Results for “bandit”

Provides guidance on using the QMT quantitative trading terminal, including strategy development, backtesting, and live trading for Chinese securities markets.

Persists app data on Android using Room, SQLite, SharedPreferences, DataStore, and encryption.

BALD EAGLE v3.0 — XYZ Alpha Hunter (Hardened). Focused on 6 high-liquidity XYZ assets: CL, BRENTOIL, GOLD, SILVER, SP500, XYZ100. Conviction-scaled leverage (5-10x based on score). Wider DSL for macro assets. Maker-only execution. Scanner calls create_position internally. v3.0: focused assets, conviction-scaled leverage, XYZ-tuned DSL, no thesis exit.

Rolls back Open-workspace phase or plan commits using a phase manifest with dependency checks and a confirmation gate, preserving history via git revert.

Simulates bandwidth throttling and network degradation attacks using tc, iperf3, and Scapy in authorized environments to test quality-of-service controls, application resilience, and network monitoring detection of traffic manipulation attacks.

Use when a human asks to check wallet balances or send/transfer BTC, SPACE, DOGE, or OPCAT to an address; do not use this skill for on-chain content publishing, remote service delegation, or identity/network management.

MANTIS v4.0 — Striker-Only SM Explosion Scanner. Stalker removed. Detects violent rank jumps across 50+ markets. Fast-cycling DSL. DSL exit managed by plugin runtime via runtime.yaml.

Git-native issue tracking with first-class dependency support. Issues stored alongside code in .beads/ directory, dual-persisted in SQLite (queries) and JSONL (git-friendly history). Hash-based IDs, DAG dependencies, daemon mode with RPC, and LSP-inspired multi-workspace support.

Lightweight local kanban boards stored in SQLite — track tasks, view board state, create/update/move cards. Syncs across machines via git.

Read the `<!-- pk-commands BEGIN -->` ... `<!-- pk-commands END -->` block

>- Skill Refiner, the eval-guided improvement loop for SKILL.md files. Runs the bootstrap, score, propose, apply, and status cycle as a thin wrapper over the published @intentsolutions/refiner CLI, proposing safe, minimal, bounded SKILL.md edits and accepting an edit only when a held-out eval score strictly improves with no regression on any other case. Ships a 3-layer cost-tiered hook architecture (sinker, line, hook) that gates skill quality at edit time, end of turn, and commit time. Use when improving an existing skill, refining a SKILL.md against measured behavior, bootstrapping an eval set for a skill, or gating skill edits before they ship. Trigger with "/j-rig", "refine this skill", "bootstrap an eval set", "propose a skill edit", "promote the candidate", or "skill refiner status".

Generate a project-level context snapshot for resuming work in a fresh session

Investigates bugs, regressions, and crashes by dispatching four parallel read-only sub-agents, then ranks hypotheses and recommends the fastest proof or fix path.

波总口语输入 → 结构化任务记录 → 同步到副官系统。当波总说"记一下""记录下来""有个任务"或描述要做的事时使用。

Applies four disciplined mindsets—audit, debt, help, review—to cut complexity, track deferrals, surface reference, and catch over-engineering in codebases.

Bun all-in-one JavaScript runtime and toolkit reference. Covers runtime APIs (file I/O, HTTP server, SQLite, shell), ultra-fast package manager, built-in bundler with plugins, test runner with mocking, TypeScript support, and Node.js compatibility.

GitHub 이슈를 완전 스냅샷으로 다시 읽어 `.issue/graph.json` 캐시를 생성·갱신합니다. "$issue-sync", "이슈 그래프 갱신", "그래프 만들기", issue-onboard가 그래프 없이 시작될 때 사용합니다.

Develops and backtests quantitative trading strategies for the Chinese securities market using the QMT terminal's built-in Python framework, covering data retrieval, order placement, and position management.