create-skill

A reusable workflow for creating or revising Shellby MCP skills. Shellby MCP is a system that lets an agent discover and load shared workflows from a workspace.

In plain words
What is it for?
Creating skill folders, writing their instructions, adding scripts or reference files when useful, and updating an existing skill catalog.
Why use it?
It provides rules for where skills live, how they are named, and what a skill file must contain, so reusable workflows can be found and used consistently.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/serbyte-development/shellby-mcp/create-skill
Any agent
npx skills add serbyte-development/shellby-mcp --skill create-skill
Clone the repo
git clone --depth 1 https://github.com/serbyte-development/shellby-mcp

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 588 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.00588
Opus 5 $0.00023 $0.00294
Sonnet 5 $0.00009 $0.00118
Haiku 4.5 $0.00005 $0.00059

Measured 2d ago against content hash 2ff901832a67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/create-skill/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Skill

Create small reusable workflows that Shellby MCP can discover from the configured workspace.

Workspace

  • Treat the configured Shellby workspace as <workspace>. Determine it from the MCP instructions or current shell context. Never assume a username or absolute path.
  • Store MCP skills at <workspace>/skills/<name>/SKILL.md.
  • Read <workspace>/AGENTS.md and inspect existing skills before changing the catalog.
  • Use lowercase hyphenated skill names. Keep the directory name and frontmatter name identical.

Skill structure

Minimum:

skills/<name>/
└── SKILL.md

Optional resources when they materially improve repeated use:

skills/<name>/
├── SKILL.md
├── scripts/
├── references/
└── assets/
  • scripts/: deterministic or repeatedly reused operations.
  • references/: detailed material loaded only when needed.
  • assets/: templates or files consumed by the workflow.

Keep the important workflow in SKILL.md. Avoid extra documentation unless the skill needs it as working material.

Frontmatter

Use:

---
name: example-skill
description: What the skill does and concrete requests that should trigger it.
---

skill_list exposes the directory name and frontmatter description, so make the description specific enough for an agent to know when to load it.

Workflow

  1. Inspect existing skills for overlap and conventions.
  2. Define the requests that should trigger the skill.
  3. Capture only reusable instructions, constraints, domain knowledge, scripts, references, and assets needed for those requests.
  4. Create or update <workspace>/skills/<name>/SKILL.md.
  5. Use skill_list to verify discovery.
  6. Use skill_load to verify the complete instructions load correctly.
  7. Exercise complex skills on a realistic request when useful.

Portability

  • Prefer paths relative to <workspace> or the skill directory.
  • Do not assume Codex, Claude, a particular username, or another agent runtime is installed.
  • If the user explicitly wants one skill shared with another runtime, inspect that runtime's supported skill location and symlink or share a canonical directory only when both runtimes can consume the same files correctly.
  • Avoid runtime-specific tool names unless the skill is intentionally specific to that runtime.

Read the full file on GitHub · 82 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 82 lines · 46 tokens per session scan A 2ff901832a67

Subscribe to this mod's changes

create-skill is a skill published in the GitHub repository serbyte-development/shellby-mcp (10 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 588 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

codexless-release-supervisor

Prepare, validate, and publish Codexless preview/hotfix releases from the canonical household source, including acceptance anti-omission gates, candidate provenance/parity, manifest/build identity, native Windows/macOS fresh-install acceptance from clean public source, safe Git integration, GitHub prerelease…

liyana31811/Codexless · 87 tokens

codexless-browser-repair

Diagnose and temporarily repair Codexless Browser compatibility after a Codex, Chrome Skill, or Browser runtime update when Codexless Browser stopped working. Use for current-version Codexless Browser compatibility drift, not ordinary website bugs, general Browser operation, Codexless install/update work, or long-term…

liyana31811/Codexless · 70 tokens

codex-with-chatgpt

Use ChatGPT (web) as the planning and review brain for Codex coding sessions, while Codex keeps full execution ownership. Use when the user says "使用 Codex with ChatGPT ..." / "Set up Codex with ChatGPT" / "用 ChatGPT 规划", when they ask to connect ChatGPT to the current workspace, disconnect it, or run a task through…

XiaoDuoYa/codex-with-chatgpt · 90 tokens

add-widget

Add a new widget (React UI + MCP tool) to this template. Use when asked to "add a widget", "add a new tool with UI", "create a new widget", "scaffold a widget", or "build a new MCP App feature".

pomerium/mcp-app-typescript-template · 56 tokens

create-mcp-tool

Add a plain (text-only) or UI-enhanced MCP tool to this template's server. Use when asked to "add a tool", "add an MCP tool", "create a new tool", "add a server-side tool without a widget", "add a tool with a UI", "add a tool with a widget", or "create a tool and a widget".

pomerium/mcp-app-typescript-template · 80 tokens

threebrowser-studio-mcp

Author, inspect, render, validate, animate, and save Three.js WebGPU projects in the native ThreeBrowser Studio through its real threestudio MCP tools. Use whenever Codex is asked to build or edit a ThreeBrowser Studio scene, material, Blender-style shader or texture graph, animation, lighting setup, camera, or…

SamG-Coder/ThreeBrowserStudio · 122 tokens