By FL03
FL03's personal skill marketplace for Claude Code. Independently installable skills covering Rust, WebAssembly, quantitative finance, Polymarket trading, workflow orchestration, and type theory.
Research-grade quantitative finance. Loads QUANT.md (mathematical toolkit: stochastic calculus, derivative pricing, risk metrics, portfolio theory, numerical methods) and MODELS.md (applied model library: Black-Scholes, Heston, Merton jump-diffusion, term structure, factor models, Monte Carlo, backtesting). Imbues any agent with the working knowledge of a PhD-level financial engineer. Attach when the user asks about option pricing, the Greeks, implied vs realized volatility, Itô / SDEs / GBM, Value-at-Risk, CVaR / expected shortfall, Sharpe / Sortino / Calmar, Kelly sizing, mean-variance optimization, factor models (CAPM / Fama-French / APT), term-structure models (Vasicek / CIR / Nelson-Siegel), Monte Carlo or PDE-based pricing, or backtesting methodology. Analysis-only — pair with `@trader` (and an exchange skill such as `@polymarket`) for live execution.
Polymarket exchange reference for prediction-market trading on Polygon. Covers protocol architecture (CLOB / relayer / on-chain CTF), authentication tiers (L1 EIP-712 vs L2 HMAC API keys), pUSD collateral, market types (binary, multi-outcome neg-risk, sports, crypto strikes), UMA resolution, fee structure, and ID disambiguation (token_id vs condition_id vs question_id vs slug). Companion files: `apis.md` (Gamma / CLOB / Data / Relayer endpoint reference — base URLs, request/response shapes, rate limits, Context7-grounded against docs.polymarket.com), `strategies.md` (trading playbooks per market category), `exploits.md` (structural edge ledger). Exchange-specific companion to @trader.
Make any agent, session, or cron fluent in idiomatic Rust. Covers ownership, borrowing, lifetimes, error handling, async (tokio), traits, generics, trait objects, the no_std/alloc/std tier system, declarative and procedural macros (syn/quote/proc-macro2 triad), and pointers to docs.rs / crates.io for ecosystem crate lookup. Companion reference files: `cargo.md` (full cargo surface — commands, manifest, workspaces, features, profiles, .cargo/config.toml, subcommand ecosystem, sccache, parallel-agent build workflows, JSON output) and `rustc.md` (practical compiler knobs — codegen flags, RUSTFLAGS precedence, target triples, lints, editions, sanitizers, cfg, --print, debug flags). Attach this skill whenever producing or reviewing Rust. Not project-specific and not style-opinionated — personal preferences live in the `code-style` skill; project rules live in the project itself. Language-agnostic WebAssembly material lives in the `webassembly` skill; Rust-side host embedding lives in the `wasmtime` skill.
Generalized autonomous trading agent. Loads SKILL.md (agent protocol + 9-gate safety contract + cycle structure), jailbreak.md (operator pre-authorization + spend caps), and axiom.md (Axiom MCP platform tool reference — the execution layer). Exchange-agnostic by design; exchange-specific strategy is loaded separately (e.g., @polymarket SKILL.md + strategies.md + exploits.md).
Language-agnostic advanced type-system knowledge. Covers the conceptual foundation that crosses typed languages — parametric/ad-hoc/subtype polymorphism, variance, kinds, higher-kinded types, type classes vs traits vs interfaces, GADTs, type-level programming, dependent and refinement types, row polymorphism, and type-driven design discipline. Worked examples span Haskell, Idris/Agda, OCaml, Scala, TypeScript, and (sparingly) Rust. Companion reference files: `dependent-types.md` (Pi/Sigma types, length- indexed vectors, refinement types, proof-carrying code in Idris/Agda/F*/ Liquid Haskell) and `type-level-programming.md` (GADTs, type families, HKTs, phantom types, kind polymorphism, type-level naturals, row types, TypeScript conditional/mapped/template-literal types). Attach this skill whenever the task is "how should I MODEL this in the type system" across languages, or when comparing type features between languages. The Rust-specific surface (impl Trait, GATs, object safety, PhantomData variance, type-state, sealed traits) lives in the `rust` skill's `typespace.md` — cross to it for Rust syntax; stay here for the cross- language theory.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub fl03/claude --plugin webassemblyResearch-grade quantitative finance. PhD-level toolkit covering stochastic calculus, derivative pricing (Black-Scholes + Greeks, Heston, Merton jump-diffusion, American options), risk metrics (VaR/CVaR/Sharpe/Sortino/Calmar), portfolio theory, term-structure models, Monte Carlo with variance reduction, and backtesting. Grounded against Hull / Bjork / Wilmott / Glasserman.
Sprint-by-sprint version-cycle conductor. Six-agent flock (engineer, critic, coder, auditor, worker, discovery) on a three-section pipeline (INTRODUCTION → BODY → CLOSE), with hardened hooks, hypothesis-driven audits, and a per-project SQLite context registry. Project-agnostic — branch topology, gates, paths, and ledger discipline configured via .claude/shepherd.toml.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.