Nuget Trusted Publishing

What it does

When your agent uses it

• Keyless NuGet publish
• Trusted-publishing policy changes
• Release authentication
• Diagnosing NuGet trusted-publishing failures

Example prompts

• “/nuget-trusted-publishing”

Workflow steps

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

1. 1.github/workflows/release.yml and release-recovery-missing-nuget.yml.
2. 2eng/package-catalog.json for the exact five governed PackageIds.
3. 3eng/publish-package-set.ps1 for publication/idempotency behavior.
4. 4eng/validate-release-artifacts.ps1 and consumer-smoke validation.
5. 5The release environment and the exact nuget.org trusted-publishing policy values when external configuration is involved.

What it can do on your machine

Read from SKILL.md and the folder at commit 4f5a39f. 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

  No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

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

• Network

  Links to these hosts (documentation or services it may open):

  • learn.microsoft.com

  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

Nuget Trusted Publishing loads about 1.3k tokens when it runs, and up to ~2.2k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 483 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~88

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.2k

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

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 rodri-oliveira-dev/Dapper-FluentMap at commit 4f5a39f, republished under its MIT licence (© rodri-oliveira-dev). 483 words, ~1,254 tokens.

name

nuget-trusted-publishing

description

Review, maintain, or set up NuGet trusted publishing (OIDC) for GitHub Actions. USE FOR: NuGet OIDC, keyless NuGet publish, NuGet/login, trusted-publishing policy changes, release authentication, and diagnosing NuGet trusted-publishing failures. DO NOT USE FOR: private feeds that do not support nuget.org trusted publishing.

license

MIT

permissions:
  contents: read
  id-token: write

- name: Exchange GitHub OIDC token for temporary NuGet API key
  id: nuget-login
  uses: NuGet/login@<approved-pinned-sha>
  with:
    user: "${{ vars.NUGET_USER }}"

© rodri-oliveira-dev, 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 2 other files (references) in .agents/skills/nuget-trusted-publishing of rodri-oliveira-dev/Dapper-FluentMap.

• SKILL.md
• references/package-types.md
• references/publish-workflow.md

Open the folder on GitHubat commit 4f5a39f