ai-services

An agent skill by digitalocean-labs, from digitalocean-labs/do-app-platform-skills. Tags: ai, api, digitalocean, sdk, serverless.

What it does

Configure DigitalOcean Gradient AI serverless inference and Agent Development Kit. Use when adding LLM inference, model access keys, serverless AI endpoints, or building AI agents with ADK on App Platform.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add digitalocean-labs/do-app-platform-skills --skill ai-services

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/digitalocean-labs/do-app-platform-skills
cp -r do-app-platform-skills/skills/ai-services ~/.claude/skills/ai-services

Safety box score

Grade C, moderate risk: 32 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is documentation-only, but it configures remote AI inference and agent services, including secret-bearing environment variables and deployment commands. The main risks are that prompts/data leave the machine to DigitalOcean endpoints, and that it can create or deploy remote AI agents that may cost money or change live resources.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	The files only document commands, but they do instruct running shell commands like `pip install gradient-adk`, `gradient agent run`, and `doctl genai list-models`.
Network access	2 (moderate)	It sends prompts and API calls to remote services such as `https://inference.do-ai.run/v1/chat/completions` and `https://agents.do-ai.run/v1/{workspace-id}/{deployment-name}/run`.
Filesystem reach	1 (low)	It edits project config such as `.do/app.yaml`, but does not read or write outside the workspace or home directory.
Secrets & credentials	2 (moderate)	It explicitly uses `MODEL_ACCESS_KEY`, `GRADIENT_MODEL_ACCESS_KEY`, and `DIGITALOCEAN_API_TOKEN`, and routes them through environment variables and GitHub Secrets.
Privilege & persistence	0 (none)	No sudo, services, global installs, shell startup edits, or OS-level settings are requested.
Instruction hijack surface	0 (none)	There is no instruction to ignore safeguards, follow hidden/remote instructions, or conceal behavior.
Irreversible actions	2 (moderate)	The skill can create and deploy remote agents with `doctl genai agent create` and `gradient agent deploy`, which are real external actions and can incur cost.
Transparency	0 (none)	All shipped files are plain Markdown; there are no binaries, installers, or decoded-at-runtime payloads.

Before installing

Confirm you are okay with prompts and outputs being sent to `inference.do-ai.run` / `agents.do-ai.run`.
Verify the exact scopes for `DIGITALOCEAN_API_TOKEN` and use a least-privilege token.
Test `gradient-adk` and `gradient agent deploy` in a scratch project first.
Check `.do/app.yaml` so only intended runtime secrets are added.

Rated 2026-10-19 by an automated review of 4 files from the skill's repository.

Source

Repository: digitalocean-labs/do-app-platform-skills (all skills from this repository)
Path: skills/ai-services/SKILL.md
Branch: main
Collection: do-app-platform
Updated: 2026-09-21

amazon-bedrock — Builds generative AI applications on Amazon Bedrock.
aws-sdk-js-v3-usage — AWS SDK for JavaScript v3 development patterns.
aws-sdk-python-usage — AWS SDK for Python (boto3/botocore) development patterns. You MUST use this skill when writing Python code that uses AWS services via boto3 or botocore.
aws-sdk-swift-usage — AWS SDK for Swift development patterns. Use when writing Swift code that uses AWS services via aws-sdk-swift package.
cursor-sdk — Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor TypeScript SDK (`@cursor/sdk`).
agents-sdk — Build, debug, or review Cloudflare Agents SDK applications using the agents package.