菜单
Use when preparing, opening, or updating an AI-Q pull request — scoping the branch, signing commits with DCO, filling the PR template with real validation evidence, and following the copy-pr-bot CI and merge flow.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/NVIDIA-AI-Blueprints/aiq --skill aiq-prepare-pr命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | aiq-prepare-pr |
| description | Use when preparing, opening, or updating an AI-Q pull request — scoping the branch, signing commits with DCO, filling the PR template with real validation evidence, and following the copy-pr-bot CI and merge flow. |
| license | Apache-2.0 |
| compatibility | Claude Code, Codex, Cursor, OpenCode, and Agent Skills-compatible tools. |
| metadata | {"version":"0.1.0","source-repo":"NVIDIA-AI-Blueprints/aiq","tags":"aiq pull-request dco contributing release-qa"} |
| allowed-tools | Read Bash Edit |
Use this skill to take a finished AI-Q change from a working branch to a
review-ready pull request: a focused branch off develop, DCO-signed commits,
the PR template filled with real validation evidence, and the copy-pr-bot CI
flow followed correctly.
aiq-release-qa first and reuse its exact output as evidence.Signed-off-by
trailer may be rejected.develop branch unless a maintainer asked for a release branch./ok to test / /merge flow.aiq-release-qa runs.For the step-by-step checklist and the bot command reference:
develop; rebase or reset scope if
unrelated files crept in.git commit -s (and git commit --amend -s
or git rebase --signoff to fix unsigned commits already made).aiq-release-qa and keep the exact output.develop./ok to test, copy-pr-bot mirrors
the PR to pull-request/<number>, and CI runs there.This skill is about PR hygiene, not code execution; verify the contributor mechanics:
git log --pretty=full origin/develop..HEAD | grep -c "Signed-off-by:" # every commit signed
git diff --name-only origin/develop..HEAD # only intended files
git status --porcelain # no stray artifacts
Expected: the sign-off count equals your commit count, the changed-file list contains only files relevant to this change, and the working tree is clean.
git commit -s; fix existing ones with
git rebase --signoff origin/develop before pushing.aiq-release-qa; "ran tests" is not evidence.deploy/.env values. Resolve secrets at runtime; never
paste them into the PR./ok to test.aiq-release-qaaiq-add-toolaiq-add-data-sourceUse when composing, adapting, or validating an AI-Q workflow YAML under configs/ — selecting a shipped profile, enabling tools and data_source_registry sources, wiring chat or direct data-science workflows, configuring NeMo Relay and general.telemetry observability plus general.front_end aiq_api settings, and pre-flighting cross-references before deploy or serve. Hand off deploy to aiq-deploy, live research to aiq-research, prompt/model edits to aiq-customize-prompts-models, and new source code to aiq-add-tool or aiq-add-data-source.
Use this skill to turn researched or computed numeric data into source-grounded charts. It has two delivery modes and picks one from the tools available to you. When an `execute` tool (sandbox) is available, render a PNG chart plus its CSV with Python/matplotlib and embed it as a durable `artifact://` reference. When there is no sandbox, emit the chart as an inline fenced `chart` (or `chart-carousel`) JSON spec that the web UI renders deterministically, followed by a portable Markdown table. Triggers: "chart", "plot", "graph", "bar chart", "line chart", "visualize", "trend over time", "compare visually", "figure", "ranking", "top-N", "distribution". Outputs: either a PNG chart artifact (plus CSV and manifest) or an inline chart spec.
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.