ruflo-neural-trader
claudeNeural trading strategies — self-learning LSTM/Transformer/N-BEATS models with Rust/NAPI backtesting
9 skills · 1 command · 4 agents
Standard-first IPS workflow: your goal and scoring standard first, then every policy answer derived from it and attacked by blind critics before you decide. Educational; not investment advice.
Plugin standard-first-ips from marketplace standard-first-ips in rdmayo21/standard-first-ips. Commands read from the repo's manifest — 6 days ago.
standard-first-ipsBuild or revise a personal Investment Policy Statement (IPS) the rigorous way. First the user writes their own goal and scoring standard. Then every policy question is derived from that standard by a builder agent, attacked by blind critics from two model families, and decided by the user. Includes
ips-builderBuilds the answer to one IPS policy question from the person's adopted standard, using the ipsengine simulation where numbers matter. Spawn with a self-contained brief (standard verbatim, scoring method, figures with sources, candidates, scope). Not for reviewing work; use ips-critic for that.
ips-criticBlind adversarial reviewer for an IPS answer or an IPS draft. Give it the files and the person's decisions, never the conclusion you hope for. Returns a verdict and specific defects with file:line and fixes.
Neural trading strategies — self-learning LSTM/Transformer/N-BEATS models with Rust/NAPI backtesting
9 skills · 1 command · 4 agents
Portfolio monitoring, valuations and analytics for private-capital GP teams using the Chronograph connector: portfolio-company one-pagers, fund quarterly review packs, markup/markdown briefs, TVPI attribution and budget-vs-actuals. Requires a Chronograph account and the Chronograph connector.
5 skills · 6 agents
Quantitative analysis, algorithmic trading strategies, financial modeling, portfolio risk management, and backtesting
2 skills · 2 agents
Investment banking productivity tools - client and market insights, deck creation, financial analysis, and transaction management
9 skills · 7 commands
Ready-to-run workflows for financial advisors in Claude Cowork, drawing live data from the tools their firm already uses through third-party connectors. The plugin holds no client data, and the advisor approves any write back to an external system. Claude gathers, organizes, summarizes, compares and presents information, while the advisor exercises judgment, makes the recommendation and gives the advice. For financial professional use only; not investment, legal, or tax advice.
8 skills · 6 agents · 36 MCP servers
Enterprise / cross-functional Research Operations domain — the managed counterpart to the academic research/ domain. v2.9.0 ships 5 skills: orchestrator (context: fork), clinical-research (protocol synopsis, endpoint selection, sample-size/power for means/proportions/survival, phase-gate feasibility), research-finance (R&D budgeting with F&A split, burn/runway, capitalize-vs-expense routing, portfolio ROI), market-research (TAM/SAM/SOM top-down and bottoms-up, survey sampling with FPC, Kotler segmentation), and product-research (goal-matched study design, method-based saturation, insight synthesis flagging single-source anecdotes). Hard rules: outputs are estimates routed to a named clinical or finance owner, market sizes show method + assumptions, product insights require recurrence across independent participants. 24 stdlib Python tools, 12 reference docs. Distinct from ra-qm-team, finance, research/grants, product-team, and marketing-skill.
6 skills · 7 commands · 2 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.