Update to DataRobot Skills

{
  "description": "Use when the user wants to design, build, code, simulate, or deploy an AI agent (not a predictive model) to DataRobot; mentions agent_spec.md, dr-assist, datarobot-agent-assist, dress rehearsal, swarm simulation, or the DataRobot agent template; wants to scaffold a LangGraph, CrewAI, LlamaIndex, NAT, or Base agent targeting DataRobot; wants to add an MCP server, backend API, or React frontend to a DataRobot agent application; or uses the DataRobot CLI (dr) to build or deploy an agentic custom application; or wants to harden, stress-test, or battle-test an agent. Covers the full workflow: agent design, agent_spec.md authoring, dress-rehearsal simulation via the DataRobot LLM Gateway, adversarial swarm simulation, template-based coding, and deployment.",
  "included_files": [
    {
      "relative_path": "agent-assist-build/SKILL.md",
      "size_in_bytes": 19100
    },
    {
      "relative_path": "agent-assist-build/references/agent-spec-examples.md",
      "size_in_bytes": 4940
    },
    {
      "relative_path": "agent-assist-build/references/agent-spec-schema.md",
      "size_in_bytes": 1695
    },
    {
      "relative_path": "agent-assist-build/references/dependency-validation.md",
      "size_in_bytes": 1005
    },
    {
      "relative_path": "agent-assist-build/references/dr-cli-setup.md",
      "size_in_bytes": 872
    },
    {
      "relative_path": "agent-assist-build/references/dress-rehearsal.md",
      "size_in_bytes": 7710
    },
    {
      "relative_path": "agent-assist-build/references/helper-scripts.md",
      "size_in_bytes": 5263
    },
    {
      "relative_path": "agent-assist-build/references/llm-selection.md",
      "size_in_bytes": 3629
    },
    {
      "relative_path": "agent-assist-build/references/pre-coding-checklist.md",
      "size_in_bytes": 13723
    },
    {
      "relative_path": "agent-assist-build/references/pre-deployment-checklist.md",
      "size_in_bytes": 2278
    },
    {
      "relative_path": "agent-assist-build/references/resume-design.md",
      "size_in_bytes": 6991
    },
    {
      "relative_path": "agent-assist-build/references/tool-mapping.md",
      "size_in_bytes": 852
    },
    {
      "relative_path": "agent-assist-build/references/workspace-resolution.md",
      "size_in_bytes": 6289
    },
    {
      "relative_path": "agent-assist-build/scripts/check_codespace.py",
      "size_in_bytes": 8325
    },
    {
      "relative_path": "agent-assist-build/scripts/clone_template.py",
      "size_in_bytes": 7534
    },
    {
      "relative_path": "agent-assist-build/scripts/env_utils.py",
      "size_in_bytes": 4040
    },
    {
      "relative_path": "agent-assist-build/scripts/list_llm_models.py",
      "size_in_bytes": 19906
    },
    {
      "relative_path": "agent-assist-build/scripts/rehearsal.py",
      "size_in_bytes": 44939
    },
    {
      "relative_path": "agent-assist-build/scripts/select_framework.py",
      "size_in_bytes": 2482
    },
    {
      "relative_path": "agent-assist-build/scripts/setup_template.py",
      "size_in_bytes": 22250
    },
    {
      "relative_path": "agent-assist-build/scripts/write_rehearsal_report.py",
      "size_in_bytes": 12511
    },
    {
      "relative_path": "agent-assist-simulate/SKILL.md",
      "size_in_bytes": 17766
    },
    {
      "relative_path": "agent-assist-simulate/prompts/evaluate-result.md",
      "size_in_bytes": 3914
    },
    {
      "relative_path": "agent-assist-simulate/prompts/generate-attack.md",
      "size_in_bytes": 4147
    },
    {
      "relative_path": "agent-assist-simulate/prompts/generate-behavior.md",
      "size_in_bytes": 3954
    },
    {
      "relative_path": "agent-assist-simulate/prompts/generate-persistence.md",
      "size_in_bytes": 4298
    },
    {
      "relative_path": "agent-assist-simulate/prompts/generate-tool-return.md",
      "size_in_bytes": 4844
    },
    {
      "relative_path": "agent-assist-simulate/prompts/industry.md",
      "size_in_bytes": 13459
    },
    {
      "relative_path": "agent-assist-simulate/prompts/run-scenario.md",
      "size_in_bytes": 2918
    },
    {
      "relative_path": "agent-assist-simulate/scripts/artifacts.py",
      "size_in_bytes": 7808
    },
    {
      "relative_path": "agent-assist-simulate/scripts/gateway_worker.py",
      "size_in_bytes": 12319
    },
    {
      "relative_path": "agent-assist-simulate/scripts/native_convergence.py",
      "size_in_bytes": 12924
    },
    {
      "relative_path": "agent-assist-simulate/scripts/native_execution.py",
      "size_in_bytes": 16082
    },
    {
      "relative_path": "agent-assist-simulate/scripts/native_scenarios.py",
      "size_in_bytes": 10962
    },
    {
      "relative_path": "agent-assist-simulate/scripts/native_swarm.py",
      "size_in_bytes": 25907
    },
    {
      "relative_path": "agent-assist-simulate/scripts/prompt_inputs.py",
      "size_in_bytes": 4014
    },
    {
      "relative_path": "agent-assist-simulate/scripts/swarm_contracts.py",
      "size_in_bytes": 6939
    },
    {
      "relative_path": "agent-assist-simulate/scripts/tool_executor.py",
      "size_in_bytes": 3872
    },
    {
      "relative_path": "agent-assist-simulate/scripts/write_report.py",
      "size_in_bytes": 6441
    }
  ],
  "name": "datarobot-agent-assist",
  "skill_md_contents": "---\nname: datarobot-agent-assist\ndescription: >-\n  Use when the user wants to design, build, code, simulate, or deploy an AI agent (not a predictive\n  model) to DataRobot; mentions agent_spec.md, dr-assist, datarobot-agent-assist, dress rehearsal,\n  swarm simulation, or the DataRobot agent template; wants to scaffold a LangGraph, CrewAI, LlamaIndex, NAT, or Base\n  agent targeting DataRobot; wants to add an MCP server, backend API, or React frontend to a\n  DataRobot agent application; or uses the DataRobot CLI (dr) to build or deploy an agentic custom\n  application; or wants to harden, stress-test, or battle-test an agent. Covers the full workflow: agent design, agent_spec.md authoring, dress-rehearsal\n  simulation via the DataRobot LLM Gateway, adversarial swarm simulation, template-based coding, and deployment.\n---\n\n# DataRobot Agent Assist\n\nThis skill covers **agent design, coding, battle-testing, and deployment** with an optional **dress-rehearsal simulation** before any code is written.\n\nA first message of `1`–`4` selects the corresponding category. If free text clearly maps to one category (e.g. \"I want to build an agent\" → Design), state the inference briefly and proceed. If ambiguous, ask which option applies — do not guess.\n\n---\n\n## Workflow Discipline\n\nFollow this skill **sequentially**. These rules apply to every phase — design, coding, deployment, and every referenced checklist.\n\n1. **Section order** — Complete each section and subsection in the order it appears in this file. Do not jump to a later section until the current one is finished.\n2. **Reference files** — When this skill says **read and follow** a file under `agent-assist-build/references/`, read that file first, then execute every step in that file in order. Do not substitute a summary, shortcut, or a later menu for steps defined in the reference.\n3. **Explicit skips only** — Skip a step only when this skill or the referenced file explicitly says to skip it (e.g. Pre-requisite Check when `<prerequisites_passed>` is true, or Frontend Check when `frontend.type` is already set).\n4. **No auto-advance** — Completing one step (e.g. writing the spec, the user saying \"move on\", or a command succeeding) does not authorize skipping remaining steps. Proceed only when the current section or reference directs you to the next step.\n5. **Menus and prompts** — When a section presents a menu or asks a question, wait for the user's reply. Do not assume a default or proceed on your own.\n6. **One design gate per turn** — During design, do not combine prompts from different subsections in one message (e.g. do not ask about spec refinement and dress rehearsal in the same turn).\n\n---\n\n## On Activation\n\nPresent the four options clearly:\n\n```\nWelcome! I help you design, code, battle-test, and deploy AI agents.\n\nWhat would you like to do?\n  1. Design an AI agent     → Describe your idea (optional dress rehearsal before coding)\n  2. Code an AI agent       → Load and implement an existing agent_spec.md\n  3. Battle-test the agent  → Run adversarial swarm simulation on an implemented agent\n  4. Deploy                 → Deploy an implemented agent to DataRobot\n```\n\nShow this menu first. After the user selects an option (`1`, `2`, `3`, or `4`), run the **[Pre-requisite Check](#pre-requisite-check)** (once per session) and then the **[Script Path Resolution](#script-path-resolution)**.\n\n- Options **1** and **2** — read and follow [agent-assist-build/references/workspace-resolution.md](agent-assist-build/references/workspace-resolution.md), then proceed to the selected workflow.\n- Option **3** — read `agent-assist-simulate/SKILL.md` and jump to **Pre-flight Check** (Pre-requisite Check and Script Path Resolution still apply first).\n- Option **4** — skip Workspace Resolution; `<target_dir>` is resolved in the [Pre-deployment Checklist](agent-assist-build/references/pre-deployment-checklist.md) when unset.\n\n---\n\n## Script Path Resolution\n\nBefore invoking any helper script, resolve `<skill_scripts_dir>` once for the session:\n\n- `<skill_scripts_dir>` is the `agent-assist-build/scripts/` subdirectory of the directory containing this `SKILL.md` file.\n- Confirm it exists with `ls <path_to_this_skill_dir>/agent-assist-build/scripts/`. If the directory is missing, tell the user the skill installation is incomplete and stop.\n- Use the resolved absolute path for every `<skill_scripts_dir>/...` reference in this skill.\n\n---\n\n## Session State\n\nTrack these for the conversation:\n\n- `<target_dir>` — project root. Set during [Workspace Resolution](agent-assist-build/references/workspace-resolution.md) or the [Pre-deployment Checklist](agent-assist-build/references/pre-deployment-checklist.md). Reuse across phases. Change only on explicit user request, [pre-coding Bootstrap step 2](agent-assist-build/references/pre-coding-checklist.md) (spec path recovery), [pre-coding step 7](agent-assist-build/references/pre-coding-checklist.md) (subdir recovery), or a new session.\n- `<prerequisites_passed>` — `false` until the [Pre-requisite Check](#pre-requisite-check) completes successfully once this session.\n- `<workspace_resolved>` — `false` until [Workspace Resolution](agent-assist-build/references/workspace-resolution.md) completes for menu options **1** or **2**.\n- `<workspace_resolved_target_dir>` — the `<target_dir>` set when workspace resolution last completed.\n- `<design_to_code>` — `false` until the user chooses **Code the agent** from [Post-design next steps](#post-design-next-steps) in the same session after design.\n- `<design_messy_cwd>` — `false` until design runs in cwd with files other than `agent_spec.md` / `.env` (see [workspace-resolution](agent-assist-build/references/workspace-resolution.md)).\n- `<dependency_check_passed>` — `false` until a passing `dr dependency check` in `<target_dir>`.\n- `<dependency_check_target_dir>` — the `<target_dir>` value when the last check passed.\n\n### `.env` placement\n\nProject credentials and config live **only** at `<target_dir>/.env` — never in cwd when `<target_dir>` is a subdirectory. This includes DataRobot CLI credentials, LLM config, and **tool/service secrets**. Pulumi reads these from the environment at deploy time (`os.environ`); a secret missing from `.env` means the corresponding credential and runtime parameter are not created.\n\n- Complete [Workspace Resolution](agent-assist-build/references/workspace-resolution.md) before any step that needs credentials or creates a `.env` file.\n- Always pass `--target-dir <target_dir>` to helper scripts that read or create `.env` (`list_llm_models.py`, `rehearsal.py`, `setup_template.py`). Do **not** run `dr dotenv setup` in cwd.\n- Never put secret values in `agent_spec.md` or source code — only env var **names** belong in infra; values stay in `.env`.\n\n### Dependency check session rule\n\nBefore running dependency validation:\n\n- If `<dependency_check_passed>` is true and `<target_dir>` equals `<dependency_check_target_dir>`, skip validation.\n- Otherwise, read and follow [agent-assist-build/references/dependency-validation.md](agent-assist-build/references/dependency-validation.md) in `<target_dir>`.\n\nInvalidate `<dependency_check_passed>` (set to false) when:\n\n- `<target_dir>` changes\n- `clone_template.py`, `select_framework.py`, or `setup_template.py` runs in `<target_dir>`\n\n### Welcome menu reset\n\nWhen showing the [welcome menu](#on-activation) again (e.g. user declined pre-coding step 7): set `<workspace_resolved>` = false, clear `<workspace_resolved_target_dir>`, `<design_to_code>` = false, and `<design_messy_cwd>` = false. Keep `<prerequisites_passed>` true.\n\n---\n\n## Workspace Resolution\n\nRead and follow [agent-assist-build/references/workspace-resolution.md](agent-assist-build/references/workspace-resolution.md) after menu options **1** or **2**.\n\n---\n\n## Pre-requisite Check\n\nIf `<prerequisites_passed>` is true, skip this section.\n\nOtherwise, run in order before proceeding:\n\n1. **Git** — run `git --version`. If missing, tell the user to install from https://git-scm.com and stop.\n2. **Python** — run `python --version`. If missing or below 3.11, tell the user to install Python 3.11+ from https://python.org and stop.\n3. **DataRobot CLI** — read and follow [agent-assist-build/references/dr-cli-setup.md](agent-assist-build/references/dr-cli-setup.md):\n   - If missing, **ALWAYS RUN** the install command before proceeding\n   - **ALWAYS RUN** the upgrade command before proceeding\n   - If not authenticated, **ALWAYS RUN** the auth command before proceeding\n4. **Codespace** — run `python <skill_scripts_dir>/check_codespace.py` (no-op outside a Codespace). On non-zero exit, relay its message and stop; otherwise relay any exposed-ports warning it prints.\n\nOn success, set `<prerequisites_passed>` = true.\n\n---\n\n## 1. Designing an AI Agent\n\nWhen `<target_dir>/agent_spec.md` already exists, read and follow [resume-design.md](agent-assist-build/references/resume-design.md) after [workspace resolution](agent-assist-build/references/workspace-resolution.md) or when returning from [Spec issues](agent-assist-build/references/pre-coding-checklist.md#spec-issues). For a **new** agent (no spec yet), start at [Clarification Phase](#clarification-phase).\n\n### Clarification Phase\n\n- Ask **at most 2 rounds** of clarifying questions before proposing an initial draft spec. If tools are still ambiguous after two rounds, start simple.\n- Focus questions on:\n  - What the agent does and who uses it\n  - What tools it needs and what external services those tools call\n  - Whether those services require authentication (API key, OAuth2, bearer token, etc.)\n  - Whether the user needs a custom frontend beyond the default chat UI\n\n- If the user mentions UI-related needs early (\"dashboard\", \"visualization\", \"multi-page\", \"admin panel\", \"settings page\"), capture it immediately in the `frontend` field and write `frontend.type` to `agent_spec.md` — do **not** defer or wait for [Frontend Check](#frontend-check).\n\n### Model Selection\n\n- To check available models, run (requires `<target_dir>` from workspace resolution — see [.env placement](#env-placement)):\n\n   ```\n   python <skill_scripts_dir>/list_llm_models.py \\\n     --json \\\n     --target-dir <target_dir>\n   ```\n\n  **CRITICAL**: Always pass `--target-dir <target_dir>`. In case the script fails due to any reason, do **not** proceed. Instead, return the error message to the user and ask how they want to proceed.\n\n- Read and follow [llm-selection.md](agent-assist-build/references/llm-selection.md) to recommend from the two sources (`gateway` and `deployed`) and record the choice.\n- If the user's desired model is unavailable, suggest starting with an available one and updating after implementation.\n\n### Frontend Check\n\nSkip this section if `frontend.type` is already captured — either written to `<target_dir>/agent_spec.md`, or held in working memory from [Clarification Phase](#clarification-phase) before the first draft exists.\n\nBefore the first spec draft, if `frontend.type` is not yet set, **always ask**:\n\n> \"The template includes a default chat UI — is that sufficient, or would you like a custom frontend such as a dashboard, data visualization, or multi-page app?\"\n\nThen set `frontend` in the spec (write to `<target_dir>/agent_spec.md` when the file exists, or hold the value for the first draft in [Spec Display](#spec-display)):\n- Default UI → `frontend.type: \"chat\"`\n- Custom UI → `frontend.type: \"multi-page\"` or `\"custom\"` with `pages` and optional `requirements`\n\n### Spec Display\n\n- Before the first draft, read [agent-assist-build/references/agent-spec-schema.md](agent-assist-build/references/agent-spec-schema.md).\n- **Always write the current spec to `<target_dir>/agent_spec.md`** (YAML format) whenever showing it to the user. The first draft must include `frontend.type` from [Frontend Check](#frontend-check) (or clarification).\n- Show the spec frequently and iteratively — even if incomplete or partial.\n- Do **not** summarize the spec in prose; display it as YAML in a code block.\n- After displaying, invite the user to refine system prompts, tools, model, or examples. Do **not** ask about dress rehearsal, coding, template setup, or \"moving on\" in the same turn, and do **not** offer \"proceed to coding\" as an alternative to refinement (including on [Resume Design](agent-assist-build/references/resume-design.md) after pre-coding [Spec issues](agent-assist-build/references/pre-coding-checklist.md#spec-issues)).\n- If the user requests changes, update the spec and show it again. If the user indicates they are done refining (e.g. \"looks good\", \"no changes\", \"move on\"), proceed to [Agent Simulation (Before Coding)](#agent-simulation-before-coding) in your **next** response — not to [Post-design next steps](#post-design-next-steps) or coding.\n\n### Agent Simulation (Before Coding)\n\nWhen spec refinement is complete, read [agent-assist-build/references/dress-rehearsal.md](agent-assist-build/references/dress-rehearsal.md) and present the **Initial prompt (design phase)** using that file's **exact wording** — in its own turn, with no spec-refinement question in the same message.\n\nThen follow dress-rehearsal.md for the user's reply (yes → rehearsal; no → [Post-design next steps](#post-design-next-steps)).\n\n### Post-design next steps\n\nAfter the user declines the initial rehearsal prompt — or **after** a dress rehearsal session ends **and** `<target_dir>/rehearsal_report/rehearsal_report.md` has been written — present this menu (exact wording):\n\n> What would you like to do next?\n> 1. **Code the agent** — start implementation from `agent_spec.md`\n> 2. **Review / edit spec** — refine `agent_spec.md`\n> 3. **Run dress rehearsal** — simulate the agent before coding\n> 4. **Review rehearsal report** — open `rehearsal_report/rehearsal_report.md`\n\nWait for their choice. **Do not** assume a default or proceed without a reply.\n\n| Choice | Action |\n|--------|--------|\n| 1 or \"code\" / \"implement\" | Set `<design_to_code>` = true. Follow **[2. Coding an AI Agent](#2-coding-an-ai-agent)** — read and follow [pre-coding-checklist.md](agent-assist-build/references/pre-coding-checklist.md). This does **not** authorize cloning or subdirectory creation; if the workspace is not spec-only, complete [pre-coding step 7](agent-assist-build/references/pre-coding-checklist.md) and wait for explicit confirmation first. |\n| 2 or \"review\" / \"edit spec\" | Display `<target_dir>/agent_spec.md` as YAML, invite changes, update the file, then show this menu again |\n| 3 or \"rehearsal\" / \"simulate\" | Follow **[Dress Rehearsal](#dress-rehearsal)** |\n| 4 or \"review report\" / \"rehearsal report\" | If `<target_dir>/rehearsal_report/rehearsal_report.md` exists, read it and present a structured summary (metadata, notes, conversation highlights, suggested changes). If missing, say no report exists yet and offer option 3. Then show this menu again. |\n\nIf the user's reply is unclear, re-display the menu and wait. Never skip straight to framework selection after a rehearsal decline.\n\n---\n\n## Dress Rehearsal\n\nRead and follow [agent-assist-build/references/dress-rehearsal.md](agent-assist-build/references/dress-rehearsal.md) end to end.\n\n---\n\n## 2. Coding an AI Agent\n\n**On Windows: coding is not supported. STOP and do NOT proceed with the next steps!**\n\n### Pre-coding Checklist\n\nRead and follow [agent-assist-build/references/pre-coding-checklist.md](agent-assist-build/references/pre-coding-checklist.md) end to end before writing or editing implementation code. Do not write or edit implementation code until the checklist is complete.\n\n### Coding Rules\n\n- Implement by adapting the template code — do not write from scratch\n- Modify files only inside `<target_dir>` and its subdirectories\n- Do not view `.env` files (`.env.template` files are OK)\n- **Tool credentials** — when implementing a tool with `auth_spec` in `agent_spec.md`:\n  1. Choose a `SCREAMING_SNAKE_CASE` env var name (e.g. `PERPLEXITY_API_KEY`).\n  2. **Append** `VAR_NAME=` to `<target_dir>/.env` without reading the file.\n  3. Ask the user to paste the secret into `<target_dir>/.env` in their editor — never in chat, `agent_spec.md`, or committed code.\n- Do not add code comments unless asked\n- Do not mock tool implementations unless they would be complex to implement\n- For tasks with 3+ steps, use the TodoWrite tool to manage your work\n- Keep text responses **concise (1–3 sentences)** while coding — skip preamble and postamble\n\n### File Write/Edit Discipline\n\n- Always explain **why** the change is needed (purpose and impact) in 1–2 sentences before writing or editing a file\n- Invoke at most **one shell command per response** — wait for the result before invoking another\n\n### After Coding\n\n1. Read `<target_dir>/AGENTS.md` to find the local test command.\n2. Display the command in a code block.\n3. Tell the user: \"Run this command in a **new terminal** in `<target_dir>` to test the agent locally.\"\n4. Do **not** run the command yourself.\n5. Present next steps: revise the implementation, battle-test the agent (option 3), or deploy to DataRobot (option 4).\n\n---\n\n## 3. Battle-testing an AI Agent\n\nRead `agent-assist-simulate/SKILL.md` and jump directly to **Pre-flight Check** — skip its On Activation menu. Also trigger directly when the user says \"simulate my agent\", \"run swarm\", \"adversarial testing\", \"harden my agent\", or \"test my agent\".\n\nSwarm requires an implemented agent; if none exists, explain and offer option 2. If code exists and no option is chosen, proactively offer: \"I can also battle-test your agent before deploying — want to run swarm simulation?\"\n\n---\n\n## 4. Deploying an AI Agent\n\nRead and follow [agent-assist-build/references/pre-deployment-checklist.md](agent-assist-build/references/pre-deployment-checklist.md) end to end.\n\n---\n\n## Error Handling\n\n- If a tool returns an error, read the error message carefully before responding\n- For dependency validation failures that cannot be fixed (install or re-check still fails): hard stop — return full output from all commands run (see [Dependency validation](agent-assist-build/references/dependency-validation.md))\n- On unexpected errors, ask the user if they want to retry\n\nHelper-script failures during pre-coding are governed by the **CRITICAL** rule in [pre-coding-checklist.md](agent-assist-build/references/pre-coding-checklist.md).\n\n---\n\n## agent_spec.md\n\nWrite specs as YAML to `<target_dir>/agent_spec.md`. Fields are optional while the spec is evolving.\n\nField definitions: [agent-assist-build/references/agent-spec-schema.md](agent-assist-build/references/agent-spec-schema.md). Complete examples: [agent-assist-build/references/agent-spec-examples.md](agent-assist-build/references/agent-spec-examples.md).\n\n---\n\n## Tool/Helper Scripts Timeouts\n\n- Allow up to 25 minutes for any helper script to complete before timing out and returning an error\n- Allow up to 25 minutes for any shell command or tool to return a response before timing out and returning an error\n- Allow up to 60 minutes for deployment-related shell commands to complete before timing out and returning an error\n\n---\n\n\n## Behavioral Rules\n\n- Follow [Workflow Discipline](#workflow-discipline) at all times\n- Welcome-menu routing: prefer `1`–`4`; for clear free-text intent, infer and state the category then proceed; if ambiguous, ask which option applies\n- If the user insists on a task outside these four categories, politely decline\n- If a user asks to code before designing, strongly encourage designing first\n- Before running any CLI command or helper script, explain in 2–5 sentences why it is needed now and what it will check/change/create\n- **Template clone / spec validation / spec issues** — follow [pre-coding-checklist.md](agent-assist-build/references/pre-coding-checklist.md) ([Clone discipline](agent-assist-build/references/pre-coding-checklist.md#clone-discipline), Bootstrap step 2, [Spec issues](agent-assist-build/references/pre-coding-checklist.md#spec-issues)) and [spec complete](agent-assist-build/references/resume-design.md#spec-complete)\n- After the user declines dress rehearsal, always show **[Post-design next steps](#post-design-next-steps)** — never skip to framework selection or the pre-coding checklist\n- During rehearsal, follow [dress-rehearsal.md](agent-assist-build/references/dress-rehearsal.md): display `output_file` verbatim; on **DONE** always run `--report` before any summary or menu; write `<target_dir>/rehearsal_report/rehearsal_report.md` before showing Post-design next steps\n- During **coding**: keep responses to 1–3 sentences; no introductions or conclusions\n- During **design**: be conversational and thorough\n\nFor helper script commands, see [helper-scripts.md](agent-assist-build/references/helper-scripts.md). For plugin tool mapping, see [tool-mapping.md](agent-assist-build/references/tool-mapping.md).\n"
}