菜单
Prompt cache cost optimization. Generates periodic conversation turns to keep the 5-minute prompt cache warm during idle gaps. TRIGGER immediately after any Bash or Agent call with `run_in_background=true` on the official Anthropic runtime, or when the user says "cache keep-alive".
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/archibate/dotfiles-claude --skill cache-hygiene命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Create or edit agent-facing/LLM prompts using modern prompt-engineering practices. Use this skill before editing agent-facing docs, rule files, references, skills, memory, or any form of LLM prompt. Also use it before writing LLM tests or evaluations. This is mandatory: NEVER skip this skill before writing agent-facing text; MUST use it before editing a file that will be fed to AI agents.
High-quality C++ OOP coding style (archibate / parallel101 lineage) that overrides sloppy AI-default C++. Use this skill WHENEVER writing, editing, refactoring, or reviewing C++ code (.cpp / .h / .hpp / .cc / .cxx), designing C++ classes, interfaces, APIs, or libraries, or when the user mentions C++ design, OOP, design patterns, dependency injection, RAII, or "clean / modern C++". Apply it even when the user does not explicitly ask for a style: the default way models write C++ leans on free functions, public mutable state, raw new/delete, sentinel return codes, and long loose parameter lists — this skill replaces all of that with abstract-class-or-data-class design, dependency injection, type-rich APIs, value-based error handling, and RAII ownership.
Evidence-driven C++ high-performance computing design, profiling, and optimization across algorithmic time/space complexity, data layout, cache and memory behavior, numerics, SIMD, multicore scheduling, and CPU/accelerator pipelines. Use before designing or changing computation-intensive kernels, high-throughput data structures, performance-critical loops, SIMD/OpenMP/TBB/CUDA code, mixed-precision or sparse representations, or when investigating throughput, latency, scaling, cache, bandwidth, compiler-vectorization, or profiling problems.
基于 SOC 职业分类
正在显示 SKILL.md
| name | cache-hygiene |
| description | Prompt cache cost optimization. Generates periodic conversation turns to keep the 5-minute prompt cache warm during idle gaps. TRIGGER immediately after any Bash or Agent call with `run_in_background=true` on the official Anthropic runtime, or when the user says "cache keep-alive". |
| allowed-tools | ["ScheduleWakeup"] |
| compatibility | Claude Code |
Prompt cache cost optimization protocol. The prompt cache has a 5-minute TTL. A cache miss costs 1.25x vs 0.1x for a hit — keeping the cache warm saves ~1.15P per avoided miss.
/cache-hygiene): user signals they will be away. Start the keep-alive loop after ending the current response.Start a keep-alive loop:
/loop Cache keep-alive. Idle tick 1/10.
Each tick:
ScheduleWakeup with delaySeconds=270. Pass the same prompt, incrementing N/10. Reset to 1/10 when user requests or there are background-task running this turn.Stop (omit ScheduleWakeup) when N would exceed 10.
Beyond 10 ticks (45 minutes), cumulative keep-alive cost (10 × 0.1P) exceeds the one-time cache miss penalty (1.15P).
Always set up schedule at <5 minutes delay, otherwise prompt cache (5-min TTL) would costly invalidate.
Never block a single tool call for >4 minutes (timeout argument in Bash, TaskOutput, Monitor). The cache TTL ticks during blocking calls — a 4-minute block plus response overhead can bust the 5-minute window. The keep-alive protocol prevents misses between turns; this cap prevents misses within turns.
Never start multiple keep-alive loops in parallel. Reset existing keep-alive loop to 1/10 instead.