Official agent skill

ONNX Runtime Release Notes

by microsoft in microsoft/onnxruntime

Drafts ONNX Runtime release notes from commit history and contributor metadata using named presets for the full runtime or a scoped component.

OfficialMITAuto-check passedDevelopment

Install ONNX Runtime Release Notes

skills CLI
$ npx skills add microsoft/onnxruntime --skill ort-release-notes -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install microsoft/onnxruntime ort-release-notes --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/microsoft/onnxruntime.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/ort-release-notes .claude/skills/ort-release-notes && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ort-release-notes
GitHub stars
22k
Token cost
~1.6k tokens
SKILL.md length
720 words
Files
2
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Drafts ONNX Runtime release notes from commit history and contributor metadata using named presets for the full runtime or a scoped component.

  • Works in 3 steps: preset: release profile name (for… → base_ref: previous release tag → target_ref: release commit/tag/branch tip
  • Drafting release notes for a full ONNX Runtime release
  • SKILL.md covers When To Use, Required Inputs, Presets and Workflow, plus 2 more sections
  • Calls python and git

What it does

You give a preset name (such as ort, webgpu-plugin-ep or cuda-plugin-ep), the previous release tag and the target ref, and optionally a version or output directory. The agent loads the preset from presets.json, which names the product for readers, the version file and an optional file of git pathspecs; a preset with a paths file runs in scoped mode and otherwise the full mode runs. The preset key itself must not appear in published text.

Version resolves from an explicit input or the preset's version file, and the output directory from an explicit input or a shared pattern built from the preset and version. If contributor artifacts are missing, the agent generates them with tools/python/compile_contributors.py, then writes highlights with PR links and a human-only acknowledgment list into the draft.

When your agent uses it

  • Drafting release notes for a full ONNX Runtime release
  • Drafting notes for a scoped release such as the CUDA or WebGPU plugin execution provider
  • Adding PR links to highlight bullets
  • Building a human-only contributor acknowledgment list

Example prompts

  • “Draft release notes with the cuda-plugin-ep preset between the previous release tag and the release branch tip.”
  • “Use the ort preset to write the full ONNX Runtime release notes.”
  • “Compile the contributor acknowledgments for this release draft, humans only.”

Requirements

  • A checkout of the onnxruntime repository with release tags
  • Python to run tools/python/compile_contributors.py

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. preset: release profile name (for example, ort, webgpu-plugin-ep, cuda-plugin-ep)
  2. base_ref: previous release tag
  3. target_ref: release commit/tag/branch tip

What it can do on your machine

Read from SKILL.md and the folder at commit a571b72. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

ONNX Runtime Release Notes loads about 1.6k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 720 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from microsoft/onnxruntime at commit a571b72, republished under its MIT licence (© microsoft). 720 words, ~1,610 tokens.

Download SKILL.mdSave it as .claude/skills/ort-release-notes/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
ort-release-notes
description
Draft ONNX Runtime release notes using preset configurations for full ORT or scoped component releases. Use when generating highlights with PR links, compiling human contributor acknowledgments from compile_contributors.py output, and applying preset path filtering.
argument-hint
preset base_ref target_ref [version] [output_dir]

ONNX Runtime Release Notes

Use this skill to produce a consistent release-note draft from commit history and contributor metadata.

When To Use

Use this skill when you need to:

  • Draft release notes for a full ONNX Runtime release
  • Draft release notes for a scoped component (e.g., in-tree plugin EP) release
  • Select a release profile by preset name instead of manually supplying path/version files
  • Add PR links to highlight bullets
  • Build a human-only contributor acknowledgment list from contributor metadata

Required Inputs

Collect these inputs from the user or infer from context:

  1. preset: release profile name (for example, ort, webgpu-plugin-ep, cuda-plugin-ep)
  2. base_ref: previous release tag
  3. target_ref: release commit/tag/branch tip

Optional inputs:

  • version override
  • output_dir override

Presets

Read preset definitions from presets.json.

The config defines shared output defaults:

  1. outputDirPattern
  2. draftFileName

Each preset defines:

  1. displayName: reader-facing product or component name
  2. versionFile
  3. pathsFile (nullable): file of git pathspecs to filter to, one per line. Use :(top) to anchor an entry at repo root.

Example presets:

  1. ort (full ONNX Runtime)
  2. webgpu-plugin-ep (scoped WebGPU Plugin EP)
  3. cuda-plugin-ep (scoped CUDA Plugin EP)
CUDA Plugin EP Scope

The cuda-plugin-ep preset uses the pathspecs in plugin-ep-cuda/paths.txt to scope release-note changes.

Workflow

  1. Determine release mode.
    • Select preset and load configuration from presets.json.
    • Use the preset's displayName whenever the release-note content names the product or component. The preset key is internal and must not appear in published content.
    • If preset has pathsFile, run in scoped mode. Otherwise run full mode.
  2. Resolve version, in this order:
    1. explicit version input
    2. value from preset versionFile
  3. Resolve output directory, referred to as resolved_output_dir after this step. The output directory contains contributor artifacts and the release notes draft. Resolve it in this order:
    1. explicit output_dir input
    2. shared outputDirPattern rendered with preset name and resolved version
  4. Gather metadata.
    • If the output directory is missing or lacks contributor artifacts, generate them with tools/python/compile_contributors.py.
    • Generation can take a while because it scans commit history and fetches PR metadata.
    • Use --paths-file only when preset has a pathsFile.
    • If existing contributor artifacts are reused, verify resolved_output_dir/logs.txt matches base/target before trusting them.
  5. Read resolved_output_dir/detail.csv as the primary source for PR numbers, titles, authors, target commits, and cherry-pick mapping.
    • Use resolved_output_dir/logs.txt for contributor summary context and base/target verification.
    • Use git log only as a fallback sanity check when artifacts are present but incomplete or suspect.
    • Check PRs with unexpectedly large author lists for rebased history that imported unrelated commits. Replace those authors with the actual PR author or authors before building contributor acknowledgments; do not credit authors solely because they authored an unrelated imported commit. For example, PR #28299, the rebased history contains unrelated commits and co-author metadata.
  6. Build highlight categories.
    • Full ORT example categories: performance, model/operator support, execution providers, API/languages, reliability/security, build/packaging/tooling, docs/dev workflow.
    • Scoped mode: narrow categories to the component domain.
  7. Draft markdown.
    • Write the release-note draft to resolved_output_dir/<draftFileName>.
    • Contents:
      • Intro sentence
      • ## Highlights
      • Inline PR links on every highlight bullet
      • ## Contributors
      • Optional scope note for scoped-component releases
        • Use the preset's reader-facing displayName, not the internal preset key.
        • Describe the scope in reader-facing terms, such as "commits affecting WebGPU Plugin EP code and packaging."
      • AI disclaimer if AI drafted
    • Do not mention presets, pathsFile, configuration files, or other release-note-generation implementation details in the release-note content.
    • Do not refer to the release notes as a "draft" in their content. "Draft" is only an internal workflow and file-naming concept.
  8. Build contributors section.
    • Start from detail.csv output
    • Include humans only
    • Exclude bots/agents (for example: github-actions[bot], app/copilot-swe-agent, claude)
    • Sort alphabetically
  9. Validate draft quality.
    • Every highlight bullet has at least one PR link
    • PRs are traceable to metadata or git history
    • Contributor list is human-only and alphabetical
    • Scope is correct for full vs component release
Show full SKILL.md (89 more words)Show less

PowerShell Command Patterns

compile_contributors.py

Full ORT metadata:

powershell
python .\tools\python\compile_contributors.py \
  --base <previous_tag> \
  --target <target_ref> \
  --dir <resolved_output_dir>

Scoped metadata:

powershell
python .\tools\python\compile_contributors.py \
   --base <previous_tag> \
   --target <target_ref> \
   --dir <resolved_output_dir> \
   --paths-file <paths_file>

Style and Policy

Default policy unless release owners override:

  1. Treat the range as changes since the previous release.
  2. Keep PR links inline with highlight claims.
  3. Keep contributor acknowledgments human-only and best effort.
  4. Include an AI disclaimer when highlights are AI drafted.
  5. Use GitHub Releases pages as preferred style references. E.g., ORT 1.28 release page.
  6. Prefer preset-driven configuration over ad-hoc path/version arguments.
  7. Use a single output_dir for contributor artifacts, logs, and the release-note draft.

© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .github/skills/ort-release-notes of microsoft/onnxruntime.

  • SKILL.md
  • presets.json

Open the folder on GitHubat commit a571b72

Compare with similar skills

ONNX Runtime Release Notes next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

ONNX Runtime Release Notes compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
ONNX Runtime Release Notes this skillmicrosoft/onnxruntime22k—~1.6kAutomated safety check: PassMIT
Embedded AI Deploymentmatlab/agent-skills-playground1811 repos~3.4kAutomated safety check: PassCustom licence
Quark Onnx Installamd/Quark181—~3.2kAutomated safety check: PassMIT
Quark Onnx Model Intakeamd/Quark181—~4.3kAutomated safety check: PassMIT
Rtvi Cv Customize ModelNVIDIA/skills3.5k—~4.5kAutomated safety check: NotesApache-2.0
Matlab Deploy Embedded AImajiayu000/claude-skill-registry6661 repos~4.6kAutomated safety check: PassMIT

Similar skills

  • Embedded AI Deployment

    matlab/agent-skills-playground

    Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder).

    181 GitHub starsUsed in 1 repo~3.4k tokens
    AI & LLM EngineeringAuto-check passed
  • Install or verify the correct ONNX Runtime build (and the onnx package) for a user's accelerator backend before Quark's ONNX-to-ONNX flow.

    181 GitHub stars~3.2k tokensUpdated 10 days ago
    AI & LLM EngineeringAuto-check passed
  • Inspect a target ONNX model and prepare metadata for Quark ONNX PTQ planning.

    181 GitHub stars~4.3k tokensUpdated 10 days ago
    AI & LLM EngineeringAuto-check passed
  • Official

    How to swap the DeepStream CV detection model in the VSS Alerts Blueprint verification (2dcv) mode - covers ONNX export, custom bbox parsers, compose mount gotchas, nvinfer config, runtime TRT…

    3.5k GitHub stars~4.5k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Matlab Deploy Embedded AI

    majiayu000/claude-skill-registry

    Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder).

    666 GitHub starsUsed in 1 repo~4.6k tokens
    AI & LLM EngineeringAuto-check passed
  • Simple English

    moeru-ai/airi

    Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop.

    50k GitHub starsUsed in 2 repos~4.6k tokens
    DevelopmentAuto-check passed

More from microsoft/onnxruntime

All 14 skills in this repo
  • Official

    Finds and fixes out-of-range output writes in ONNX Runtime operator shape-inference functions where a getNumOutputs guard admits too few outputs.

    22k GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • Official

    Explains why editing CUTLASS fused-MHA headers in ONNX Runtime can leave stale CUDA kernels after an incremental build, and how to force and verify a real rebuild.

    22k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • ONNX Runtime Source Build

    microsoft/onnxruntime

    Official

    Builds ONNX Runtime from source with its build scripts, explaining the update, build and test phases, key flags and where the build output lands.

    22k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • ONNX Runtime CI Management

    microsoft/onnxruntime

    Official

    Triggers, re-runs and unblocks the CI checks on an ONNX Runtime pull request, after diagnosing whether a failure is transient or needs a code change.

    22k GitHub stars~4.1k tokensUpdated today
    Auto-check passed
  • ONNX Runtime Test Runner

    microsoft/onnxruntime

    Official

    Runs and debugs ONNX Runtime tests: Google Test executables for C++ and unittest or pytest for Python, with filters and build-directory guidance.

    22k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Official

    Runs the ONNX Runtime transformers Python tests against a GPU wheel and proves the cuDNN flash attention path was used rather than a silent fallback.

    22k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about ONNX Runtime Release Notes

What does ONNX Runtime Release Notes do?

Drafts ONNX Runtime release notes from commit history and contributor metadata using named presets for the full runtime or a scoped component. You give a preset name (such as ort, webgpu-plugin-ep or cuda-plugin-ep), the previous release tag and the target ref, and optionally a version or output directory.json, which names the product for readers, the version file and an optional file of git pathspecs; a preset with a paths file runs in scoped mode and otherwise the full mode runs.

When should I use ONNX Runtime Release Notes?

ONNX Runtime Release Notes fits situations like: drafting release notes for a full ONNX Runtime release; drafting notes for a scoped release such as the CUDA or WebGPU plugin execution provider; adding PR links to highlight bullets; building a human-only contributor acknowledgment list.

How do I install ONNX Runtime Release Notes in Claude Code?

Run `npx skills add microsoft/onnxruntime --skill ort-release-notes -a claude-code`. Or copy the skill folder (.github/skills/ort-release-notes in microsoft/onnxruntime) into .claude/skills/ort-release-notes in your project. Claude Code loads it when a task matches its description.

How do I install ONNX Runtime Release Notes in Codex?

Run `npx skills add microsoft/onnxruntime --skill ort-release-notes -a codex`. Or copy the skill folder (.github/skills/ort-release-notes in microsoft/onnxruntime) into .agents/skills/ort-release-notes in your project. Codex loads it when a task matches its description.

Can I use ONNX Runtime Release Notes in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microsoft/onnxruntime --skill ort-release-notes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ort-release-notes, .gemini/skills/ort-release-notes, .github/skills/ort-release-notes and .opencode/skills/ort-release-notes in your project.

What does ONNX Runtime Release Notes need to run?

Going by SKILL.md and its folder, ONNX Runtime Release Notes needs the command-line tools its instructions call (python and git). Our summary lists: A checkout of the onnxruntime repository with release tags; Python to run tools/python/compile_contributors.py.

Does ONNX Runtime Release Notes access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is ONNX Runtime Release Notes safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does ONNX Runtime Release Notes use?

ONNX Runtime Release Notes is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does ONNX Runtime Release Notes use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to ONNX Runtime Release Notes?

Skills that share tags, products or a category with ONNX Runtime Release Notes: Embedded AI Deployment (matlab/agent-skills-playground, 181 stars), Quark Onnx Install (amd/Quark, 181 stars), Quark Onnx Model Intake (amd/Quark, 181 stars) and Rtvi Cv Customize Model (NVIDIA/skills, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains ONNX Runtime Release Notes?

microsoft (a GitHub organization, an official publisher) maintains it in microsoft/onnxruntime, which has 22,035 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 8, 2026.

Source: microsoft/onnxruntime on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.