{"id":"3840191b-d97e-4ae8-a96d-433d21e8b21c","entityType":"agent","slug":"clawhub-oomol-oo-openai","name":"OpenAI","canonicalUrl":"https://www.xpersona.co/agent/clawhub-oomol-oo-openai","canonicalPath":"/agent/clawhub-oomol-oo-openai","generatedAt":"2026-10-13T21:56:43.938Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T02:37:45.182Z","emptyReason":null},"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.","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 953 downloads reported by the source. Last updated 10/12/2026.","installCommand":"clawhub skill install s1790xw8jww1c6hgm8aqy9q25187t1rg:oo-openai","sourceUrl":"https://clawhub.ai/oomol/oo-openai","homepage":"https://clawhub.ai/oomol/skills/oo-openai","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/oomol/oo-openai","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/oomol/skills/oo-openai","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"OpenAI technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-12T02:37:45.182Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T02:37:45.182Z","emptyReason":null},"stars":null,"forks":null,"downloads":953,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.4","tractionLabel":"953 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T02:37:45.169Z","emptyReason":null},"lastUpdatedAt":"2026-10-12T02:37:45.182Z","lastCrawledAt":"2026-10-12T02:37:45.169Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-13T02:37:45.169Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.4","createdAt":"2026-09-20T03:34:19.811Z","changelog":"- 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`","fileCount":3,"zipByteSize":3526},{"version":"1.0.3","createdAt":"2026-09-15T05:46:14.478Z","changelog":"- Operate OpenAI through an OOMOL-connected account using the `oo` CLI. - Inspect live action schemas before constructing requests. - Support responses, embeddings, image generation, speech, transcription, translation, moderation, and token counting. - Manage batch jobs and retrieve models, responses, and stored input items. - Keep credentials server-side and require confirmation for state-changing actions. Source: `oomol-lab/skills@75bac03`","fileCount":3,"zipByteSize":3666},{"version":"1.0.1","createdAt":"2026-06-09T10:21:41.358Z","changelog":"- Connects Codex to OpenAI through the OOMOL `oo` CLI and server-side credential handling. - Uses live connector schemas before execution so action payloads match the current OpenAI contract. - Supports Responses API calls, response retrieval, input item listing, model lookup, and model listing. - Adds write actions for batches, embeddings, images, moderation, transcription, translation, and speech synthesis. - Documents safety rules for read, write, and destructive actions plus first-time setup fallback steps. Source: `oomol-lab/skills@146ef20`","fileCount":3,"zipByteSize":3531},{"version":"1.0.0","createdAt":"2026-06-03T14:32:11.879Z","changelog":"- Initial release of `oo-openai`, an OOMOL skill for operating OpenAI through the `openai` connector and `oo` CLI without handling raw API tokens locally. - Adds 15 OpenAI actions covering Responses, embeddings, image generation, moderation, audio transcription, audio translation, speech synthesis, batches, models, stored responses, input items, and token counting. - Documents the standard action workflow: inspect the live connector schema first, then run actions with JSON payloads via `oo connector run`. - Includes safety guidance for read, write, and destructive actions, with explicit confirmation required before state-changing or destructive OpenAI operations. - Provides first-time setup and troubleshooting notes for missing CLI installation, authentication failures, connection scope issues, expired credentials, and billing stops.","fileCount":18,"zipByteSize":11655}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s1790xw8jww1c6hgm8aqy9q25187t1rg:oo-openai","setupComplexity":"low","setupSteps":["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":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-oomol-oo-openai/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-oomol-oo-openai/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-oomol-oo-openai/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-oomol-oo-openai/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-oomol-oo-openai/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-oomol-oo-openai/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-13T21:56:43.937Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-oomol-oo-openai/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-oomol-oo-openai/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-oomol-oo-openai/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-oomol-oo-openai/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T02:37:45.182Z","emptyReason":null},"readme":"Skill: OpenAI\n\nOwner: oomol\n\nSummary: 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.\n\nTags: latest:1.0.4\n\nVersion history:\n\nv1.0.4 | 2026-09-20T03:34:19.811Z | user\n\n- Connects OOMOL workflows to OpenAI through the `oo` CLI using server-side credentials.\n- Supports Responses API calls, stored response retrieval, input item listing, and token counting.\n- Provides model discovery and metadata lookup for the connected OpenAI account.\n- Includes creation actions for embeddings, images, moderation checks, speech, transcription, and translation.\n- Supports OpenAI batch lifecycle operations, including creating, fetching, and canceling batch jobs.\n\nSource: `oomol-lab/skills@792ad44`\n\nv1.0.3 | 2026-09-15T05:46:14.478Z | user\n\n- Operate OpenAI through an OOMOL-connected account using the `oo` CLI.\n- Inspect live action schemas before constructing requests.\n- Support responses, embeddings, image generation, speech, transcription, translation, moderation, and token counting.\n- Manage batch jobs and retrieve models, responses, and stored input items.\n- Keep credentials server-side and require confirmation for state-changing actions.\n\nSource: `oomol-lab/skills@75bac03`\n\nv1.0.1 | 2026-06-09T10:21:41.358Z | user\n\n- Connects Codex to OpenAI through the OOMOL `oo` CLI and server-side credential handling.\n- Uses live connector schemas before execution so action payloads match the current OpenAI contract.\n- Supports Responses API calls, response retrieval, input item listing, model lookup, and model listing.\n- Adds write actions for batches, embeddings, images, moderation, transcription, translation, and speech synthesis.\n- Documents safety rules for read, write, and destructive actions plus first-time setup fallback steps.\n\nSource: `oomol-lab/skills@146ef20`\n\nv1.0.0 | 2026-06-03T14:32:11.879Z | user\n\n- Initial release of `oo-openai`, an OOMOL skill for operating OpenAI through the `openai` connector and `oo` CLI without handling raw API tokens locally.\n- Adds 15 OpenAI actions covering Responses, embeddings, image generation, moderation, audio transcription, audio translation, speech synthesis, batches, models, stored responses, input items, and token counting.\n- Documents the standard action workflow: inspect the live connector schema first, then run actions with JSON payloads via `oo connector run`.\n- Includes safety guidance for read, write, and destructive actions, with explicit confirmation required before state-changing or destructive OpenAI operations.\n- Provides first-time setup and troubleshooting notes for missing CLI installation, authentication failures, connection scope issues, expired credentials, and billing stops.\n\nArchive index:\n\nArchive v1.0.4: 3 files, 3526 bytes\n\nFiles: skill-card.md (2138b), SKILL.md (4509b), _meta.json (128b)\n\nFile v1.0.4:SKILL.md\n\n---\nname: oo-openai\ndescription: \"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.\"\nallowed-tools: [Bash(oo *)]\nmetadata:\n  title: \"OpenAI\"\n  author: \"OOMOL\"\n  version: \"1.0.4\"\n  services: [\"openai\"]\n  icon: \"https://static.oomol.com/logo/third-party/OpenAI.svg\"\n---\n\n# OpenAI\n\nOperate **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.\n\n## Running an action\n\nAssume 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.\n\n**1. Inspect the contract** to get the authoritative input/output schema before building a payload:\n\n```bash\noo connector schema \"openai\" --action \"<action_name>\"\n```\n\n**2. Run the action** with a JSON payload that matches the input schema:\n\n```bash\noo connector run \"openai\" --action \"<action_name>\" --data '<json>' --json\n```\n\n- `--data` takes a JSON object string or `@path/to/file.json`; omit it to send `{}`.\n- The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`; the execution id lives under `meta.executionId`.\n\nEach 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.\n\n## Available actions\n\n- `cancel_batch` — Cancel one OpenAI batch job by its identifier. [destructive]\n- `create_audio_transcription` — Transcribe one uploaded audio file with the OpenAI audio transcription API. [write]\n- `create_audio_translation` — Translate one uploaded audio file into English with the OpenAI audio translation API. [write]\n- `create_batch` — Create an OpenAI batch job from an uploaded input file. [write]\n- `create_embeddings` — Create embeddings with an OpenAI embedding model. [write]\n- `create_image` — Generate images with the OpenAI image generation API. [write]\n- `create_moderation` — Classify text or image inputs with the OpenAI Moderations API. [write]\n- `create_response` — Create a non-streaming OpenAI response through the Responses API. [write]\n- `create_speech` — Synthesize speech audio from text with the OpenAI audio speech API. [write]\n- `get_batch` — Fetch one OpenAI batch job by its identifier.\n- `get_input_token_counts` — Count how many input tokens a Responses-style OpenAI request would consume.\n- `get_model` — Retrieve the metadata for a single OpenAI model by ID.\n- `get_response` — Retrieve one stored OpenAI response by its identifier.\n- `list_input_items` — List the stored input items for one OpenAI response.\n- `list_models` — List the OpenAI models available to the current API key.\n\n## Safety\n\n- Untagged actions are reads (get / list / search) — safe to run directly.\n- **Actions tagged `[write]` change OpenAI state — confirm the exact payload and effect with the user before running.**\n- **Actions tagged `[destructive]` remove or overwrite data — always confirm the target and get explicit approval first.**\n\n## First-time setup\n\nThese are **one-time** steps — do not repeat them on every call. Run a step only when a command fails for the matching reason.\n\n- **`oo: command not found`** — install the oo CLI (other platforms: <https://cli.oomol.com/install-guide.md>):\n\n  ```bash\n  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux\n  ```\n\n  ```powershell\n  irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell\n  ```\n\n- **Not signed in / authentication error** — sign in to your OOMOL account once:\n\n  ```bash\n  oo auth login\n  ```\n\n- **`scope_missing` / `credential_expired` / `app_not_ready` / `app_not_found`** — OpenAI is not connected, or the connection expired or lacks a scope. Connect once (auth type: API key) at:\n\n  ```text\n  https://console.oomol.com/app-connections?provider=openai\n  ```\n\n- **HTTP 402 / `OOMOL_INSUFFICIENT_CREDIT`** — billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.\n\n## Resources\n\n- OpenAI homepage: https://openai.com/api/\n\nFile v1.0.4:_meta.json\n\n{\n  \"ownerId\": \"kn76z80283f7fz2wxq5mf3mf4n87zydc\",\n  \"slug\": \"oo-openai\",\n  \"version\": \"1.0.4\",\n  \"publishedAt\": 1789875259811\n}\n\nFile v1.0.4:skill-card.md\n\n## Description:\n\nOpenAI connector skill for reading, creating, updating, and deleting OpenAI data through an OOMOL-connected account using the oo CLI.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[oomol](https://clawhub.ai/user/oomol)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers 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.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can run broad read, write, and destructive actions against a credentialed OpenAI account.\n\nMitigation: Confirm the exact action, payload, cost impact, and target resource before any write or destructive command is run.\n\nRisk: The first-time setup section includes remote shell install commands for the oo CLI.\n\nMitigation: Install the oo CLI only through a verified package or reviewed installer before relying on this skill.\n\nRisk: OpenAI usage can affect paid or sensitive workloads.\n\nMitigation: Review the skill before installation and limit use to accounts and data appropriate for the intended workload.\n\n## Reference(s):\n\n- [OpenAI API](https://openai.com/api/)\n- [oo CLI](https://github.com/oomol-lab/oo-cli)\n- [oo CLI install guide](https://cli.oomol.com/install-guide.md)\n- [ClawHub skill page](https://clawhub.ai/oomol/skills/oo-openai)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, Configuration, Guidance]\n\n**Output Format:** [Markdown with shell commands and JSON payload guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Connector responses are JSON when the skill runs commands with --json.]\n\n## Skill Version(s):\n\n1.0.4 (source: server release metadata and skill frontmatter)\n\n## Ethical Considerations:\n\nUsers 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.\n\nArchive v1.0.3: 3 files, 3666 bytes\n\nFiles: skill-card.md (2559b), SKILL.md (4493b), _meta.json (128b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: oo-openai\ndescription: \"OpenAI (openai.com). Use this skill for ANY OpenAI request — reading, creating, and updating data. Whenever a task involves OpenAI, use this skill instead of calling the API directly.\"\nallowed-tools: [Bash(oo *)]\nmetadata:\n  title: \"OpenAI\"\n  author: \"OOMOL\"\n  version: \"1.0.3\"\n  services: [\"openai\"]\n  icon: \"https://static.oomol.com/logo/third-party/OpenAI.svg\"\n---\n\n# OpenAI\n\nOperate **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.\n\n## Running an action\n\nAssume 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.\n\n**1. Inspect the contract** to get the authoritative input/output schema before building a payload:\n\n```bash\noo connector schema \"openai\" --action \"<action_name>\"\n```\n\n**2. Run the action** with a JSON payload that matches the input schema:\n\n```bash\noo connector run \"openai\" --action \"<action_name>\" --data '<json>' --json\n```\n\n- `--data` takes a JSON object string or `@path/to/file.json`; omit it to send `{}`.\n- The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`; the execution id lives under `meta.executionId`.\n\nEach 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.\n\n## Available actions\n\n- `cancel_batch` — Cancel one OpenAI batch job by its identifier. [write]\n- `create_audio_transcription` — Transcribe one uploaded audio file with the OpenAI audio transcription API. [write]\n- `create_audio_translation` — Translate one uploaded audio file into English with the OpenAI audio translation API. [write]\n- `create_batch` — Create an OpenAI batch job from an uploaded input file. [write]\n- `create_embeddings` — Create embeddings with an OpenAI embedding model. [write]\n- `create_image` — Generate images with the OpenAI image generation API. [write]\n- `create_moderation` — Classify text or image inputs with the OpenAI Moderations API. [write]\n- `create_response` — Create a non-streaming OpenAI response through the Responses API. [write]\n- `create_speech` — Synthesize speech audio from text with the OpenAI audio speech API. [write]\n- `get_batch` — Fetch one OpenAI batch job by its identifier.\n- `get_input_token_counts` — Count how many input tokens a Responses-style OpenAI request would consume.\n- `get_model` — Retrieve the metadata for a single OpenAI model by ID.\n- `get_response` — Retrieve one stored OpenAI response by its identifier.\n- `list_input_items` — List the stored input items for one OpenAI response.\n- `list_models` — List the OpenAI models available to the current API key.\n\n## Safety\n\n- Untagged actions are reads (get / list / search) — safe to run directly.\n- **Actions tagged `[write]` change OpenAI state — confirm the exact payload and effect with the user before running.**\n- **Actions tagged `[destructive]` remove or overwrite data — always confirm the target and get explicit approval first.**\n\n## First-time setup\n\nThese are **one-time** steps — do not repeat them on every call. Run a step only when a command fails for the matching reason.\n\n- **`oo: command not found`** — install the oo CLI (other platforms: <https://cli.oomol.com/install-guide.md>):\n\n  ```bash\n  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux\n  ```\n\n  ```powershell\n  irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell\n  ```\n\n- **Not signed in / authentication error** — sign in to your OOMOL account once:\n\n  ```bash\n  oo auth login\n  ```\n\n- **`scope_missing` / `credential_expired` / `app_not_ready` / `app_not_found`** — OpenAI is not connected, or the connection expired or lacks a scope. Connect once (auth type: API key) at:\n\n  ```text\n  https://console.oomol.com/app-connections?provider=openai\n  ```\n\n- **HTTP 402 / `OOMOL_INSUFFICIENT_CREDIT`** — billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.\n\n## Resources\n\n- OpenAI homepage: https://openai.com/api/\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn76z80283f7fz2wxq5mf3mf4n87zydc\",\n  \"slug\": \"oo-openai\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1789451174478\n}\n\nFile v1.0.3:skill-card.md\n\n## Description:\n\nProvides agent guidance for using OpenAI through an OOMOL-connected account and the oo CLI, including schema inspection and actions for responses, embeddings, media, moderation, batches, models, and token counting.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[oomol](https://clawhub.ai/user/oomol)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent operators use this skill to perform OpenAI tasks through an OOMOL-connected account while inspecting live action schemas before constructing requests. It supports read workflows and state-changing OpenAI actions such as responses, embeddings, generated media, batch jobs, and audio processing.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: OpenAI work is routed through a third-party OOMOL-connected account.\n\nMitigation: Install only when this routing is intended, and avoid sending sensitive or proprietary content unless the account, connection, and data handling are approved.\n\nRisk: The artifact recommends remote installer commands that pipe downloaded scripts into a shell.\n\nMitigation: Prefer an official package, pinned release, or verified installer, and inspect installer contents before execution.\n\nRisk: Write actions can create or change OpenAI resources such as responses, embeddings, media, batch jobs, and audio outputs.\n\nMitigation: Inspect the live action schema and confirm the exact payload and expected effect with the user before running any write action.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/oomol/skills/oo-openai)\n- [OOMOL publisher profile](https://clawhub.ai/user/oomol)\n- [oo CLI](https://github.com/oomol-lab/oo-cli)\n- [OpenAI API](https://openai.com/api/)\n- [oo CLI install guide](https://cli.oomol.com/install-guide.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with oo CLI shell commands and JSON payload examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires a signed-in OOMOL account with an OpenAI connection; write actions require payload review and user confirmation.]\n\n## Skill Version(s):\n\n1.0.3 (source: server release metadata and skill metadata)\n\n## Ethical Considerations:\n\nUsers 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.\n\nArchive v1.0.1: 3 files, 3531 bytes\n\nFiles: skill-card.md (2202b), SKILL.md (4493b), _meta.json (128b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: oo-openai\ndescription: \"OpenAI (openai.com). Use this skill for ANY OpenAI request — reading, creating, and updating data. Whenever a task involves OpenAI, use this skill instead of calling the API directly.\"\nallowed-tools: [Bash(oo *)]\nmetadata:\n  title: \"OpenAI\"\n  author: \"OOMOL\"\n  version: \"1.0.1\"\n  services: [\"openai\"]\n  icon: \"https://static.oomol.com/logo/third-party/OpenAI.svg\"\n---\n\n# OpenAI\n\nOperate **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.\n\n## Running an action\n\nAssume 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.\n\n**1. Inspect the contract** to get the authoritative input/output schema before building a payload:\n\n```bash\noo connector schema \"openai\" --action \"<action_name>\"\n```\n\n**2. Run the action** with a JSON payload that matches the input schema:\n\n```bash\noo connector run \"openai\" --action \"<action_name>\" --data '<json>' --json\n```\n\n- `--data` takes a JSON object string or `@path/to/file.json`; omit it to send `{}`.\n- The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`; the execution id lives under `meta.executionId`.\n\nEach 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.\n\n## Available actions\n\n- `cancel_batch` — Cancel one OpenAI batch job by its identifier. [write]\n- `create_audio_transcription` — Transcribe one uploaded audio file with the OpenAI audio transcription API. [write]\n- `create_audio_translation` — Translate one uploaded audio file into English with the OpenAI audio translation API. [write]\n- `create_batch` — Create an OpenAI batch job from an uploaded input file. [write]\n- `create_embeddings` — Create embeddings with an OpenAI embedding model. [write]\n- `create_image` — Generate images with the OpenAI image generation API. [write]\n- `create_moderation` — Classify text or image inputs with the OpenAI Moderations API. [write]\n- `create_response` — Create a non-streaming OpenAI response through the Responses API. [write]\n- `create_speech` — Synthesize speech audio from text with the OpenAI audio speech API. [write]\n- `get_batch` — Fetch one OpenAI batch job by its identifier.\n- `get_input_token_counts` — Count how many input tokens a Responses-style OpenAI request would consume.\n- `get_model` — Retrieve the metadata for a single OpenAI model by ID.\n- `get_response` — Retrieve one stored OpenAI response by its identifier.\n- `list_input_items` — List the stored input items for one OpenAI response.\n- `list_models` — List the OpenAI models available to the current API key.\n\n## Safety\n\n- Untagged actions are reads (get / list / search) — safe to run directly.\n- **Actions tagged `[write]` change OpenAI state — confirm the exact payload and effect with the user before running.**\n- **Actions tagged `[destructive]` remove or overwrite data — always confirm the target and get explicit approval first.**\n\n## First-time setup\n\nThese are **one-time** steps — do not repeat them on every call. Run a step only when a command fails for the matching reason.\n\n- **`oo: command not found`** — install the oo CLI (other platforms: <https://cli.oomol.com/install-guide.md>):\n\n  ```bash\n  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux\n  ```\n\n  ```powershell\n  irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell\n  ```\n\n- **Not signed in / authentication error** — sign in to your OOMOL account once:\n\n  ```bash\n  oo auth login\n  ```\n\n- **`scope_missing` / `credential_expired` / `app_not_ready` / `app_not_found`** — OpenAI is not connected, or the connection expired or lacks a scope. Connect once (auth type: API key) at:\n\n  ```text\n  https://console.oomol.com/app-connections?provider=openai\n  ```\n\n- **HTTP 402 / `OOMOL_INSUFFICIENT_CREDIT`** — billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.\n\n## Resources\n\n- OpenAI homepage: https://openai.com/api/\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn76z80283f7fz2wxq5mf3mf4n87zydc\",\n  \"slug\": \"oo-openai\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1781000501358\n}\n\nFile v1.0.1:skill-card.md\n\n## Description: <br>\nOpenAI (openai.com). Use this skill for ANY OpenAI request — reading, creating, and updating data. Whenever a task involves OpenAI, use this skill instead of calling the API directly. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[oomol](https://clawhub.ai/user/oomol) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agents use this skill to operate an OOMOL-connected OpenAI account through the oo CLI for model lookup, Responses API calls, batches, embeddings, image generation, moderation, transcription, translation, and speech synthesis. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill can access a user's OOMOL-connected OpenAI account and run write actions that create or modify OpenAI resources. <br>\nMitigation: Review exact payloads before approving write actions, avoid sending sensitive data unless intended, and reserve first-time setup steps for actual authentication or connection failures. <br>\nRisk: The first-time setup path installs the oo CLI through a remote installer when the CLI is missing. <br>\nMitigation: Inspect the oo CLI installer before using that setup path. <br>\n\n\n## Reference(s): <br>\n- [ClawHub OpenAI skill page](https://clawhub.ai/oomol/oo-openai) <br>\n- [OOMOL oo CLI](https://github.com/oomol-lab/oo-cli) <br>\n- [OpenAI API](https://openai.com/api/) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Shell commands, JSON, Text, Configuration guidance] <br>\n**Output Format:** [Markdown guidance with oo CLI commands and JSON connector responses] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Uses live connector schemas before execution and returns connector data with execution metadata when actions run.] <br>\n\n## Skill Version(s): <br>\n1.0.1 (source: frontmatter and server evidence) <br>\n\n## Ethical Considerations: <br>\nUsers 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. <br>\n\nArchive v1.0.0: 18 files, 11655 bytes\n\nFiles: actions/cancel_batch.md (603b), actions/create_audio_transcription.md (826b), actions/create_audio_translation.md (826b), actions/create_batch.md (736b), actions/create_embeddings.md (755b), actions/create_image.md (734b), actions/create_moderation.md (768b), actions/create_response.md (761b), actions/create_speech.md (753b), actions/get_batch.md (587b), actions/get_input_token_counts.md (682b), actions/get_model.md (596b), actions/get_response.md (611b), actions/list_input_items.md (629b), actions/list_models.md (608b), skill-card.md (2223b), SKILL.md (4917b), _meta.json (128b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: oo-openai\ndescription: \"OpenAI (openai.com). Use this skill for ANY OpenAI request — reading, creating, and updating data. Whenever a task involves OpenAI, use this skill instead of calling the API directly.\"\nallowed-tools: [Bash(oo *)]\nmetadata:\n  title: \"OpenAI\"\n  author: \"OOMOL\"\n  version: \"1.0.0\"\n  service: \"openai\"\n  categories: \"AI, Developer Tools\"\n  homepage: \"https://openai.com/api/\"\n  icon: \"https://static.oomol.com/logo/third-party/OpenAI.svg\"\n---\n\n# OpenAI\n\nOperate **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.\n\nCategory: AI, Developer Tools. Exposes 15 action(s).\n\n## Running an action\n\nAssume 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.\n\n**1. Inspect the contract** to get the authoritative input/output schema before building a payload:\n\n```bash\noo connector schema \"openai\" --action \"<action_name>\"\n```\n\n**2. Run the action** with a JSON payload that matches the input schema:\n\n```bash\noo connector run \"openai\" --action \"<action_name>\" --data '<json>' --json\n```\n\n- `--data` takes a JSON object string or `@path/to/file.json`; omit it to send `{}`.\n- The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`; the execution id lives under `meta.executionId`.\n\nEach action below links to a reference file with its purpose and exact commands. Read the linked file, then fetch the live schema with `oo connector schema` before constructing `--data`.\n\n## Available actions\n\n- [`cancel_batch`](actions/cancel_batch.md) — Cancel one OpenAI batch job by its identifier.\n- [`create_audio_transcription`](actions/create_audio_transcription.md) — Transcribe one uploaded audio file with the OpenAI audio transcription API.\n- [`create_audio_translation`](actions/create_audio_translation.md) — Translate one uploaded audio file into English with the OpenAI audio translation API.\n- [`create_batch`](actions/create_batch.md) — Create an OpenAI batch job from an uploaded input file.\n- [`create_embeddings`](actions/create_embeddings.md) — Create embeddings with an OpenAI embedding model.\n- [`create_image`](actions/create_image.md) — Generate images with the OpenAI image generation API.\n- [`create_moderation`](actions/create_moderation.md) — Classify text or image inputs with the OpenAI Moderations API.\n- [`create_response`](actions/create_response.md) — Create a non-streaming OpenAI response through the Responses API.\n- [`create_speech`](actions/create_speech.md) — Synthesize speech audio from text with the OpenAI audio speech API.\n- [`get_batch`](actions/get_batch.md) — Fetch one OpenAI batch job by its identifier.\n- [`get_input_token_counts`](actions/get_input_token_counts.md) — Count how many input tokens a Responses-style OpenAI request would consume.\n- [`get_model`](actions/get_model.md) — Retrieve the metadata for a single OpenAI model by ID.\n- [`get_response`](actions/get_response.md) — Retrieve one stored OpenAI response by its identifier.\n- [`list_input_items`](actions/list_input_items.md) — List the stored input items for one OpenAI response.\n- [`list_models`](actions/list_models.md) — List the OpenAI models available to the current API key.\n\n## Safety\n\n- Read actions (get / list / search) are safe to run directly.\n- **Create, update, send, or post actions change OpenAI state — confirm the exact payload and effect with the user before running.**\n- **Delete or remove actions are destructive — always confirm the target and get explicit approval first.**\n\n## First-time setup\n\nThese are **one-time** steps — do not repeat them on every call. Run a step only when a command fails for the matching reason.\n\n- **`oo: command not found`** — install the oo CLI (other platforms: <https://cli.oomol.com/install-guide.md>):\n\n  ```bash\n  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux\n  ```\n\n  ```powershell\n  irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell\n  ```\n\n- **Not signed in / authentication error** — sign in to your OOMOL account once:\n\n  ```bash\n  oo auth login\n  ```\n\n- **`scope_missing` / `credential_expired` / `app_not_ready` / `app_not_found`** — OpenAI is not connected, or the connection expired or lacks a scope. Connect once (auth type: API key) at:\n\n  ```text\n  https://console.oomol.com/app-connections?provider=openai\n  ```\n\n- **HTTP 402 / `OOMOL_INSUFFICIENT_CREDIT`** — billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.\n\n## Resources\n\n- OpenAI homepage: https://openai.com/api/\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn76z80283f7fz2wxq5mf3mf4n87zydc\",\n  \"slug\": \"oo-openai\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1780497131879\n}\n\nFile v1.0.0:actions/cancel_batch.md\n\n# OpenAI · `cancel_batch`\n\nCancel one OpenAI batch job by its identifier.\n\n- **Service**: `openai`\n- **Action**: `cancel_batch`\n- **Action id**: `openai.cancel_batch`\n\n## Inspect the schema\n\nAlways fetch the authoritative input/output schema before building a payload — fields and defaults can change upstream:\n\n```bash\noo connector schema \"openai\" --action \"cancel_batch\"\n```\n\n## Run\n\n```bash\noo connector run \"openai\" --action \"cancel_batch\" --data '{}' --json\n```\n\nReplace `{}` with a JSON object that matches the input schema. The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`.\n\nFile v1.0.0:actions/create_audio_transcription.md\n\n# OpenAI · `create_audio_transcription`\n\nTranscribe one uploaded audio file with the OpenAI audio transcription API.\n\n- **Service**: `openai`\n- **Action**: `create_audio_transcription`\n- **Action id**: `openai.create_audio_transcription`\n\n## Inspect the schema\n\nAlways fetch the authoritative input/output schema before building a payload — fields and defaults can change upstream:\n\n```bash\noo connector schema \"openai\" --action \"create_audio_transcription\"\n```\n\n## Run\n\n```bash\noo connector run \"openai\" --action \"create_audio_transcription\" --data '{}' --json\n```\n\nReplace `{}` with a JSON object that matches the input schema. The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`.\n\n> **Write action.** This changes OpenAI state. Confirm the exact payload and intended effect with the user before running.\n\nFile v1.0.0:actions/create_audio_translation.md\n\n# OpenAI · `create_audio_translation`\n\nTranslate one uploaded audio file into English with the OpenAI audio translation API.\n\n- **Service**: `openai`\n- **Action**: `create_audio_translation`\n- **Action id**: `openai.create_audio_translation`\n\n## Inspect the schema\n\nAlways fetch the authoritative input/output schema before building a payload — fields and defaults can change upstream:\n\n```bash\noo connector schema \"openai\" --action \"create_audio_translation\"\n```\n\n## Run\n\n```bash\noo connector run \"openai\" --action \"create_audio_translation\" --data '{}' --json\n```\n\nReplace `{}` with a JSON object that matches the input schema. The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`.\n\n> **Write action.** This changes OpenAI state. Confirm the exact payload and intended effect with the user before running.\n\nFile v1.0.0:actions/create_batch.md\n\n# OpenAI · `create_batch`\n\nCreate an OpenAI batch job from an uploaded input file.\n\n- **Service**: `openai`\n- **Action**: `create_batch`\n- **Action id**: `openai.create_batch`\n\n## Inspect the schema\n\nAlways fetch the authoritative input/output schema before building a payload — fields and defaults can change upstream:\n\n```bash\noo connector schema \"openai\" --action \"create_batch\"\n```\n\n## Run\n\n```bash\noo connector run \"openai\" --action \"create_batch\" --data '{}' --json\n```\n\nReplace `{}` with a JSON object that matches the input schema. The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`.\n\n> **Write action.** This changes OpenAI state. Confirm the exact payload and intended effect with the user before running.\n\nFile v1.0.0:actions/create_embeddings.md\n\n# OpenAI · `create_embeddings`\n\nCreate embeddings with an OpenAI embedding model.\n\n- **Service**: `openai`\n- **Action**: `create_embeddings`\n- **Action id**: `openai.create_embeddings`\n\n## Inspect the schema\n\nAlways fetch the authoritative input/output schema before building a payload — fields and defaults can change upstream:\n\n```bash\noo connector schema \"openai\" --action \"create_embeddings\"\n```\n\n## Run\n\n```bash\noo connector run \"openai\" --action \"create_embeddings\" --data '{}' --json\n```\n\nReplace `{}` with a JSON object that matches the input schema. The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`.\n\n> **Write action.** This changes OpenAI state. Confirm the exact payload and intended effect with the user before running.\n\nFile v1.0.0:actions/create_image.md\n\n# OpenAI · `create_image`\n\nGenerate images with the OpenAI image generation API.\n\n- **Service**: `openai`\n- **Action**: `create_image`\n- **Action id**: `openai.create_image`\n\n## Inspect the schema\n\nAlways fetch the authoritative input/output schema before building a payload — fields and defaults can change upstream:\n\n```bash\noo connector schema \"openai\" --action \"create_image\"\n```\n\n## Run\n\n```bash\noo connector run \"openai\" --action \"create_image\" --data '{}' --json\n```\n\nReplace `{}` with a JSON object that matches the input schema. The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`.\n\n> **Write action.** This changes OpenAI state. Confirm the exact payload and intended effect with the user before running.\n\nFile v1.0.0:actions/create_moderation.md\n\n# OpenAI · `create_moderation`\n\nClassify text or image inputs with the OpenAI Moderations API.\n\n- **Service**: `openai`\n- **Action**: `create_moderation`\n- **Action id**: `openai.create_moderation`\n\n## Inspect the schema\n\nAlways fetch the authoritative input/output schema before building a payload — fields and defaults can change upstream:\n\n```bash\noo connector schema \"openai\" --action \"create_moderation\"\n```\n\n## Run\n\n```bash\noo connector run \"openai\" --action \"create_moderation\" --data '{}' --json\n```\n\nReplace `{}` with a JSON object that matches the input schema. The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`.\n\n> **Write action.** This changes OpenAI state. Confirm the exact payload and intended effect with the user before running.\n\nFile v1.0.0:actions/create_response.md\n\n# OpenAI · `create_response`\n\nCreate a non-streaming OpenAI response through the Responses API.\n\n- **Service**: `openai`\n- **Action**: `create_response`\n- **Action id**: `openai.create_response`\n\n## Inspect the schema\n\nAlways fetch the authoritative input/output schema before building a payload — fields and defaults can change upstream:\n\n```bash\noo connector schema \"openai\" --action \"create_response\"\n```\n\n## Run\n\n```bash\noo connector run \"openai\" --action \"create_response\" --data '{}' --json\n```\n\nReplace `{}` with a JSON object that matches the input schema. The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`.\n\n> **Write action.** This changes OpenAI state. Confirm the exact payload and intended effect with the user before running.\n\nFile v1.0.0:actions/create_speech.md\n\n# OpenAI · `create_speech`\n\nSynthesize speech audio from text with the OpenAI audio speech API.\n\n- **Service**: `openai`\n- **Action**: `create_speech`\n- **Action id**: `openai.create_speech`\n\n## Inspect the schema\n\nAlways fetch the authoritative input/output schema before building a payload — fields and defaults can change upstream:\n\n```bash\noo connector schema \"openai\" --action \"create_speech\"\n```\n\n## Run\n\n```bash\noo connector run \"openai\" --action \"create_speech\" --data '{}' --json\n```\n\nReplace `{}` with a JSON object that matches the input schema. The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`.\n\n> **Write action.** This changes OpenAI state. Confirm the exact payload and intended effect with the user before running.\n\nFile v1.0.0:actions/get_batch.md\n\n# OpenAI · `get_batch`\n\nFetch one OpenAI batch job by its identifier.\n\n- **Service**: `openai`\n- **Action**: `get_batch`\n- **Action id**: `openai.get_batch`\n\n## Inspect the schema\n\nAlways fetch the authoritative input/output schema before building a payload — fields and defaults can change upstream:\n\n```bash\noo connector schema \"openai\" --action \"get_batch\"\n```\n\n## Run\n\n```bash\noo connector run \"openai\" --action \"get_batch\" --data '{}' --json\n```\n\nReplace `{}` with a JSON object that matches the input schema. The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`.","readmeExcerpt":"Skill: OpenAI Owner: oomol Summary: 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. Tags: latest:1.0.4 Version history: v1.0.4 | 2026-09-20T03:34:19.811Z | user - Connects OOMOL workflows to OpenAI through the oo CLI using server-side credentials. - Supports Responses API c","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"oo connector schema \"openai\" --action \"<action_name>\""},{"language":"bash","snippet":"oo connector run \"openai\" --action \"<action_name>\" --data '<json>' --json"},{"language":"bash","snippet":"curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux"},{"language":"bash","snippet":"curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux"},{"language":"powershell","snippet":"irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell"},{"language":"bash","snippet":"oo auth login"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: oo-openai\ndescription: \"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.\"\nallowed-tools: [Bash(oo *)]\nmetadata:\n  title: \"OpenAI\"\n  author: \"OOMOL\"\n  version: \"1.0.4\"\n  services: [\"openai\"]\n  icon: \"https://static.oomol.com/logo/third-party/OpenAI.svg\"\n---\n\n# OpenAI\n\nOperate **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.\n\n## Running an action\n\nAssume 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.\n\n**1. Inspect the contract** to get the authoritative input/output schema before building a payload:\n\n```bash\noo connector schema \"openai\" --action \"<action_name>\"\n```\n\n**2. Run the action** with a JSON payload that matches the input schema:\n\n```bash\noo connector run \"openai\" --action \"<action_name>\" --data '<json>' --json\n```\n\n- `--data` takes a JSON object string or `@path/to/file.json`; omit it to send `{}`.\n- The response is `{ \"data\": ..., \"meta\": { \"executionId\": \"...\" } }`; the execution id lives under `meta.executionId`.\n\nEach 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.\n\n## Available actions\n\n- `cancel_batch` — Cancel one OpenAI batch job by its identifier. [destructive]\n- `create_audio_transcription` — Transcribe one uploaded audio file with the OpenAI audio transcription API. [write]\n- `create_audio_translation` — Translate one uploaded audio file into English with the OpenAI audio translation API. [write]\n- `create_batch` — Create an OpenAI batch job from an uploaded input file. [write]\n- `create_embeddings` — Create embeddings with an OpenAI embedding model. [write]\n- `create_image` — Generate images with the OpenAI image generation API. [write]\n- `create_moderation` — Classify text or image inputs with the OpenAI Moderations API. [write]\n- `create_response` — Create a non-streaming OpenAI response through the Responses API. [write]\n- `create_speech` — Synthesize speech audio from text with the OpenAI audio speech API. [write]\n- `get_batch` — Fetch one OpenAI batch job by its identifier.\n- `get_input_token_counts` — Count how many input tokens a Responses-style OpenAI request would consume.\n- `get_model` — Retrieve the metadata for a single OpenAI model by ID.\n- `get_response` — Retrieve one stored OpenAI response by its identifier.\n- `list_input_items` — List the stored input items for o"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn76z80283f7fz2wxq5mf3mf4n87zydc\",\n  \"slug\": \"oo-openai\",\n  \"version\": \"1.0.4\",\n  \"publishedAt\": 1789875259811\n}"},{"path":"skill-card.md","content":"## Description:\n\nOpenAI connector skill for reading, creating, updating, and deleting OpenAI data through an OOMOL-connected account using the oo CLI.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[oomol](https://clawhub.ai/user/oomol)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers 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.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can run broad read, write, and destructive actions against a credentialed OpenAI account.\n\nMitigation: Confirm the exact action, payload, cost impact, and target resource before any write or destructive command is run.\n\nRisk: The first-time setup section includes remote shell install commands for the oo CLI.\n\nMitigation: Install the oo CLI only through a verified package or reviewed installer before relying on this skill.\n\nRisk: OpenAI usage can affect paid or sensitive workloads.\n\nMitigation: Review the skill before installation and limit use to accounts and data appropriate for the intended workload.\n\n## Reference(s):\n\n- [OpenAI API](https://openai.com/api/)\n- [oo CLI](https://github.com/oomol-lab/oo-cli)\n- [oo CLI install guide](https://cli.oomol.com/install-guide.md)\n- [ClawHub skill page](https://clawhub.ai/oomol/skills/oo-openai)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, Configuration, Guidance]\n\n**Output Format:** [Markdown with shell commands and JSON payload guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Connector responses are JSON when the skill runs commands with --json.]\n\n## Skill Version(s):\n\n1.0.4 (source: server release metadata and skill frontmatter)\n\n## Ethical Considerations:\n\nUsers 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."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1361,"uniquenessScore":42,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-12T02:37:45.182Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-12T02:37:45.182Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-13T21:56:43.938Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"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!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"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","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}