Xukai-YE

@xukai-ye source repo

7 skills
0 followers
9 hours ago last updated

▌
Cc Main Implement · xukai-ye bundle
Use when a coding task is medium or high-risk and Claude Code should do the main implementation work. Pass -Tier to select model preference: medium uses Sonnet 4.6 first, high-risk uses Opus 4.6 first. Codex reviews, verifies, and applies only short follow-up patches.

0 installs
▌
Cc Opus First Pass · xukai-ye bundle
Use to classify a coding task into the 3-tier system (tiny/medium/high-risk) and get an analysis brief before implementation. Always uses Opus 4.6 first for deep reasoning. Skip for tasks that are obviously tiny.

0 installs
▌
Cc Opus Review Loop · xukai-ye bundle
Use for plan reviews and checkpoint reviews during implementation. Pass -Tier to select model preference: high-risk uses Opus 4.6 first, medium uses Sonnet 4.6 first. Supports relaxed cadence after 2 consecutive clean reviews.

0 installs
▌
Cc Three Tier Orchestrator · xukai-ye
Route non-trivial coding tasks through a risk-first 3-tier Codex and Claude Code workflow. Use when you want tiny tasks handled locally, medium tasks implemented mainly by Claude Code, and high-risk tasks reviewed and implemented through staged plan and checkpoint reviews.

0 installs
▌
Effort Calibration · xukai-ye bundle
难度分级与 effort 自适应。在回答前先内部判断任务难度、风险、不确定性与错误代价，自主选择 low/medium/high/max 档位，使分析深度、检查强度与输出结构动态匹配任务难度。适用于所有任务，始终在后台运行。

0 installs
▌
Plan Review Collaboration · xukai-ye bundle
方案复核协同 skill，用于处理复杂计划、实验方案、研究路线、系统搭建、工程排查、多阶段实现路径设计等任务。当任务具有多步骤依赖关系、需要完整执行方案、涉及实验设计/变量控制/风险分析、需要工程实现路径或调试顺序、需要在多候选方案中权衡，或任务链路较长且错误代价较高时，自动启用此 skill。

0 installs
▌
Background Supervisor Skill · xukai-ye bundle
Enable automatic Python-based supervision for long-running Claude Code background Bash tasks. Use when you want background programs to emit periodic monitor output and have Claude Code review, verify, and rerun jobs after failures. Installs and maintains hook-driven monitoring in ~/.claude/settings.json.

0 installs

7 published skills