openai
Skill38 starsChanged 8 months agoMITView on GitHub
Manage OpenAI models, assistants, files and usage via REST API
2 other projects use a version of this.
Adopted by
Most recently taken up by
- JustinPerea/nebula-nodestheir own version, first seen Nov 5, 2026
- jcsaaddupuy/badrobotstheir own version, first seen Feb 26, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- JustinPerea/nebula-nodes★ 23same name
- jcsaaddupuy/badrobots★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository36 other files it gives its agents.
- abacatepaySkill
- appsignalSkill
- clickupSkill
- cloudflareSkill
- cloudinarySkill
- datadogSkill
- digitaloceanSkill
- discordSkill
- firebaseSkill
- flyioSkill
- google-sheetsSkill
- herokuSkill
- honeybadgerSkill
- hostingerSkill
- hubspotSkill
- intercomSkill
- jiraSkill
- linearSkill
- mercadopagoSkill
- n8nSkill
- notionSkill
- planetscaleSkill
- posthogSkill
- railwaySkill
- resendSkill
- rewriteSkill
- sentrySkill
- shopifySkill
- slackSkill
- stripeSkill
- supabaseSkill
- trelloSkill
- twilioSkill
- vercelSkill
- xSkill
- zendeskSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 35
If the output is OK, proceed to the Flow section.
- Very specific: line 37
If the output is SETUP_NEEDED, guide the user step by step.
- Distinctive: line 54
If the script outputs an error, the key is invalid.
≈ “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.
Files
/openai
Connect to the OpenAI API to manage models, assistants, files, fine-tuning jobs and usage. Pure Ruby, zero gems — stdlib only.
Structure
scripts/
├── auth.rb # Bearer token + openai_request helper (required by all scripts)
├── check_setup.rb # Check if token exists (outputs OK or SETUP_NEEDED)
├── save_token.rb # Save and validate an API token
├── models.rb # List available models
├── assistants.rb # List assistants
├── assistant.rb # Get assistant details
├── files.rb # List uploaded files
├── file.rb # Get file details
├── delete_file.rb # Delete a file
├── usage.rb # Get usage stats (last 30 days)
└── fine_tuning_jobs.rb # List fine-tuning jobsSetup (check before using)
ruby ~/.claude/skills/openai/scripts/check_setup.rbIf the output is OK, proceed to the Flow section.
If the output is SETUP_NEEDED, guide the user step by step. Present ONE step at a time, wait for the user to confirm before moving to the next.
Step 1 — Ask the user to create an API key:
You need an OpenAI API key. Go to API Keys in the OpenAI Platform dashboard: https://platform.openai.com/api-keys
Click Create new secret key, give it a name (e.g. "hitank"), and copy the key.
Paste the key here.
Step 2 — When the user pastes the key, save it:
ruby ~/.claude/skills/openai/scripts/save_token.rb 'PASTED_KEY'If the script outputs an error, the key is invalid. Ask the user to double-check and try again.
If setup is not complete, DO NOT proceed to the Flow. Complete all steps first.
Flow
The argument $ARGUMENTS may contain a model name or assistant ID.
Step 1: List models
ruby ~/.claude/skills/openai/scripts/models.rbPresent the models to the user. If $ARGUMENTS matches a model name, highlight it.
Step 2: List assistants
ruby ~/.claude/skills/openai/scripts/assistants.rbPresent the assistants. If $ARGUMENTS matches an assistant ID, show its details automatically.
Step 3: Actions
Get assistant details:
ruby ~/.claude/skills/openai/scripts/assistant.rb ASSISTANT_IDList uploaded files:
ruby ~/.claude/skills/openai/scripts/files.rbGet file details:
ruby ~/.claude/skills/openai/scripts/file.rb FILE_IDDelete a file (requires user confirmation):
Show the file details first, then ask: "Do you want to delete this file?" Only execute after a "yes".
ruby ~/.claude/skills/openai/scripts/delete_file.rb FILE_IDGet usage stats (last 30 days):
ruby ~/.claude/skills/openai/scripts/usage.rbList fine-tuning jobs:
ruby ~/.claude/skills/openai/scripts/fine_tuning_jobs.rbNotes
- Pure Ruby, zero gems — stdlib only (json, net/http, uri, fileutils)
- Auth via Bearer token in Authorization header
- Token file:
~/.config/openai/token(outside the repo, never commit) - Deleting files requires explicit user confirmation
- Assistants API requires the
OpenAI-Beta: assistants=v2header - Base URL:
https://api.openai.com/v1
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
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.

