Low Latency Systems logo

Low Latency Systems

Community
egorfedorov
low-latency-systems

Design, diagnose, and optimize low-latency request paths in backend and realtime systems. Use when profiling p50/p95/p99 latency regressions, reducing queueing and lock contention, tuning network/serialization overhead, validating tail-latency improvements, or preparing latency sign-off evidence with strict percentile gates.

Overview

Publisheregorfedorov
RepositorySlot-Casino-Game-Developer-Skills-for-Stake-Engine
Skill namelow-latency-systems
Stars
63
Forks
16
Bundled files
5
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by egorfedorov on GitHub. Read the source before you install it.

Installation

Install the Low Latency Systems AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/egorfedorov/Slot-Casino-Game-Developer-Skills-for-Stake-Engine.git /tmp/Slot-Casino-Game-Developer-Skills-for-Stake-Engine
mkdir -p .claude/skills
cp -r /tmp/Slot-Casino-Game-Developer-Skills-for-Stake-Engine/low-latency-systems .claude/skills/low-latency-systems
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Low Latency Systems in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Low Latency Systems on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Low Latency Systems is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Low Latency Systems

Use this skill to turn latency incidents and regressions into measurable, reproducible fixes.

Workflow

  1. Lock measurement context first.
  • Capture workload, concurrency, payload sizes, warmup policy, and hardware/runtime settings.
  • Keep baseline and current runs environment-compatible.
  1. Decompose latency path.
  • Split end-to-end latency into ingress, queue, compute, storage/network, and egress components.
  • Prioritize tail-latency contributors over average-only improvements.
  1. Apply targeted latency fixes.
  • Reduce blocking, contention, and unbounded queues.
  • Reduce allocations/serialization overhead in hot paths.
  • Use batching, caching, and async boundaries only when measured beneficial.
  1. Validate percentile regressions.
  • Compare baseline vs current percentiles (p50, p95, p99, optional p999).
  • Gate release on configured regression thresholds.
  1. Produce sign-off output.
  • Provide measured deltas, affected components/files, and residual risks.
  • Include exact rerun commands for verification.

Commands

bash
python3 scripts/compare_latency_runs.py \
  --baseline <baseline.json> \
  --current <current.json> \
  --threshold-pct 5

Treat non-zero exits as blocker regressions.

Output Contract

Return:

  1. Latency Baseline: environment/workload assumptions.
  2. Findings: percentile deltas and hotspot classes.
  3. Optimization Plan: exact changes with expected impact.
  4. Verification: rerun commands and regression gates.
  5. Residual Risks: variance or unresolved tail spikes.

References

  • references/workflow.md: detailed low-latency process.
  • references/latency-playbook.md: bottleneck-to-fix mapping.
  • references/signoff-template.md: concise sign-off format.

Execution Rules

  • Prioritize tail latency (p95/p99) when evaluating user impact.
  • Keep measurement setup stable across comparisons.
  • Require before/after evidence for each claimed improvement.
  • Escalate threshold breaches as blockers.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Low Latency Systems AI skill do?

Design, diagnose, and optimize low-latency request paths in backend and realtime systems. Use when profiling p50/p95/p99 latency regressions, reducing queueing and lock contention, tuning network/serialization overhead, validating tail-latency improvements, or preparing latency sign-off evidence with strict percentile gates.

Why use Low Latency Systems on TypingMind?

Because you install it once and use it with any model. Low Latency Systems is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Low Latency Systems in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/egorfedorov/Slot-Casino-Game-Developer-Skills-for-Stake-Engine/tree/main/low-latency-systems. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Low Latency Systems?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Low Latency Systems?

As many as you like. As long as a model supports skills, you can use Low Latency Systems with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Low Latency Systems AI skill free?

It is published on GitHub by egorfedorov. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
mattpocock logo

Code Review

mattpocock
CommunityPopular

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what…

22.3K
264.4K
1 files
View
mattpocock logo

Codebase Design

mattpocock
CommunityPopular

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or…

22.3K
264.4K
3 files
View
mattpocock logo

Diagnosing Bugs

mattpocock
CommunityPopular

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

22.3K
264.4K
2 files
View
mattpocock logo

Implement

mattpocock
CommunityPopular

Implement a piece of work based on a spec or set of tickets.

22.3K
264.4K
1 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇