Skip to content

datarobot-oss/datarobot-agent-skills / skills/datarobot-agent-assist/agent-assist-build

datarobot-agent-assist-build

Flagged

Use when the user wants to design, build, code, or deploy an AI agent on DataRobot; mentions agent_spec.yaml, dress rehearsal, the DataRobot agent template, LangGraph, CrewAI, LlamaIndex, NAT, Base agents, MCP servers, backend APIs, custom frontends, or the DataRobot CLI.

references/pre-deployment-checklist.md

View on GitHub
## Pre-deployment Checklist

Run this checklist when the user enters **[3. Deploying an AI Agent](../SKILL.md#3-deploying-an-ai-agent)** — including after coding when the user chooses to deploy.

**Prerequisite:** The agent must be implemented before deployment in the same session. If the user requests deploy without having coded, explain that implementation is required and offer **[2. Coding an AI Agent](../SKILL.md#2-coding-an-ai-agent)** — do not deploy until coding completes. This is the canonical rule; other documents link here.

**Different project:** If the user wants to deploy a different project than the one in this session, tell them to start a new session. Do not switch `<target_dir>` unless the user explicitly asks to change the project directory.

---

### Steps

1. **Resolve `<target_dir>`:**

   - If already set this session (from design or coding) → reuse it. Briefly confirm: *"Deploying from `<target_dir>`."*
   - If unset (typically a deploy-only session) → ask:

     > Which project directory contains your implemented agent (the directory with `AGENTS.md`)?

     Set `<target_dir>` to the user's answer. Do not scan subdirectories automatically.

2. **Read `REPO_URL`** from `REPO_URL` in `<skill_scripts_dir>/clone_template.py`.

3. **Verify implementation** in `<target_dir>`:

   | Check | On failure |
   |-------|------------|
   | `AGENTS.md` exists | Agent is not implemented. Offer **[2. Coding an AI Agent](../SKILL.md#2-coding-an-ai-agent)** on this `<target_dir>` and run the [Pre-coding Checklist](pre-coding-checklist.md) (deploy → coding handoff — skip Bootstrap step 1; run step 2 spec validation, then Template setup). |
   | Git repository with `origin` matching `REPO_URL` | Template is not initialized. Offer coding on this `<target_dir>` (deploy → coding handoff — same as above). |
   | User declines coding | Show the [welcome menu](../SKILL.md#on-activation). Stop. |

   Do **not** check for `agent_spec.yaml` — it is not required for deployment.

4. **Validate dependencies** — read and follow [dependency-validation.md](dependency-validation.md) end to end.

5. **Deploy** — read `<target_dir>/AGENTS.md` and follow deployment instructions **strictly**. Do not deviate without user confirmation.
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 323kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall