DeevsDeevs

Run multi-lens hypothesis generation across accounting, flows, networks, microstructure, and causal checks. Use when you need market hypotheses with mechanism, counterparty, and decay. Triggers: alpha squad, fundamentalist, vulture, network-architect, book-physicist, causal-detective, hypothesis generation, mechanism first.

Run systematic bug hunting with spec reconstruction, adversarial validation, and confidence scoring. Use when you want to hunt bugs (not fix them), validate correctness, or run logic-first/code-first investigations. Triggers: bug hunt, spec reconstruction, logic-first, code-first, orchestrator, logic-hunter, cpp-hunter, python-hunter.

Apply opinionated developer personas for architecture decisions, production debugging, language-specific code review, comprehensive reviewer passes, and test strategy. Use when you need an architect plan, devops investigation, Rust/Python/C++ review, grumpy reviewer audit, or tester-driven test plan. Triggers: architect, devops, rust-dev, python-dev, cpp-dev, reviewer, tester, pre-merge review, refactor for maintainability.

Run research orchestration for data quality, factor geometry, hypothesis validation, and incident forensics. Use when you need SHIP/KILL/ITERATE decisions with strict validation. Triggers: mft-strategist, data-sentinel, factor-geometer, skeptic, forensic-auditor, research pipeline, hypothesis validation, post-mortem.

This skill should be used when the user asks about "market microstructure", "exchange mechanics", "order book", "auction", "NBBO", "Reg NMS", "trading venue", "halt", "LULD", "tick size", "maker-taker", "price-time priority", "SIP", "direct feed", "TRF", "wholesaler", "PFOF", "best execution", "trade-through", "ISO", "opening cross", "closing cross", "NOII", "ITCH", "OUCH", or mentions specific exchanges (Nasdaq, NYSE, CME, Binance, SHFE, DCE, CZCE, CFFEX, INE, etc.). For Chinese futures: "CTP", "综合交易平台", "夜盘", "night session", "看穿式监管", "position limits", "持仓限额", queue position in Chinese markets, or Chinese product codes (rb, cu, sc, if, ic, i, j, ta, ma, etc.). Provides hierarchical venue expertise for research and debugging trading systems.

Apply timeless programming wisdom from "97 Things Every Programmer Should Know" when writing, reviewing, or refactoring code. Use for design decisions, code quality checks, professional development guidance, testing strategies, and workflow optimization.

After working on the code, ensure the branch contains only the minimal, idiomatic changes by removing AI-generated slop introduced on this branch.

Search arXiv preprint repository for research papers in physics, mathematics, computer science, quantitative biology, finance, and statistics. Use when finding academic papers, preprints, ML research, scientific publications. Triggers: arxiv, preprint, research paper, academic paper, scientific literature.

Use for long-running commands that must stay observable, such as dev servers, watchers, REPLs, services, or workers. Prefer managed proc_* tools over shell backgrounding.

Create source-grounded visual explanations such as codebase maps, flows, sequence diagrams, state machines, and architecture views. Prefer compact Mermaid; use SVG/HTML only for polished artifacts.

Run a disciplined debugging loop for broken behavior, failing builds, flaky commands, hung processes, or regressions. Use when the user asks to diagnose, debug, or find root cause.

Build, query, and maintain curated markdown wikis with schema/index/log discipline. Use for project/domain wikis, durable research notes, source ingestion, linting, or canonicalized chain findings.

Use the interactive ask_user UI when 1-5 concrete clarifications or decisions materially affect implementation, scope, safety, or acceptance criteria. Gather evidence first; do not ask what tools can answer.

Create, fork, search, list, and load multi-session chain links under .chains. Use when saving work context, resuming a project from previous sessions, passing context to subagents, or finding prior decisions/next steps.

Use Pi's `todo_list` tool to plan and track non-trivial current-session work. Use for multi-step implementation, debugging, validation, research, or coordinating subagents; avoid for one-shot answers.

Use curated Deevs staff subagents for background exploration, review, testing, architecture, devops, language-specific review, and anti-slop passes.

Implements Rust features with TDD, testing, and verification for the Wagner codebase