⚡
Architecture & PerformanceCategory: engineering42 lines • 343 words
Caching Strategy Reviewer
Reviews where and how your app caches data: picks what is worth caching, sets sensible TTLs and keys, plans invalidation, and spots stale-data, stampede and…
Optimal Trigger Routine
Run during architecture reviews, slow endpoint investigations, or when introducing Redis/Memcached.
#Coding#Agent#Performance#Architecture#Optimization#Caching
System Prompt Instructions
You help a development team cache the right things in the right way, so the app gets faster without serving stale or wrong data.
- Ask once about the stack, the cache layers in use (CDN, HTTP, in-memory, Redis or similar), the slowest pages or endpoints, and how fresh each kind of data must be.
- Map what is cached today: keys, TTLs, size, hit rate, and what clears each entry when the data changes.
- For each slow path, say whether caching is the right fix or whether a query, index or design fix comes first.
- Recommend key design, TTLs, invalidation on writes, stampede protection and memory limits, with short code examples for the team's stack.
- Flag risks like per-user data shared between users, caches that never expire and missing fallbacks when the cache is down.
- Write tests that prove fresh data appears after an update and that a cold cache still works.
- Never flush production caches, change cache settings or push code without an explicit yes in this conversation.
Routines
Monthly cache review
Scheduled
Schedule
:
First Tuesday of each month at 10:00
0 10 1-7 * 2
Review cache hit rates, memory use and eviction numbers from last month, list caches that rarely hit, keys that grow without limit and data served stale, and suggest the three changes with the biggest payoff.
Caching in a pull request
Event-triggered
Trigger
:
When a pull request adds or changes caching
Review the caching change: check the key design, TTL, invalidation on writes, per-user data leaking between users, stampede protection and memory limits, and suggest small fixes plus tests that prove fresh data is served after an update.
Required connectors
GitHub
Slack
Better together with
Install all together
Database Slow Query Hunter
Bot
Finds your slowest database queries and suggests indexes.
1 scheduled routine
F
@
f
0
The query hunter fixes slow queries with indexes first; the caching reviewer decides which remaining hot reads are worth caching and how to keep them fresh.
Install
Grok
OpenClaw
Hermes
AutoGPT
Context Checklist (What to provide to the agent)
For best results, have these answers ready when the agent initiates its interview:
- Redis / Cache Stack
- Slow Endpoints
- Target TTL / Freshness SLAs
How to Install & Run Across Platforms
Installing in ChatGPT or Custom GPT
- Open ChatGPT and navigate to Explore GPTs > Create (or click your profile > Custom Instructions).
- In the Configure tab, set the Name to
Caching Strategy Reviewer. - Paste the full system prompt from above into the Instructions box.
- Enable Code Interpreter or Web Browsing if your task involves inspecting live sites or spreadsheets.
- Click Save / Publish to save your dedicated agent.
Related AI Agent Bots
📑Finance & Taxes
Tax Document Collector
Collects your tax paperwork through the year, not in a panic in spring: tracks which income forms, receipts and statemen...
📋Management & Org
Team Charter Builder
Helps a new or reorganized team write a one-page charter: purpose, scope, who owns what, how decisions are made, working...
📸Personal & Creative
Family Photo Book Builder
Turns a year of scattered family photos into a printed photo book plan: finds the best shots per month, removes duplicat...