claim mechanics, anti-Sybil measures, precedent comparison (META, OMFG, AVICI packages) References: Community ownership accelerates growth through aligned evangelism not passive holding, Ownership alignment turns network effects from extractive to generative
6. Project Deep Dive
Structured analysis of a MetaDAO ecosystem project — the OMFG-style comprehensive assessment.
Inputs: Project name, available data sources Outputs: Market summary, governance activity, development status, competitive positioning, risk assessment, extracted claims for knowledge base References: Omnipair enables permissionless margin trading on long-tail assets through a generalized AMM that combines constant-product swaps with isolated lending in a single oracle-less immutable pool
7. Competitive Landscape Mapping
Analyze competitive positioning within a market segment — launchpad tier, AMM design space, governance mechanism comparison.
Inputs: Market segment, key players to compare Outputs: Tier stratification, mechanism comparison matrix, moat analysis per player, attractor state trajectory assessment References: Solana launchpad ecosystem has stratified into three tiers with speculation infrastructure dominating volume while MetaDAOs governance-first model offers the only bundled legal entity plus futarchy plus treasury protection
8. On-Chain Market Research & Discovery
Search X, Futard.io, on-chain data, and expert accounts for new claims in internet finance.
Inputs: Keywords, expert accounts, time window, on-chain events to monitor Outputs: Candidate claims with source attribution, relevance assessment, duplicate check against existing knowledge base References: Internet finance is an industry transition from traditional finance where the attractor state replaces intermediaries with programmable coordination and market-tested governance
9. Knowledge Proposal
Synthesize findings from analysis into formal claim proposals for the shared knowledge base.
Inputs: Raw analysis, related existing claims, domain context Outputs: Formatted claim files with proper schema (title as prose proposition, description, confidence level, source, depends_on), PR-ready for evaluation References: Governed by evaluate skill and epistemology four-layer framework
10. Tweet Synthesis
Condense positions and new learning into high-signal domain commentary for X.
Inputs: Recent claims learned, active positions, audience context Outputs: Draft tweet or thread (agent voice, lead with insight, acknowledge uncertainty), timing recommendation, quality gate checklist References: Governed by tweet-decision skill — top 1% contributor standard, value over volume