New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

MCP Authoring

by OtoDock in OtoDock/oto-dock

Author an MCP package for OtoDock: the manifest.json fields and their rules, the package layout, what the installer refuses or drops, credentials and instances, skills bundled with an MCP, and the…

Custom licenceAuto-check: notesAgent Workflows

Install MCP Authoring

skills CLI
$ npx skills add OtoDock/oto-dock --skill mcp-authoring -a claude-code

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

GitHub CLI
$ gh skill install OtoDock/oto-dock mcp-authoring --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/OtoDock/oto-dock.git skills-src && mkdir -p .claude/skills && cp -r skills-src/mcps/custom/mcps-mcp/skills/mcp-authoring .claude/skills/mcp-authoring && 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
mcp-authoring
GitHub stars
190
Token cost
~1.3k tokens
SKILL.md length
652 words
Files
4 (incl. references)
Skills in repo
19
Repo updated
First seen
Licence
Custom licence

At a glance

Author an MCP package for OtoDock: the manifest.json fields and their rules, the package layout, what the installer refuses or drops, credentials and instances, skills bundled with an MCP, and the…

  • Works in 4 steps: Pick the source. Wrap an existing… → Write the folder in your workspace:… → Check it: call validate_mcp_package with… → …
  • Asked to wrap an MCP server (npm
  • SKILL.md covers The flow, Rules the installer enforces, Writing the server side and Updating a shipped package
  • Needs PROXY_API_KEY

What it does

MCP Authoring is an agent skill from OtoDock/oto-dock. Author an MCP package for OtoDock: the manifest.json fields and their rules, the package layout, what the installer refuses or drops, credentials and instances, skills bundled with an MCP, and the hand-over to an admin. Use when asked to wrap an MCP server (npm, PyPI, a git repository, a container image or a vendor-hosted endpoint, including one that signs people in itself) as an installable OtoDock MCP, to check a package with validatemcppackage, or to prepare a catalog entry.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/examples.md`, `references/manifest.md` and `references/package-rules.md`).

It sits in Agent Workflows, covering MCP servers and Containers. It works with Model Context Protocol, Git, npm and Python. The repository describes itself as: The agentic company OS. The brains of your company, built on Claude Code and Codex, working on your Anthropic and OpenAI subscriptions.

When your agent uses it

  • Asked to wrap an MCP server (npm
  • A git repository
  • A container image
  • A vendor-hosted endpoint

Example prompts

  • “/mcp-authoring”

Requirements

  • Python 3
  • Docker
  • A credential in PROXY_API_KEY

Workflow steps

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

  1. Pick the source. Wrap an existing server: npm: (Node),
  2. Write the folder in your workspace: manifest.json, README.md,
  3. Check it: call validate_mcp_package with the folder's path (a
  4. Hand it over: zip the folder (manifest.json at the zip root or one

What it can do on your machine

Read from SKILL.md and the folder at commit 5308f5a. 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.

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

  • Network

    No URLs in SKILL.md.

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • PROXY_API_KEY

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

Context cost

MCP Authoring loads about 1.3k tokens when it runs, and up to ~7.9k if it reads all its reference files. Until then it costs about 125 tokens; SKILL.md has 652 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~125
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
~7.9k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:38
    `.git` or a `.env`) and give the zip to an admin. The admin installs it
  • NoteMentions a .env fileSKILL.md:46
    - No `.env` anywhere, no `.git`, no `node_modules`, no `venv`: the archive is

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 652 words (~1,309 tokens).

“An OtoDock MCP is a folder with a manifest.json at its root. The manifest says what to run, how to install it, what credentials it needs and which skills ride with it; the platform does the rest (install, sandbox, env…”

— opening of SKILL.md by OtoDock, Custom licence
name
mcp-authoring

Read the full SKILL.md on GitHub

Files

SKILL.md and 3 other files (references) in mcps/custom/mcps-mcp/skills/mcp-authoring of OtoDock/oto-dock.

  • SKILL.md
  • references/examples.md
  • references/manifest.md
  • references/package-rules.md

Open the folder on GitHubat commit 5308f5a

Compare with similar skills

MCP Authoring 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.

MCP Authoring compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
MCP Authoring this skillOtoDock/oto-dock190—~1.3kAutomated safety check: NotesCustom licence
Devcontainer Devstacklok/toolhive-studio170—~3.8kAutomated safety check: NotesApache-2.0
Project Releaseswimmwatch/cloakbrowser-mcp164—~1.9kAutomated safety check: PassMIT
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
Unraiddinglebear-ai/unraid135—~5.4kAutomated safety check: NotesMIT
Pluggedin Stack OpsVeriTeknik/pluggedin-app103—~1.3kAutomated safety check: NotesMIT

Similar skills

  • Devcontainer Dev

    stacklok/toolhive-studio

    Spin up and interact with ToolHive Studio's containerized dev environment (Xvfb + noVNC + DinD).

    170 GitHub stars~3.8k tokensUpdated today
    Agent WorkflowsAuto-check: notes

  • Project Release

    swimmwatch/cloakbrowser-mcp

    Prepare, publish, verify, or recover a cloakbrowser-mcp release only when the user explicitly requests release work.

    164 GitHub stars~1.9k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Unraid

    dinglebear-ai/unraid

    This skill should be used when the user mentions Unraid, asks to check server health, monitor array or disk status, list or restart Docker containers, start or stop VMs, read system logs, check…

    135 GitHub stars~5.4k tokensUpdated 5 days ago
    DevOps & CloudAuto-check: notes

  • Pluggedin Stack Ops

    VeriTeknik/pluggedin-app

    A skill your agent uses when deploying, restarting, verifying or rolling back the containerised plugged.in production stack, when the site returns 404 or 5xx after a deploy or git operation, or when…

    103 GitHub stars~1.3k tokensUpdated 3 days ago
    DevOps & CloudAuto-check: notes

  • Context7 MCP Skill

    holon-run/uxc

    Query up-to-date library documentation and code examples using Context7 MCP.

    116 GitHub stars~564 tokensUpdated 24 days ago
    Agent WorkflowsAuto-check passed

More from OtoDock/oto-dock

All 19 skills in this repo

  • Agent Creation

    OtoDock/oto-dock

    How to author an agent template folder and install it as a new agent - folder layout, manifest fields, persona rules, shipped apps and checks, and the scaffold-validate-create flow.

    190 GitHub stars~4.1k tokensUpdated 2 days ago
    Auto-check: notes

  • Checks

    OtoDock/oto-dock

    How checks work on OtoDock — named units that judge an agent's work at the end of a turn (schema, script, handler and judge kinds), conditions on what the turn changed, rounds, where a check lives…

    190 GitHub stars~2.2k tokensUpdated 2 days ago
    Auto-check passed

  • Image Search Usage

    OtoDock/oto-dock

    Search the web for images with filters and download them. An agent skill from OtoDock/oto-dock.

    190 GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed

  • Subtitle Burning

    OtoDock/oto-dock

    Transcribe audio and burn styled subtitles into videos. An agent skill from OtoDock/oto-dock.

    190 GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed

  • Triggers Guide

    OtoDock/oto-dock

    Reference for the triggers-mcp tools — the trigger↔task and trigger↔notification patterns with full call shapes, vendor-subscribed (OAuth) triggers and eventfilter rules, payload placeholders…

    190 GitHub stars~3k tokensUpdated 2 days ago
    Auto-check passed

  • Otodock Platform

    OtoDock/oto-dock

    How the OtoDock platform itself works and where every setting lives — installing and first-run setup, agents, AI engines, sessions, apps and sharing, checks, departments and delegation, shared…

    190 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about MCP Authoring

What does MCP Authoring do?

Author an MCP package for OtoDock: the manifest.json fields and their rules, the package layout, what the installer refuses or drops, credentials and instances, skills bundled with an MCP, and the…. MCP Authoring is an agent skill from OtoDock/oto-dock.json fields and their rules, the package layout, what the installer refuses or drops, credentials and instances, skills bundled with an MCP, and the hand-over to an admin.

When should I use MCP Authoring?

MCP Authoring fits situations like: asked to wrap an MCP server (npm; A git repository; A container image; A vendor-hosted endpoint.

How do I install MCP Authoring in Claude Code?

Run `npx skills add OtoDock/oto-dock --skill mcp-authoring -a claude-code`. Or copy the skill folder (mcps/custom/mcps-mcp/skills/mcp-authoring in OtoDock/oto-dock) into .claude/skills/mcp-authoring in your project. Claude Code loads it when a task matches its description.

How do I install MCP Authoring in Codex?

Run `npx skills add OtoDock/oto-dock --skill mcp-authoring -a codex`. Or copy the skill folder (mcps/custom/mcps-mcp/skills/mcp-authoring in OtoDock/oto-dock) into .agents/skills/mcp-authoring in your project. Codex loads it when a task matches its description.

Can I use MCP Authoring 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 OtoDock/oto-dock --skill mcp-authoring -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcp-authoring, .gemini/skills/mcp-authoring, .github/skills/mcp-authoring and .opencode/skills/mcp-authoring in your project.

What does MCP Authoring need to run?

Going by SKILL.md and its folder, MCP Authoring needs credentials named PROXY_API_KEY. Our summary lists: Python 3; Docker; A credential in PROXY_API_KEY.

Does MCP Authoring access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is MCP Authoring safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does MCP Authoring use?

MCP Authoring has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does MCP Authoring use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.6k tokens, read only when the agent opens those files.

What are the alternatives to MCP Authoring?

Skills that share tags, products or a category with MCP Authoring: Devcontainer Dev (stacklok/toolhive-studio, 170 stars), Project Release (swimmwatch/cloakbrowser-mcp, 164 stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars) and Unraid (dinglebear-ai/unraid, 135 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains MCP Authoring?

OtoDock (a GitHub organization) maintains it in OtoDock/oto-dock, which has 190 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 7, 2026.

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