What makes OpenAI notable?

953 downloads. Trust evidence available

How should OpenAI be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

OpenAI

OpenAI (openai.com). Use this skill for ANY OpenAI request — reading, creating, updating, and deleting data. Whenever a task involves OpenAI, use this skill instead of calling the API directly.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

953

Updated

Oct 12, 2026

Version

1.0.4

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 953 downloads reported by the source. Last updated 10/12/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 12, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 12, 2026
Adoption signal: 953 downloadsadoption · observed Oct 12, 2026
Latest release: 1.0.4release · observed Sep 20, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.0.4release
- Connects OOMOL workflows to OpenAI through the `oo` CLI using server-side credentials. - Supports Responses API calls, stored response retrieval, input item listing, and token counting. - Provides model discovery and metadata lookup for the connected OpenAI account. - Includes creation actions for embeddings, images, moderation checks, speech, transcription, and translation. - Supports OpenAI batch lifecycle operations, including creating, fetching, and canceling batch jobs. Source: `oomol-lab/skills@792ad44`
Observed Sep 20, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s1790xw8jww1c6hgm8aqy9q25187t1rg:oo-openai

Install using `clawhub skill install s1790xw8jww1c6hgm8aqy9q25187t1rg:oo-openai` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/oomol/oo-openai before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-oomol-oo-openai/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

37,405 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: oo-openai
description: "OpenAI (openai.com). Use this skill for ANY OpenAI request — reading, creating, updating, and deleting data. Whenever a task involves OpenAI, use this skill instead of calling the API directly."
allowed-tools: [Bash(oo *)]
metadata:
  title: "OpenAI"
  author: "OOMOL"
  version: "1.0.4"
  services: ["openai"]
  icon: "https://static.oomol.com/logo/third-party/OpenAI.svg"
---

# OpenAI

Operate **OpenAI** through your OOMOL-connected account. This skill calls the `openai` connector with the [oo CLI](https://github.com/oomol-lab/oo-cli); OOMOL injects credentials server-side, so you never handle raw tokens.

## Running an action

Assume the user has already installed the oo CLI, signed in, and connected OpenAI. **Do not run `oo auth login` or open the connection URL proactively — just run the action.** Fall back to [First-time setup](#first-time-setup) only when a command actually fails with an auth or connection error.

**1. Inspect the contract** to get the authoritative input/output schema before building a payload:

```bash
oo connector schema "openai" --action "<action_name>"
```

**2. Run the action** with a JSON payload that matches the input schema:

```bash
oo connector run "openai" --action "<action_name>" --data '<json>' --json
```

- `--data` takes a JSON object string or `@path/to/file.json`; omit it to send `{}`.
- The response is `{ "data": ..., "meta": { "executionId": "..." } }`; the execution id lives under `meta.executionId`.

Each action is listed below with a one-line description; actions that change state carry a `[write]` or `[destructive]` tag. Before constructing `--data`, fetch the action's live schema with `oo connector schema` to get its authoritative input fields.

## Available actions

- `cancel_batch` — Cancel one OpenAI batch job by its identifier. [destructive]
- `create_audio_transcription` — Transcribe one uploaded audio file with the OpenAI audio transcription API. [write]
- `create_audio_translation` — Translate one uploaded audio file into English with the OpenAI audio translation API. [write]
- `create_batch` — Create an OpenAI batch job from an uploaded input file. [write]
- `create_embeddings` — Create embeddings with an OpenAI embedding model. [write]
- `create_image` — Generate images with the OpenAI image generation API. [write]
- `create_moderation` — Classify text or image inputs with the OpenAI Moderations API. [write]
- `create_response` — Create a non-streaming OpenAI response through the Responses API. [write]
- `create_speech` — Synthesize speech audio from text with the OpenAI audio speech API. [write]
- `get_batch` — Fetch one OpenAI batch job by its identifier.
- `get_input_token_counts` — Count how many input tokens a Responses-style OpenAI request would consume.
- `get_model` — Retrieve the metadata for a single OpenAI model by ID.
- `get_response` — Retrieve one stored OpenAI response by its identifier.
- `list_input_items` — List the stored input items for o

_meta.json

{
  "ownerId": "kn76z80283f7fz2wxq5mf3mf4n87zydc",
  "slug": "oo-openai",
  "version": "1.0.4",
  "publishedAt": 1789875259811
}

skill-card.md

## Description:

OpenAI connector skill for reading, creating, updating, and deleting OpenAI data through an OOMOL-connected account using the oo CLI.

This skill is ready for commercial/non-commercial use.

## Publisher:

[oomol](https://clawhub.ai/user/oomol)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and operators use this skill to inspect OpenAI connector schemas and run OpenAI account actions through the oo CLI, including model lookup, Responses API calls, embeddings, images, moderation, audio, and batch operations.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can run broad read, write, and destructive actions against a credentialed OpenAI account.

Mitigation: Confirm the exact action, payload, cost impact, and target resource before any write or destructive command is run.

Risk: The first-time setup section includes remote shell install commands for the oo CLI.

Mitigation: Install the oo CLI only through a verified package or reviewed installer before relying on this skill.

Risk: OpenAI usage can affect paid or sensitive workloads.

Mitigation: Review the skill before installation and limit use to accounts and data appropriate for the intended workload.

## Reference(s):

- [OpenAI API](https://openai.com/api/)
- [oo CLI](https://github.com/oomol-lab/oo-cli)
- [oo CLI install guide](https://cli.oomol.com/install-guide.md)
- [ClawHub skill page](https://clawhub.ai/oomol/skills/oo-openai)

## Skill Output:

**Output Type(s):** [Shell commands, Configuration, Guidance]

**Output Format:** [Markdown with shell commands and JSON payload guidance]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Connector responses are JSON when the skill runs commands with --json.]

## Skill Version(s):

1.0.4 (source: server release metadata and skill frontmatter)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 4d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular