cc-skill:openai-assistants-api

Claude Code skill · anthropic · active

last 30 days

0 calls

0 of 30 days active

explain like I am new to this

what it does

This skill guides you through building applications with OpenAI's Assistants API. It helps you set up persistent conversations (called threads), add tools like file search and code execution, and manage the back-and-forth between your app and OpenAI. You'll get working code examples and best practices.

who it is for

Developers building chatbots, research tools, or document search features that need to remember conversations or run code without building those capabilities from scratch.

when it fires

You mention OpenAI Assistants, Threads, Runs, file search, vector stores, code interpreter, or custom function calling for OpenAI.

say something like

"Show me how to build a research assistant with the OpenAI Assistants API that can search through files"
"I want to create a chatbot that remembers conversation history. Should I use Chat Completions or Assistants?"
"How do I set up code interpreter in OpenAI Assistants to analyze data files?"

what you might get back

An example might show you how to create an Assistant with instructions, attach the file_search tool, create a Thread for the conversation, send a user message, run it, and then poll for the response. The code includes comments explaining when to use Assistants versus simpler APIs, and warns about setting timeouts to control costs.

how to know it worked

You received working Python code that uses the OpenAI beta API to set up an Assistant, Thread, and Run, along with clear guidance on whether Assistants or Chat Completions is right for your use case.

is this skill working for me

never used

cloud runs

0 deployments

local fires

Claude Code (optional)

posts published

from drafts

attributed

$0.00

signups + revenue

Deploy this skill as a cloud automation to put it to work — runs on a schedule, dispatches output to Telegram or email, and logs every result here.

Deploy this skill

no laptop required

Run this skill on a schedule in the cloud. Pipe output to Telegram, email, or any webhook. Every run is logged here with full output, cost, and thumbs feedback.

How this performs

Cloud-automation runs, real outputs, and feedback.

No cloud runs yet for this skill.

Once you deploy it (above), every run will show up here with the actual output, exact cost, and a thumbs button so you can rate quality over time.

what this is

Claude Code skill at /Users/olanrewajukareem/.claude/skills/openai-assistants-api/SKILL.md. Auto-triggered by description matching when you type in Claude Code, OR embedded into agent system prompts (LeadFlow framework skills are wired this way). Auto-synced from disk every 6h via launchd.

Use this skill when building with OpenAI's Assistants API, including the Assistant + Thread + Run model, function calling, code interpreter, file search, vector stores, and streaming. Triggers on "OpenAI Assistants", "Assistants API", "OpenAI Thread"

Local Claude Code use (optional)

Install the SKILL.md file locally so this skill is available the next time you open Claude Code on your Mac. Most users skip this and just use cloud deployments above.

Install on your machine

Save this skill to ~/.claude/skills/openai-assistants-api/SKILL.md so Claude Code auto-loads it whenever its description matches your prompt.

30-day activity

never used

2026-04-03today

cost model

unitincluded

capabilities

{
  "source": "global",
  "description": "Use this skill when building with OpenAI's Assistants API, including the Assistant + Thread + Run model, function calling, code interpreter, file search, vector stores, and streaming. Triggers on \"OpenAI Assistants\", \"Assistants API\", \"OpenAI Thread\", \"OpenAI Run\", \"code interpreter\", \"file search\", \"vector store\", \"OpenAI tools\", \"OpenAI function calling\". Different from Chat Completions API (stateless) and Claude Agent SDK."
}

how it gets called

{
  "method": "embed_in_prompt",
  "skill_path": "/Users/olanrewajukareem/.claude/skills/openai-assistants-api/SKILL.md"
}

This tool has never been called in the last 30 days.

That means either: (a) the system has not had a task that matched its strengths, (b) a more cost-effective alternative was picked by the router, or (c) the related automation is toggled OFF on /automations. The Recommender reviews idle tools weekly and may suggest killing it.