Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From oh-my-agent
Audits prompt cache stability for prefix risks and volatile instructions/tools, then recommends specific fixes to boost hit consistency.
npx claudepluginhub sswym/oh-my-agent --plugin oh-my-agentHow this command is triggered — by the user, by Claude, or both
Slash command
/oh-my-agent:cacheThe summary Claude sees in its command listing — used to decide when to auto-load this command
运行专注于缓存的 oma 审计。 用户上下文： $ARGUMENTS 任务： 1. 评估前缀稳定性风险。 2. 识别导致缓存未命中的易变指令或工具更改。 3. 推荐具体修复以提高缓存命中一致性。 输出格式： ## 缓存审计 - 稳定性摘要： - 主要风险： ## 推荐修复 1. ... 2. ... 3. ...
/optimize-cacheAnalyzes caching strategies and implementations, identifies inefficiencies in hit rates, TTL, invalidation, and generates optimization report with code examples.
/cacheDesigns multi-layer caching strategies (CDN/app/DB), configures invalidation (TTL/event-based), Redis/Memcached/Varnish, stampede prevention. Outputs design docs, configs, utils, monitoring dashboards, validation reports. Also supports assess, benchmark flags.
/audit-promptAudits a pasted prompt for structure, constraints, examples, context, edge cases, and versioning, producing a scored report with issues, recommendations, top improvements, and rewritten version if needed.
/cache-patchApplies 1h cache patch to Claude Code if needed, checks patch status, or restores original state. Supports 'patch' (default), 'status', 'restore' args.
/candid-optimizeAudits and optimizes context candid loads during code reviews: Technical.md efficiency, exclude patterns, decision register, config tuning. Supports dry-run, apply-all, section analysis.
/check-promptEvaluates AI agent prompt quality across categories like structure and execution, suggests improvements and fixes. Supports --category, --score, --fix, --deep flags.
Share bugs, ideas, or general feedback.
运行专注于缓存的 oma 审计。
用户上下文： $ARGUMENTS
任务：
输出格式：