AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Oo Publish Skill

skill-oomol-lab-oo-cli-oo-publish-skill · by oomol-lab

Publish, release, upload, or submit an existing AI agent skill directory with SKILL.md to the OOMOL registry by running oo skills publish, or generate a share prompt for a published skill by running oo skills share, including temporary shares for private packages. Use when the user asks to publish a skill, share a published skill, make a skill available in the OOMOL skill catalog, release a regis…

No reviews yet
0 installs
19 views
0.0% view→install

Install

$ agentstack add skill-oomol-lab-oo-cli-oo-publish-skill

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-oomol-lab-oo-cli-oo-publish-skill)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
23d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Oo Publish Skill? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

oo Publish Skill

Use this skill when the user wants to publish an existing agent skill to the OOMOL registry or skill catalog. The source can be any valid agent skill directory with a SKILL.md; it does not need to be an oo-specific skill.

Workflow

Share a published skill

If the user asks to share a published skill, run:

oo --lang zh skills share  -y
oo --lang en skills share  -y

Use the skill id from the current context when the user has just created, published, or used a specific skill. If no likely skill id is available, ask the user which skill or package to share. oo skills share will confirm the resolved id and package, then print the copyable share prompt. Public packages are shared directly. Private packages create a temporary share id and the prompt must use #. Private package shares support optional limits: --days sets the share duration, defaults to 7, and cannot exceed 7; --downloads limits install count; omitting --downloads leaves installs unlimited. Match the user's language when generating the prompt: use oo --lang zh skills share -y for Chinese users and oo --lang en skills share -y for English users. That prompt is meant for recipients to follow a language-specific general install preparation guide before running the final install command. It should include the package name, skill name when applicable, Hub URL, the general install preparation URL, and the exact oo skills install ... command. In the final response, put the complete recipient-facing share prompt in one copyable text code block. Do not use nested fenced code blocks inside it. Do not split the hub URL, guide URL, or install command outside the block.

1. Identify the publish source

Ask for the missing skill id or skill directory path only when needed:

  • skill id or path to a skill directory

Publish accepts a concrete path:

oo skills publish 

If the user gives only a skill id, oo skills locate --agent can help resolve the local path. Use it when it is helpful, but do not force an extra locate step when the path is already clear from context.

The publish command performs its own environment, authentication, and account checks, so run it directly.

For first-time packages in non-interactive agent sessions, choose visibility before publishing and pass --visibility private or --visibility public. Use --visibility public when the user asks to publish to the public catalog or otherwise clearly wants a public package. Use --visibility private only when the user asks for a private package. If the user's intended visibility is unclear, ask before publishing. Existing packages can omit --visibility when the current registry visibility should be preserved.

Do not ask whether to publish to the current account. oo skills publish resolves the account and asks any necessary ownership questions itself.

2. Publish through oo

Run the publish command directly:

oo skills publish ./my-skill --visibility public
oo skills publish /path/to/my-skill/SKILL.md --visibility private
oo skills publish ./already-published-skill

If this shared skill file is running in another supported host, replace `` with that host id from the supported list.

If the command prompts about publishing a registry-installed skill under the active account or overwriting an existing remote package, let that prompt drive the next user confirmation. Do not ask those questions in advance.

Do not package manually, do not use npm publish, and do not copy files into an arbitrary fallback directory.

3. Report the result

Report the published package name, version, visibility, and hub URL from the command output. Also mention any metadata writeback that occurred. If publish fails, do not retry blindly; summarize the failing command, the user-facing error, and the smallest next fix. If the failure says the self-hosted connector only supports connector commands, or the JSON error code is not_authenticated in self-hosted connector mode, publishing requires an OOMOL account: ask the user to run oo auth login, then stop.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.