Desenvolvimento

Gera código de estratégia quantitativa preciso e executável para a plataforma JoinQuant (聚宽). Use esta skill para criar estratégias de backtest, paper-trading ou live-trading de ações, ETFs e futuros no JoinQuant.

Guides test-driven development — decompose a feature or bug fix into behaviors, then cycle through Red (failing test) → Green (minimal implementation) → Refactor for each one. Requires /optimus:init and working test infrastructure. Use when starting a new feature or bug fix with test-first discipline.

Stages, commits, and optionally pushes local changes with a conventional commit message — analyzes diffs, generates the message, confirms with the user, and commits. On protected branches, offers to create a feature branch automatically. Multi-repo aware. Use when ready to commit work in one step.

Reviews local changes, PRs/MRs, or branch diffs against project coding guidelines using 5 to 7 parallel review agents (bug detection, security/logic, guideline compliance x2, code simplification, test coverage, contract quality). Use before committing, on open PRs/MRs, or to review any branch diff. HIGH SIGNAL only: real bugs, logic errors, security concerns, and guideline violations. Supports a "

Creates and switches to a new, conventionally named branch — derives the name from an inline description, conversation context, or local git diffs. Preserves all local changes. Never commits or pushes. Use when you want a properly named branch for new or in-progress work.

O desenvolvimento Zephyr RTOS abrange placas, devicetree, o sistema de compilação (west, Kconfig, CMake, sysbuild), drivers, periféricos, BLE, rede, kernel, armazenamento, energia, testes, depuração, segurança e OTA. Use esta skill para qualquer tarefa de Zephyr RTOS ou firmware embarcado, direcionando para habilidades especializadas via o registro zephyr-cli.

CVSS 3.1 vector examples, executive summary template, full technical finding template, and remediation language bank for pentest reports

Improves unit test coverage on demand — discovers testing gaps and generates tests that follow project conventions. Requires /optimus:init to have set up test infrastructure first. Conservative — only adds new test files, never refactors existing source code. Supports `deep` mode for iterative in-conversation test generation and `deep harness` mode for an automated multi-cycle unit-test + testabil

Compacts the current conversation into a single self-contained handoff document under docs/handoffs/ so a fresh agent — a new session, a different AI tool, or another developer on a different machine — can resume the work by reading only that file. References committed artifacts (PRDs, plans, ADRs, issues, commits) by path or URL and inlines anything not yet pushed. Redacts secrets and PII. Re-run

SecLists path map, hashcat rules, CeWL usage, and custom wordlist generation for all attack categories

Suggests conventional commit messages by analyzing staged, unstaged, and untracked git changes — read-only, never commits. Use when a commit message suggestion is needed without actually committing.

Active Directory attack reference — BloodHound Cypher queries, Kerberos attack decision tree, ACE/ACL abuse, ADCS ESC1-8, and AD misconfig checklist