SageMaker Serving Image Selection
huggingface/skills
Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.
Diagnose and fix OCI AI Quick Actions (AQUA) issues including deployment failures, OOM errors, authorization problems, capacity issues, container errors, and policy misconfigurations.
Install Aqua Troubleshooting
$ npx skills add oracle/accelerated-data-science --skill aqua-troubleshooting -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install oracle/accelerated-data-science aqua-troubleshooting --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/oracle/accelerated-data-science.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/aqua-troubleshooting .claude/skills/aqua-troubleshooting && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "aqua-troubleshooting" agent skill from https://github.com/oracle/accelerated-data-science/tree/main/skills/aqua-troubleshooting into .claude/skills/aqua-troubleshooting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aqua-troubleshooting", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/oracle/accelerated-data-science/tree/main/skills/aqua-troubleshootingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add oracle/accelerated-data-science --skill aqua-troubleshooting -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install oracle/accelerated-data-science aqua-troubleshooting --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oracle/accelerated-data-science.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/aqua-troubleshooting .agents/skills/aqua-troubleshooting && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "aqua-troubleshooting" agent skill from https://github.com/oracle/accelerated-data-science/tree/main/skills/aqua-troubleshooting into .agents/skills/aqua-troubleshooting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aqua-troubleshooting", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add oracle/accelerated-data-science --skill aqua-troubleshooting -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install oracle/accelerated-data-science aqua-troubleshooting --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oracle/accelerated-data-science.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/aqua-troubleshooting .cursor/skills/aqua-troubleshooting && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "aqua-troubleshooting" agent skill from https://github.com/oracle/accelerated-data-science/tree/main/skills/aqua-troubleshooting into .cursor/skills/aqua-troubleshooting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aqua-troubleshooting", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/oracle/accelerated-data-science.git --path skills/aqua-troubleshooting--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add oracle/accelerated-data-science --skill aqua-troubleshooting -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install oracle/accelerated-data-science aqua-troubleshooting --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oracle/accelerated-data-science.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/aqua-troubleshooting .gemini/skills/aqua-troubleshooting && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "aqua-troubleshooting" agent skill from https://github.com/oracle/accelerated-data-science/tree/main/skills/aqua-troubleshooting into .gemini/skills/aqua-troubleshooting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aqua-troubleshooting", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install oracle/accelerated-data-science aqua-troubleshootingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add oracle/accelerated-data-science --skill aqua-troubleshooting -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/oracle/accelerated-data-science.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/aqua-troubleshooting .github/skills/aqua-troubleshooting && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "aqua-troubleshooting" agent skill from https://github.com/oracle/accelerated-data-science/tree/main/skills/aqua-troubleshooting into .github/skills/aqua-troubleshooting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aqua-troubleshooting", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add oracle/accelerated-data-science --skill aqua-troubleshooting -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install oracle/accelerated-data-science aqua-troubleshooting --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oracle/accelerated-data-science.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/aqua-troubleshooting .opencode/skills/aqua-troubleshooting && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "aqua-troubleshooting" agent skill from https://github.com/oracle/accelerated-data-science/tree/main/skills/aqua-troubleshooting into .opencode/skills/aqua-troubleshooting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aqua-troubleshooting", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
aqua-troubleshooting- GitHub stars
- 125
- Token cost
- ~1.8k tokens
- SKILL.md length
- 624 words
- Files
- 1
- Skills in repo
- 8
- Repo updated
- First seen
- Licence
- UPL-1.0
At a glance
Diagnose and fix OCI AI Quick Actions (AQUA) issues including deployment failures, OOM errors, authorization problems, capacity issues, container errors, and policy misconfigurations.
- Encounters errors
- SKILL.md covers Step 1: Check Logs, Common Deployment Errors, Authorization Errors and Environment Setup Issues, plus 4 more sections
- Calls jq and huggingface-cli; reaches datascience.us-ashburn-1.oci.oraclecloud.com; needs HF_TOKEN
- Needs help debugging AQUA workflows
What it does
Aqua Troubleshooting is an agent skill from oracle/accelerated-data-science, published by the product's own GitHub organization. Diagnose and fix OCI AI Quick Actions (AQUA) issues including deployment failures, OOM errors, authorization problems, capacity issues, container errors, and policy misconfigurations. Triggered when user encounters errors or needs help debugging AQUA workflows.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Deployment, Authorization and RBAC and LLM inference and serving. It works with vLLM. The repository describes itself as: ADS is the Oracle Data Science Cloud Service's python SDK supporting, model ops (train/eval/deploy), along with running workloads on Jobs and Pipeline resources.
When your agent uses it
- Encounters errors
- Needs help debugging AQUA workflows
Example prompts
- “/aqua-troubleshooting”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 0418ab4. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
jqhuggingface-cli
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
datascience.us-ashburn-1.oci.oraclecloud.com
Also links to:
docs.vllm.aidocs.oracle.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
HF_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Aqua Troubleshooting loads about 1.8k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 624 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (UPL-1.0) doesn't allow us to republish the file, so here is its outline and opening line. It has 624 words (~1,808 tokens).
“Use this skill when the user encounters errors or needs help diagnosing issues with OCI AI Quick Actions deployments, fine-tuning, evaluation, or model registration.”
- name
- aqua-troubleshooting
- user-invocable
- true
- disable-model-invocation
- false
Files
Just SKILL.md in skills/aqua-troubleshooting of oracle/accelerated-data-science.
Open the folder on GitHubat commit 0418ab4
Compare with similar skills
Aqua Troubleshooting next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Aqua Troubleshooting this skilloracle/accelerated-data-science | 125 | — | ~1.8k | Automated safety check: Pass | UPL-1.0 | |
| SageMaker Serving Image Selectionhuggingface/skills | 11k | 1 repos | ~4.6k | Automated safety check: Pass | Apache-2.0 | |
| Phase 1 Kernel ValidationXilinx/mlir-air | 150 | — | ~3.4k | Automated safety check: Pass | MIT | |
| LLM App Builderrevfactory/harness-100 | 1.3k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| vLLM Model ServingOrchestra-Research/AI-Research-SKILLs | 13k | 5 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Rtvi Byom PortingNVIDIA-AI-Blueprints/video-search-and-summarization | 1.9k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Phase 1 Kernel Validation
Xilinx/mlir-air
Phase 1 of LLM deployment — for every leaf kernel × shape the model needs, verify numerical correctness on real NPU2 against the registry's GPU/vLLM-aligned standard.
LLM App Builder
revfactory/harness-100
Full pipeline where an agent team collaborates to develop an LLM app.
vLLM Model Serving
Orchestra-Research/AI-Research-SKILLs
Deploys LLMs with vLLM for high-throughput serving, covering the OpenAI-compatible server, offline batch inference, monitoring and a Docker rollout.
Rtvi Byom Porting
NVIDIA-AI-Blueprints/video-search-and-summarization
A skill your agent uses when adding, debugging, or validating a bring-your-own VLM in VSS RT-VLM, including custom Hugging Face or NGC checkpoints, vLLM adapters or plugins, model shims, and…
Vllm Deploy K8s
vllm-project/vllm-skills
Deploy vLLM to Kubernetes (K8s) with GPU support, health probes, and OpenAI-compatible API endpoint.
More from oracle/accelerated-data-science
All 8 skills in this repo- Official
Aqua CLI
oracle/accelerated-data-science
Complete CLI reference for the ADS AQUA command-line interface (ads aqua).
- Official
Aqua Deployment
oracle/accelerated-data-science
Deploy LLM models on OCI using AI Quick Actions (AQUA) - single model, multi-model, stacked (LoRA), with GPU shape selection, vLLM configuration, streaming, and tool calling.
- Official
Aqua Model Lifecycle
oracle/accelerated-data-science
Register, list, get, and manage LLM models in OCI AI Quick Actions (AQUA) using the ADS SDK.
- Official
Aqua Evaluation
oracle/accelerated-data-science
Evaluate LLM model quality using BERTScore, ROUGE, Perplexity, and Text Readability metrics on OCI AI Quick Actions (AQUA).
- Official
Aqua Finetuning
oracle/accelerated-data-science
Fine-tune LLM models using LoRA on OCI AI Quick Actions (AQUA).
- Official
Aqua Metrics
oracle/accelerated-data-science
Set up Prometheus and Grafana monitoring for AQUA vLLM model deployments on OCI.
Related
Works with
Categories
Questions about Aqua Troubleshooting
What does Aqua Troubleshooting do?
Diagnose and fix OCI AI Quick Actions (AQUA) issues including deployment failures, OOM errors, authorization problems, capacity issues, container errors, and policy misconfigurations. Aqua Troubleshooting is an agent skill from oracle/accelerated-data-science, published by the product's own GitHub organization. Diagnose and fix OCI AI Quick Actions (AQUA) issues including deployment failures, OOM errors, authorization problems, capacity issues, container errors, and policy misconfigurations.
When should I use Aqua Troubleshooting?
Aqua Troubleshooting fits situations like: encounters errors; needs help debugging AQUA workflows.
How do I install Aqua Troubleshooting in Claude Code?
Run `npx skills add oracle/accelerated-data-science --skill aqua-troubleshooting -a claude-code`. Or copy the skill folder (skills/aqua-troubleshooting in oracle/accelerated-data-science) into .claude/skills/aqua-troubleshooting in your project. Claude Code loads it when a task matches its description.
How do I install Aqua Troubleshooting in Codex?
Run `npx skills add oracle/accelerated-data-science --skill aqua-troubleshooting -a codex`. Or copy the skill folder (skills/aqua-troubleshooting in oracle/accelerated-data-science) into .agents/skills/aqua-troubleshooting in your project. Codex loads it when a task matches its description.
Can I use Aqua Troubleshooting in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add oracle/accelerated-data-science --skill aqua-troubleshooting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aqua-troubleshooting, .gemini/skills/aqua-troubleshooting, .github/skills/aqua-troubleshooting and .opencode/skills/aqua-troubleshooting in your project.
What does Aqua Troubleshooting need to run?
Going by SKILL.md and its folder, Aqua Troubleshooting needs the command-line tools its instructions call (jq and huggingface-cli) and credentials named HF_TOKEN. Our summary lists: Python 3.
Does Aqua Troubleshooting access the network?
SKILL.md names 3 domains. In commands or code: datascience.us-ashburn-1.oci.oraclecloud.com; the agent is likely to contact it when it follows the instructions. As links in the text: docs.vllm.ai and docs.oracle.com. This is read from the text; nothing was executed.
Is Aqua Troubleshooting safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Aqua Troubleshooting use?
Aqua Troubleshooting is published under the UPL-1.0 licence (the repository's licence).
How many tokens does Aqua Troubleshooting use?
About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Aqua Troubleshooting?
Skills that share tags, products or a category with Aqua Troubleshooting: SageMaker Serving Image Selection (huggingface/skills, 11k stars), Phase 1 Kernel Validation (Xilinx/mlir-air, 150 stars), LLM App Builder (revfactory/harness-100, 1.3k stars) and vLLM Model Serving (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Aqua Troubleshooting?
oracle (a GitHub organization, an official publisher) maintains it in oracle/accelerated-data-science, which has 125 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 3, 2026.
Source: oracle/accelerated-data-science on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.