Agent skill

Horse Streaming

by HashLoad in HashLoad/horse

Diretrizes e workflows para desenvolvimento e manutenção de transmissões de dados em tempo real (Web Streams e Server-Sent Events - SSE) no framework Horse.

MITAuto-check passedBackend & APIs

Install Horse Streaming

skills CLI
$ npx skills add HashLoad/horse --skill horse-streaming -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HashLoad/horse horse-streaming --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HashLoad/horse.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/horse-streaming .claude/skills/horse-streaming && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
horse-streaming
GitHub stars
1.4k
Token cost
~606 tokens
SKILL.md length
230 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Diretrizes e workflows para desenvolvimento e manutenção de transmissões de dados em tempo real (Web Streams e Server-Sent Events - SSE) no framework Horse.

  • Works in 2 steps: Deve-se herdar uma classe especializada… → Registrar a fábrica através de…
  • Tasks that involve Realtime and WebSockets
  • SKILL.md covers 🟢 Conceitos Fundamentais, 🟢 Como usar nas Rotas do Horse, 🟢 Implementação dos… and 🟢 Peculiaridades por Provedor
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Horse Streaming is an agent skill from HashLoad/horse. Diretrizes e workflows para desenvolvimento e manutenção de transmissões de dados em tempo real (Web Streams e Server-Sent Events - SSE) no framework Horse.

Its SKILL.md is about 610 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering Realtime and WebSockets. The repository describes itself as: Fast, opinionated, minimalist web framework for Delphi. The licence is MIT.

When your agent uses it

  • Tasks that involve Realtime and WebSockets

Example prompts

  • “Use the horse-streaming skill to diretriz e workflows para desenvolvimento e manutenção de transmissões de dados em tempo real (Web Streams e…”
  • “/horse-streaming”

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Deve-se herdar uma classe especializada de THorseStreamWriterBase e implementar os métodos Write (escrita física), IsConnected (validação…
  2. Registrar a fábrica através de THorseResponse.RegisterStreamWriterFactory(Factory).

What it can do on your machine

Read from SKILL.md and the folder at commit d4351a5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are delphi).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Horse Streaming loads about 606 tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 230 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~606

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HashLoad/horse at commit d4351a5, republished under its MIT licence (© HashLoad). 230 words, ~606 tokens.

Download SKILL.mdSave it as .claude/skills/horse-streaming/SKILL.md (or your agent's skills folder).
name
horse-streaming
description
Diretrizes e workflows para desenvolvimento e manutenção de transmissões de dados em tempo real (Web Streams e Server-Sent Events - SSE) no framework Horse.

Horse Streaming Development Guide

Esta skill guia o desenvolvimento, depuração e manutenção de fluxos de streaming de dados (Web Streams / SSE) no framework Horse.

🟢 Conceitos Fundamentais

  • Web Streams (NDJSON): Envio de dados formatados como múltiplos JSONs delimitados por quebras de linha (\n), utilizando o cabeçalho Transfer-Encoding: chunked.
  • Server-Sent Events (SSE): Fluxo unidirecional persistente onde o servidor envia eventos estruturados sob o formato event: message\ndata: ...\n\n com o Content-Type text/event-stream.

🟢 Como usar nas Rotas do Horse

Para enviar dados via streaming, o manipulador da rota deve definir o ContentType adequado e invocar o Res.SendStream:

delphi
  THorse.Get('/stream',
    procedure(Req: THorseRequest; Res: THorseResponse; Next: TProc)
    begin
      Res.ContentType('application/x-ndjson; charset=utf-8');
      Res.SendStream(
        procedure(const AWriter: IHorseStreamWriter)
        begin
          if AWriter.IsConnected then
            AWriter.Write('{"data": "teste"}'#10);
        end);
    end);

🟢 Implementação dos Provedores Físicos

Ao criar ou estender novos provedores lógicos de transporte no Horse:

  1. Deve-se herdar uma classe especializada de THorseStreamWriterBase e implementar os métodos Write (escrita física), IsConnected (validação física de conectividade do socket) e Close (fim de transmissão/descarregamento de buffers).
  2. Registrar a fábrica através de THorseResponse.RegisterStreamWriterFactory(Factory).

🟢 Peculiaridades por Provedor

Indy (TIdHTTPAppResponse)
  • Conexão: A thread física é acessada via o campo FThread da Friend Class.
  • Envio de Headers: Invocar MoveCookiesAndCustomHeaders do TIdHTTPAppResponse para carregar headers customizados e cookies antes do WriteHeader.
  • Flag de Envio: Marcar FSent := True no TIdHTTPAppResponse para impedir que o WebBroker dispare novamente os headers no fim do dispatcher.
  • Bypass de HTML do Indy: Preencher ContentStream com um TMemoryStream vazio, FreeContentStream := True e ContentLength := 0 para desativar a injeção do HTML default de 200 OK de 39 bytes pelo Indy.

© HashLoad, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/horse-streaming of HashLoad/horse.

Open the folder on GitHubat commit d4351a5

Compare with similar skills

Horse Streaming next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Horse Streaming compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Horse Streaming this skillHashLoad/horse1.4k—~606Automated safety check: PassMIT
Supabase Development and Debuggingsupabase/agent-skills2.7k3 repos~3.6kAutomated safety check: PassMIT
Use Yaakmountain-loop/yaak19k—~1.9kAutomated safety check: PassMIT
Gemini Live API Devgoogle-gemini/gemini-skills4.3k—~4.6kAutomated safety check: PassApache-2.0
Web3 PolymarketPolymarket/agent-skills1912 repos~2kAutomated safety check: PassNone
GraphQL ArchitectJeffallan/claude-skills12k1 repos~1.3kAutomated safety check: PassMIT

Similar skills

  • Official

    General Supabase skill for database, auth, Edge Functions, Realtime and storage work, plus client libraries, migrations, security audits, debugging and reading logs.

    2.7k GitHub starsUsed in 3 repos~3.6k tokens
    Backend & APIsAuto-check passed
  • Use Yaak

    mountain-loop/yaak

    A skill your agent uses when the user mentions Yaak, a Yaak workspace, or the yaak command, or asks to call, hit, or smoke test HTTP/REST endpoints, save or organize API requests for reuse or manual…

    19k GitHub stars~1.9k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Gemini Live API Dev

    google-gemini/gemini-skills

    Official

    A skill your agent uses when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) to Gemini 3.8 Live.

    4.3k GitHub stars~4.6k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Web3 Polymarket

    Polymarket/agent-skills

    Polymarket integration for prediction market trading on Polygon.

    191 GitHub starsUsed in 2 repos~2k tokens
    Backend & APIsAuto-check passed
  • GraphQL Architect

    Jeffallan/claude-skills

    Designs GraphQL schemas and Apollo Federation graphs, with DataLoader resolvers, subscriptions, query complexity limits and caching.

    12k GitHub starsUsed in 1 repo~1.3k tokens
    Backend & APIsAuto-check passed
  • Broker Integration

    marketcalls/openalgo

    Integrate a new Indian broker into OpenAlgo, or modify an existing broker plugin.

    2.8k GitHub stars~4.7k tokensUpdated today
    Backend & APIsAuto-check: notes

More from HashLoad/horse

All 23 skills in this repo
  • Horse App Structure

    HashLoad/horse

    Guide for setting up Horse applications, bootstrap program (.dpr), basic console initialization, and registering modules.

    1.4k GitHub stars~716 tokensUpdated yesterday
    Auto-check passed
  • Guide for setting up thread-safe database connection pooling (FireDAC / UniDAC) in multithreaded Horse applications.

    1.4k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Guide for managing request-scoped contextual services and IoC (dependency injection) in Delphi and Lazarus.

    1.4k GitHub stars~985 tokensUpdated yesterday
    Auto-check passed
  • Horse Files Streams

    HashLoad/horse

    Guide to handling file uploads (multipart), downloads, and stream lifetime management in the Horse framework.

    1.4k GitHub stars~601 tokensUpdated yesterday
    Auto-check passed
  • Horse Grpc

    HashLoad/horse

    Guidelines and workflows for developing and maintaining gRPC services, HTTP/2 h2c transport, and Protobuf serialization within the Horse framework.

    1.4k GitHub stars~776 tokensUpdated yesterday
    Auto-check passed
  • Guide for writing automated integration tests for Horse endpoints using DUnit/DUnitX and THTTPClient.

    1.4k GitHub stars~964 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Horse Streaming

What does Horse Streaming do?

Diretrizes e workflows para desenvolvimento e manutenção de transmissões de dados em tempo real (Web Streams e Server-Sent Events - SSE) no framework Horse. Horse Streaming is an agent skill from HashLoad/horse. Diretrizes e workflows para desenvolvimento e manutenção de transmissões de dados em tempo real (Web Streams e Server-Sent Events - SSE) no framework Horse.

When should I use Horse Streaming?

Horse Streaming fits situations like: tasks that involve Realtime and WebSockets.

How do I install Horse Streaming in Claude Code?

Run `npx skills add HashLoad/horse --skill horse-streaming -a claude-code`. Or copy the skill folder (.agents/skills/horse-streaming in HashLoad/horse) into .claude/skills/horse-streaming in your project. Claude Code loads it when a task matches its description.

How do I install Horse Streaming in Codex?

Run `npx skills add HashLoad/horse --skill horse-streaming -a codex`. Or copy the skill folder (.agents/skills/horse-streaming in HashLoad/horse) into .agents/skills/horse-streaming in your project. Codex loads it when a task matches its description.

Can I use Horse Streaming in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HashLoad/horse --skill horse-streaming -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/horse-streaming, .gemini/skills/horse-streaming, .github/skills/horse-streaming and .opencode/skills/horse-streaming in your project.

What does Horse Streaming need to run?

SKILL.md names no scripts, command-line tools or credentials: Horse Streaming is instructions for the agent only.

Does Horse Streaming access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Horse Streaming safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Horse Streaming use?

Horse Streaming is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Horse Streaming use?

About 606 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Horse Streaming?

Skills that share tags, products or a category with Horse Streaming: Supabase Development and Debugging (supabase/agent-skills, 2.7k stars), Use Yaak (mountain-loop/yaak, 19k stars), Gemini Live API Dev (google-gemini/gemini-skills, 4.3k stars) and Web3 Polymarket (Polymarket/agent-skills, 191 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Horse Streaming?

HashLoad (a GitHub organization) maintains it in HashLoad/horse, which has 1,377 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 7, 2026.

Source: HashLoad/horse on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.