复制安装命令
用 Codex 或 Claude 安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
SkillAtlasSkill 详情
aiq-deploy
Official, NVIDIA-verified Agent Skills for Claude Code, Codex, and other coding agents.
审核状态：已审核Quality 72Security 70
项目 README
来源文件：README.md
NVIDIA Agent Skills
Official, NVIDIA-verified Agent Skills for Claude Code, Codex, and other coding agents.
📖 Docs: docs.nvidia.com/skills · 📺 Livestream: From Vulnerable to Verified · 📝 Blog: NVIDIA Verified Agent Skills: Capability Governance for AI Agents
Skills are portable instruction sets that teach AI agents how to use NVIDIA software optimally: Physical AI and robotics workflows, simulation, CUDA-X libraries, RAG and AI Blueprints, and platform tools. This repository is a catalog: skills are maintained in their respective product repos, and mirrored here daily via an automated sync pipeline. Skills are being added continuously, so check back for updates. We are building this infrastructure in the open, and contributions are welcome. See the Roadmap for what is planned next.
Quickstart
Install NVIDIA skills with the default skills CLI flow:
npx skills add nvidia/skills
The CLI runs through npx and prompts you to choose a skill and install destination. You do not need to clone this repo or copy skill folders by hand.
Requires a current
skillsCLI (v1.5.16 or newer). Installing vianpx skills@latest add nvidia/skillsalways uses the latest. On older CLIs (v1.5.15 and earlier), skills may install but not appear in Claude Code — see Troubleshooting.
The skill is available the next time your agent loads skills and encounters a relevant task. For example, ask your agent to "solve a linear programming problem with cuOpt" and the skill guides it through the cuOpt Python API. In Claude Code, run /reload-skills to load newly installed skills in your current session.
Install One Skill Without Prompts
Use this when you already know the skill name and want to skip prompts.
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --yes
Replace cuopt-numerical-optimization-api with any skill name from the Skill Catalog.
Install for a Specific Agent
Use --agent to target a specific AI coding agent. Initially, we'll support common client targets, expanding the list over time. For the full list of clients supported by the spec, see the skills CLI Supported Agents table.
Claude Code
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent claude-code
Codex
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent codex
Snowflake CoCo
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent cortex
Cursor
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent cursor
Kiro
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent kiro-cli
Use --agent more than once to install the same skill into multiple agents.
npx skills add nvidia/skills \
--skill cuopt-numerical-optimization-api \
--agent claude-code \
--agent codex \
--agent cursor \
--agent kiro-cli
Keep Skills Up to Date
New skills land continuously, and existing ones are revised, renamed, or consolidated as the catalog evolves. Refresh what you have installed with:
npx skills update
Run it interactively and the CLI also flags skills that were removed or merged upstream (for example, when several skills are consolidated into one) and offers to remove the stale local copies. Use npx skills list to see what is installed and npx skills check to preview what is out of date first.
Browse the Catalog
Use this when you want to see available NVIDIA skills before installing anything.
npx skills add nvidia/skills --list
For non-interactive installs, global installs, agent-specific installs, updates, removals, and fallback manual copying, see Advanced installation.
Skill Catalog
Getting Help & Contributing
Where to file an issue depends on what's broken:
- Skill content issues (a specific skill has a bug, missing functionality, or incorrect content) — file in the source repo for that product, using the per-product table below.
- Catalog issues (catalog README errors, sync workflow problems, distribution channels, signing/verification flow, docs in this repo) — file here using the catalog issue templates: Bug Report, Feature Request, or Documentation Request or Correction.
- Questions or general discussion — use Discussions. The issue tracker is reserved for bug reports, feature proposals with a design, and documentation issues.
- Security vulnerabilities — follow the disclosure process in SECURITY.md; do not open a public issue.
Per-product source repo links:
For issues with this catalog repo itself (README, structure, listing a new product): open an issue here.
Verifying Skills
Every published skill ships with a detached OMS signature (skill.oms.sig). The sync pipeline drops any skill missing the required artifacts before publishing, so every skill in the catalog carries:
SKILL.md— the skill instructions consumed by the agentskill-card.md— skill identity and governance cardskill.oms.sig— detached OMS signature (verifiable againstnv-agent-root-cert.pem)- A Tier-3 evaluation dataset — accepted at
evals/evals.json,evals/*.json,eval/*.json, orbenchmark/evals.json BENCHMARK.md— generated benchmark report capturing verifiable uplift data
Verify a skill against the NVIDIA trust anchor nv-agent-root-cert.pem:
pip install model-signing
model_signing verify certificate SKILL_DIR \
--signature SKILL_DIR/skill.oms.sig \
--certificate_chain nv-agent-root-cert.pem \
--ignore_unsigned_files
A successful verification confirms that the skill contents have not been modified since signing by NVIDIA.
See Verify Signed Agent Skills for signature layout, the trust pipeline, and policy options.
Roadmap
- ✅ Public skills catalog with NVIDIA-verified skills across multiple products
- ✅ Automated sync pipeline with skills mirrored from product repos daily
- ✅ Security scanning for all published skills covering instruction safety and supply-chain integrity
- ✅ Skills signing so every published skill carries a verifiable NVIDIA signature
- ✅ Skills universal evaluation criteria and task-specific criteria
- ✅ Skill Card with machine-readable metadata for identity, provenance, quality, and behavioral boundaries
- ✅ Sync-time compliance gates — signature drift detection and missing-artifact enforcement
- ✅ Syndication to external marketplaces — Skills.sh, Codex plugin, Claude Code plugin, ClawHub, Hermes Hub
- 🔲 Syndication to additional MCP hubs and partner channels
Repository Structure
NVIDIA/skills/
├── skills/ # NVIDIA-verified skills (count grows continuously),
│ │ synced from upstream product repos
│ ├── README.md # Browser-facing install guidance
│ ├── <product-prefix>-*/ # Flat layout — one dir per skill, product-prefixed
│ │ # e.g. aiq-*, cufolio, cuopt-*, cupynumeric-*,
│ │ # dali-*, deepstream-*, dicom-*, digital-health-*,
│ │ # dynamo-*, earth2studio-*, holoscan-*, hsb-*,
│ │ # jetson-*, launch-nemo-rl, mcore-*,
│ │ # nemo-automodel-*, nemo-data-designer-plugin,
│ │ # nemo-evaluator-plugin, nemo-mbridge-* (20 skills),
│ │ # nemo-retriever, nemo-rl-* (4 skills),
│ │ # nemoclaw-user-guide, nemotron-*, nemotron-speech,
│ │ # nv-* (medical AI), physicsnemo-*, rag-*,
│ │ # skill-card-generator, tao-*, tilegym-*,
│ │ # vss-* (15 skills), accelerated-computing-cudf,
│ │ # cudaq-guide
│ ├── omniverse-*/ # Physical AI — manually staged (see manual-components.yml)
│ └── physical-ai-*/ # Physical AI — manually staged
├── components.d/ # Product registry — one file per component, teams onboard here
│ ├── README.md # Schema and onboarding instructions
│ └── <product>.yml # one file per registered product
├── plugins/ # Packaged plugin distributions
│ └── nvidia-skills/ # Curated NVIDIA skills bundle (Claude Code, Codex)
├── plugins.d/ # Plugin build registry — config for `build-plugins.py`
│ ├── README.md
│ ├── _defaults.yml
│ └── nvidia-skills.yml
├── .claude-plugin/ # Claude Code marketplace metadata
│ └── marketplace.json
├── .agents/plugins/ # Agent marketplace metadata (other clients)
│ └── marketplace.json
├── docs/ # Long-form documentation (published via Fern)
│ ├── README.md # How to build the docs locally
│ ├── index.mdx
│ ├── advanced-install.mdx
│ ├── agent-skill-trust-pipeline.mdx
│ ├── release-checklist.mdx
│ ├── scanning-agent-skills.mdx
│ ├── signing-agent-skills.mdx
│ └── skill-cards.mdx
├── fern/ # Fern docs site configuration
├── .github/
│ ├── workflows/ # Sync pipeline, plugin validation, DCO check, author verify
│ └── scripts/ # regenerate-readme.sh, build-plugins.py,
│ # manual-components.yml (temp Physical AI catalog
│ # exception, removed after Computex 2026),
│ # marketplace/metadata.json (skill metadata sidecar)
├── nv-agent-root-cert.pem # Trust anchor for OMS signature verification
├── skills.sh.json # Skills.sh marketplace grouping config
├── CHANGELOG.md
├── CONTRIBUTING.md # Contribution guidelines
├── SECURITY.md # Security reporting policy
├── CODE_OF_CONDUCT.md # Community code of conduct
├── LICENSE-APACHE # Apache 2.0 (source code)
└── LICENSE-CC-BY-4.0 # CC BY 4.0 (documentation/skills)
Skills are maintained in their respective product repos (see the Source column in the Skill Catalog) and synced to this repo daily. Products only appear under skills/ after the sync pipeline confirms each skill carries:
skill.oms.sig— detached OMS-format signature (verifiable againstnv-agent-root-cert.pem)skill-card.md— skill identity and governance card- A Tier-3 evaluation dataset — accepted at
evals/evals.json,evals/*.json,eval/*.json, orbenchmark/evals.json
When evaluation runs produce a BENCHMARK.md, it ships alongside the skill so consumers can see verifiable benchmark uplift data.
Standards & Compatibility
This repository adheres to the Agent Skills specification:
- Skills are portable directories with a
SKILL.mdfile at their root. - Metadata uses YAML frontmatter with required
nameanddescriptionfields. - Skills follow a progressive disclosure model — lightweight metadata loads at startup, full instructions load on activation.
- Validate your skill using the
skills-refreference library.
License
Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
This code is dual-licensed with documentation/skills under the CC-BY-4.0 AND source code under Apache-2.0 license terms. The full license texts can be found in LICENSE-APACHE and LICENSE-CC-BY-4.0 respectively.
DevOps 与部署
中风险
- 来源需自行核对维护者身份。
- 包含脚本或命令调用，安装前请复核。
- 可能需要外部 token、网络权限或第三方服务。
- 未检测到高风险命令。
- 扫描发现：3 条。
Codex — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/example/repo.git
- 将 "repo" 文件夹复制到 Codex 的 skills 目录中。
- 重启 Codex 让新的 skill 生效。
Codex — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 Codex 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 Codex 让新的 skill 生效。
Claude Code — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/example/repo.git
- 将 "repo" 文件夹复制到 Claude Code 的 skills 目录中。
- 重启 Claude Code 让新的 skill 生效。
Claude Code — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 Claude Code 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 Claude Code 让新的 skill 生效。
Cursor — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/example/repo.git
- 将 "repo" 文件夹复制到 Cursor 的 skills 目录中。
- 重启 Cursor 让新的 skill 生效。
Cursor — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 Cursor 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 Cursor 让新的 skill 生效。
GitHub Copilot — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/example/repo.git
- 将 "repo" 文件夹复制到 GitHub Copilot 的 skills 目录中。
- 重启 GitHub Copilot 让新的 skill 生效。
GitHub Copilot — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 GitHub Copilot 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 GitHub Copilot 让新的 skill 生效。
Windsurf — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/example/repo.git
- 将 "repo" 文件夹复制到 Windsurf 的 skills 目录中。
- 重启 Windsurf 让新的 skill 生效。
Windsurf — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 Windsurf 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: aiq-deploy
description: |
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
license: Apache-2.0
compatibility: |
Designed for Claude Code, OpenCode, Codex, and Agent Skills-compatible tools. Requires Git, network
access to GitHub, and one selected runtime path: Docker Compose v2 for the default local deployment,
Python 3.11+ and uv for local process or CLI mode, Node.js 20+ and npm for local web UI mode, or
kubectl 1.28+ and Helm 3.12+ for Kubernetes and Helm mode.
metadata:
version: "2.1.0"
author: "NVIDIA AI-Q Blueprint Team <aiq-blueprint@nvidia.com>"
github-url: "https://github.com/NVIDIA-AI-Blueprints/aiq"
tags:
- nvidia
- aiq
- blueprint
- deploy
- operations
- agent-skills
allowed-tools: Read BashAIQ Deploy Skill
Purpose
Use this skill to get a local or self-hosted NVIDIA AI-Q Blueprint server running and verified for use by
aiq-research.
This skill owns setup, deployment, operational checks, troubleshooting, and shutdown. It does not run deep
research itself. After deployment is healthy, hand off the verified server URL to aiq-research.
The workflow stays explicit so deployment validation and handoff are repeatable across supported agent clients.
Prerequisites
Users need:
- Access to clone or update
https://github.com/NVIDIA-AI-Blueprints/aiq. - Git available in the shell.
- One deployment runtime:
- Docker Engine with Docker Compose v2 for the default durable local deployment.
- Python 3.11+ and
uvfor local process or CLI mode. - Node.js 20+ and
npmfor local browser UI development mode. kubectl1.28+, Helm 3.12+, and access to a Kubernetes cluster for Helm mode.
- Network access to GitHub, NVIDIA-hosted model endpoints, and any selected search provider.
- Credentials stored outside chat. Hosted-model usage requires
NVIDIA_API_KEY; web research requires at least one supported search provider key such asTAVILY_API_KEY,SERPER_API_KEY, orEXA_API_KEY. - System capacity for the selected runtime. Docker Compose mode starts the AI-Q backend and PostgreSQL by default;
browser UI mode also uses frontend port
3000. Self-hosted model or RAG deployments may require GPU resources.
Before writing secrets, verify deploy/.env is ignored:
git check-ignore deploy/.env
Expected output: deploy/.env or a matching ignore rule. If it is not ignored, stop and fix the ignore rule before
placing credentials in the file.
Instructions
- Locate or clone the AI-Q repository.
- Confirm the expected repository files exist.
- Select the deployment mode.
- Prepare
deploy/.envwithout overwriting user secrets. - Check runtime prerequisites for the selected path.
- Start the selected deployment.
- Run basic validation.
- Report the verified
AIQ_SERVER_URLforaiq-research. - Ask whether to run optional deep research completion validation.
Step 1 - Locate or clone AI-Q
If no AI-Q checkout exists, read references/locate-or-clone.md before cloning. In an existing checkout, confirm the
required files:
pwd
test -f pyproject.toml
test -f deploy/.env.example
test -d configs
Expected output: pwd prints the AI-Q repository path; the test commands exit with status 0 and no output.
Step 2 - Select the deployment mode
If the user asks to install, deploy, set up, or run AI-Q without naming a mode, ask:
How do you want to run AI-Q?
1. Skill backend - backend-only service for aiq-research w/o browser UI.
2. CLI - interactive terminal AI-Q.
3. UI - browser AI-Q app with backend and frontend.
4. Custom - choose an existing AI-Q config or review advanced customization docs before deployment.
Wait for the user's answer before starting services.
Do not ask this question when the user already specified a mode, such as Docker Compose, Helm, UI, CLI, or Agent Skill
backend. Do not ask the full mode question when aiq-research routed here because a deep research request needs a
backend. In that case, prefer Agent Skill backend and ask only for permission to start it if needed.
Step 3 - Prepare environment and secrets
Read references/env-and-secrets.md before changing deploy/.env.
if [ ! -f deploy/.env ]; then
cp deploy/.env.example deploy/.env
echo "created deploy/.env from deploy/.env.example"
fi
Expected output when the file is missing: created deploy/.env from deploy/.env.example. Expected output when the file
already exists: no output, and the existing file is preserved.
Never print secret values. If credentials are missing, ask the user to update deploy/.env; do not ask them to paste
secret values into chat.
Step 4 - Route to the selected deployment path
Match the user request, then read the referenced file before acting:
| User Intent | Reference |
|---|---|
| No AI-Q checkout exists, install AIQ, clone AIQ, locate repo | references/locate-or-clone.md |
Configure environment, check API keys, inspect .env | references/env-and-secrets.md |
Choose an AI-Q workflow config, understand config files, set BACKEND_CONFIG or CONFIG_FILE | references/configs.md |
Backend-only local server for aiq-research, AIQ as an Agent Skill | references/skill-backend.md |
| Terminal assistant, CLI-only run, no web UI | references/terminal-cli.md |
| Quick local development run, start UI/backend without containers | references/local-web.md |
| Default durable local deployment, Docker Compose, containers, PostgreSQL | references/docker-compose.md |
| Kubernetes, Helm, cluster deployment | references/kubernetes-helm.md |
| Foundational RAG / FRAG integration | references/frag.md |
Basic health checks, shallow smoke checks, handoff to aiq-research | references/validation.md |
| Optional deep research completion validation | references/end-to-end-validation.md |
| Logs, unhealthy services, port conflicts, config failures | references/troubleshooting.md |
| Stop services, restart, rebuild, safe cleanup | references/shutdown.md |
Step 5 - Validate and hand off
After startup, read references/validation.md and run the appropriate checks for the selected mode. For the default
local backend, verify health:
curl -sf http://localhost:8000/health
Expected output: a successful JSON health response or an empty successful response depending on the server build. If the
command fails, read references/troubleshooting.md and diagnose before claiming the backend is ready.
aiq-research needs a reachable AI-Q server URL. If the backend is on the default port, no extra configuration is
needed:
AIQ_SERVER_URL=http://localhost:8000
If the backend runs elsewhere, tell the user to set:
export AIQ_SERVER_URL="http://localhost:<PORT>"
Do not continue into deep research or deep research completion validation unless the user asks for it or confirms the post-deploy validation prompt. This skill's success criterion is a deployed and basically validated server, not report generation quality.
Version Compatibility
IMPORTANT: This skill is designed for NVIDIA AI-Q Blueprint version 2.1.0.
Semantic Versioning Compatibility Rules:
Skill version: X.Y.Z
Blueprint version: A.B.C
Compatible IF:
1. A == X (Major versions MUST match)
2. B >= Y (Minor version must be equal or greater)
3. C can be anything (Patch version does not affect compatibility)
Examples:
- Skill version 2.1.0 is compatible with Blueprint version 2.1.0.
- Skill version 2.1.0 is compatible with Blueprint version 2.2.0.
- Skill version 2.1.0 is compatible with Blueprint version 2.1.5.
- Skill version 2.1.0 is not compatible with Blueprint version 3.0.0.
- Skill version 2.1.0 is not compatible with Blueprint version 2.0.0.
If your Blueprint version is not compatible:
- Check for an updated skill version matching your Blueprint version.
- Use a Blueprint version compatible with this skill.
- Proceed with caution only when the user accepts the compatibility risk; deployment commands or config names may have changed.
Security Best Practices
- Never print secret values. Check only whether required environment variables are set.
- Store credentials in
deploy/.envor environment variables, not in chat transcripts, shell history, committed files, or example commands. - Do not overwrite
deploy/.envwhen it already exists. - Ask before destructive cleanup such as deleting Docker volumes with
down -v. - Do not claim FRAG is ready unless both
RAG_SERVER_URLandRAG_INGEST_URLare configured and reachable. - Run verification commands yourself when possible.
Limitations
- This skill prepares and validates AI-Q infrastructure; it does not judge deep research report quality.
- It cannot provide or inspect secret values. Users must configure credentials outside chat.
- Helm, FRAG, custom config, and self-hosted model paths depend on infrastructure the user controls.
- Destructive cleanup, such as deleting Docker volumes, requires explicit user approval.
Examples
Example 1: Deploy a backend-only Skill server with Docker Compose
test -f deploy/.env || cp deploy/.env.example deploy/.env
git check-ignore deploy/.env
cd deploy/compose
BUILD_TARGET=release docker compose --env-file ../.env -f docker-compose.yaml config --quiet
BUILD_TARGET=release docker compose --env-file ../.env -f docker-compose.yaml up -d --build aiq-agent
curl -sf http://localhost:8000/health
Expected output:
deploy/.env
<docker compose starts aiq-agent and dependencies>
<health endpoint returns a successful response>
If Docker, ports, credentials, or health checks fail, read references/troubleshooting.md before retrying.
Example 2: Hand off a non-default backend URL to aiq-research
export AIQ_SERVER_URL="http://localhost:8100"
curl -sf "$AIQ_SERVER_URL/health"
Expected output: a successful health response. Then tell the user to keep AIQ_SERVER_URL set before invoking
aiq-research.
References
| Topic | Documentation |
|---|---|
| Locate or clone AI-Q | references/locate-or-clone.md |
| Environment and secrets | references/env-and-secrets.md |
| Workflow configs | references/configs.md |
| Agent Skill backend | references/skill-backend.md |
| CLI deployment | references/terminal-cli.md |
| Local web deployment | references/local-web.md |
| Docker Compose deployment | references/docker-compose.md |
| Kubernetes and Helm deployment | references/kubernetes-helm.md |
| FRAG integration | references/frag.md |
| Basic validation | references/validation.md |
| End-to-end validation | references/end-to-end-validation.md |
| Troubleshooting | references/troubleshooting.md |
| Shutdown and cleanup | references/shutdown.md |
Common Issues
Issue: Backend port is already in use
Symptoms:
- Docker Compose fails to bind port
8000. curl -sf http://localhost:8000/healthreaches an unexpected service or fails.
Causes:
- Another AI-Q backend or local development server is already running.
PORTindeploy/.envconflicts with an existing process.
Solutions:
- Identify the process:
lsof -nP -iTCP:8000 -sTCP:LISTEN - Either stop the conflicting process with the user's approval or set a different port in
deploy/.env, such asPORT=8100. - Restart the selected deployment path and verify:
curl -sf http://localhost:8100/health
Issue: Required credentials are missing
Symptoms:
- Infrastructure starts, but model-backed chat or research requests fail.
- Logs mention unauthorized, forbidden, invalid key, or missing provider configuration.
Causes:
NVIDIA_API_KEYis missing or empty.- No supported search provider key is configured for web research.
Solutions:
- Check presence without printing values by following
references/env-and-secrets.md. - Ask the user to update
deploy/.env; do not ask them to paste secrets into chat. - Rerun
references/validation.mdafter the user updates credentials.
Issue: Backend is healthy but not compatible with aiq-research
Symptoms:
/healthsucceeds, but/chator/v1/jobs/async/agentsfails.aiq-researchreports that async agents are unavailable.
Causes:
- The selected config is CLI-only or does not expose the web/API backend expected by the skill.
BACKEND_CONFIGorCONFIG_FILEpoints at the wrong AI-Q config.
Solutions:
- Read
references/configs.mdand confirm the selected config is API-enabled. - For the default Skill backend, use
configs/config_web_default_llamaindex.yml. - Restart the backend and rerun
references/validation.md.
Issue: Docker cleanup would remove useful state
Symptoms:
- Troubleshooting suggests
docker compose down -v. - The user may have local PostgreSQL job or checkpoint data they want to keep.
Causes:
down -vremoves Docker volumes.- Rebuilds and restarts are often enough for config or image changes.
Solutions:
- Prefer a normal restart from
references/shutdown.md. - Ask for explicit approval before running volume deletion.
- After cleanup, rerun deployment and validation from the selected route.
评论 (0)
暂无评论，成为第一个评论者吧！