agentleFS
aksuharunaksuharun/skills/raison-sdk/SKILL.md

raison-sdk

Skill1 starsChanged 6 months agoMITView on GitHub

Raison JavaScript/TypeScript prompt management SDK. Use when working with the `raison` npm package to render templates or query prompt data.

  • Reads credentials
  • Installs packages

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All methods (render, find, findOne) await the initial WebSocket sync automatically — no race conditions, no manual readiness checks.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Raison SDK

Raison is a prompt management platform. Prompts live in the dashboard at raison.ist with full version history and are delivered to applications via real-time WebSocket sync — no redeployments needed when prompts change.

Key concepts: Organization → Project → Agent → Prompt. Each project has Development/Staging/Production environments, each with its own rsn_ API key.

Installation

npm install raison

Connect and Use

import { Raison } from "raison";

const raison = new Raison({ apiKey: process.env.RAISON_API_KEY }); // rsn_...

// Render a prompt with variables (Handlebars template)
const message = await raison.render("PROMPT_ID", { userName: "Alice" });

// Query all prompts in this environment
const all = await raison.find();

// Find by agent + name (most efficient — uses composite index)
const systemPrompt = await raison.findOne({ agentId: "AGENT_ID", name: "system-prompt" });

// Shutdown
raison.disconnect();

All methods (render, find, findOne) await the initial WebSocket sync automatically — no race conditions, no manual readiness checks.

Core Methods

MethodReturnsNotes
render(id, vars?)Promise<string>Returns "" if not found; raw content if no vars
find(params?)Promise<Prompt[]>Returns [] if no match
findOne(params)Promise<Prompt | null>Returns null if no match
disconnect()voidCall on process shutdown
Raison.registerHelper(name, fn)voidGlobal Handlebars helper; register at startup

Finding IDs

  • Prompt ID — Dashboard: open project → click agent → click prompt → copy ID at top
  • Agent ID — Dashboard: open project → click agent → copy ID at top
  • IDs are stable across environments (same ID works in Dev/Staging/Prod)

Error Handling Pattern

const prompt = await raison.render("PROMPT_ID", variables);
if (!prompt) {
  return FALLBACK_SYSTEM_PROMPT; // render() returns "" for missing prompts
}

References

  • sdk-reference.md — Full API reference: constructor options, method signatures, types, and error behavior table. Read when you need precise signatures, TypeScript types, or to check all error cases.
  • templating.md — Handlebars guide: variables, nested objects, {{#if}}, {{#each}}, custom helpers with code examples. Read when writing or debugging prompt templates.
  • examples.md — Integration patterns: Anthropic/Claude, OpenAI, Express.js, Next.js serverless singleton, multiple environments, graceful shutdown. Read when integrating Raison into a specific framework or setting up a production pattern.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.