skill-creator

A guide for creating new skills for AI coding agents such as Claude Code, Codex, and Cursor. These skills are instruction packages that teach an agent how to handle a specific kind of work.

In plain words
What is it for?
Use it to create a new agent capability, including its instructions, optional helper scripts or resources, and copies for each supported agent.
Why use it?
It gives the required file layout and workflow so a skill can be shared consistently across supported coding agents.

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/stacklok/toolhive-studio/skill-creator
Any agent
npx skills add stacklok/toolhive-studio --skill skill-creator
Clone the repo
git clone --depth 1 https://github.com/stacklok/toolhive-studio

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 712 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 $0.00040 $0.00712
Opus 5 $0.00020 $0.00356
Sonnet 5 $0.00008 $0.00142
Haiku 4.5 $0.00004 $0.00071

Measured 2d ago against content hash 38ee7f6d21d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-creator 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.

.claude/skills/skill-creator/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Creator

Create AI agent skills that work across Claude Code, Codex, and Cursor.

Workflow

  1. Claude is canonical - Always create/edit in .claude/skills/<name>/ first
  2. Replicate with CLI - Copy to .codex/skills/ and .cursor/skills/ using cp -r
  3. Format differences - Use sed only if agent-specific tweaks are needed (rare)

Directory Structure

.claude/skills/<skill-name>/
├── SKILL.md          # Required - instructions + metadata
├── references/       # Optional - supporting documentation
├── scripts/          # Optional - executable helpers
└── assets/           # Optional - templates, resources

.codex/skills/<skill-name>/   # Copy of Claude's
.cursor/skills/<skill-name>/  # Copy of Claude's

SKILL.md Format

---
name: skill-name # Required: lowercase, hyphens, max 64 chars
description: What it does... # Required: triggers auto-selection by agent
allowed-tools: Read, Grep, Bash # Optional: Claude-specific (ignored by others)
model: claude-opus-4-5-20251101 # Optional: Claude-specific (ignored by others)
---
# Skill Title

Instructions in markdown...

Required Fields

  • name: Lowercase with hyphens, must match directory name
  • description: Explains what the skill does and when to use it. Include keywords users would say to help the agent auto-select this skill.

Optional Fields (Claude-specific, ignored by other agents)

  • allowed-tools: Tools the agent can use without asking permission
  • model: Override the model for this skill
  • context: fork: Run in isolated subagent context

Creating a New Skill

  1. Ask the user what the skill should do
  2. Choose a descriptive name (lowercase, hyphens)
  3. Create the Claude skill:
    mkdir -p .claude/skills/<name>
    
  4. Write .claude/skills/<name>/SKILL.md with proper frontmatter
  5. Replicate to other agents:
    cp -r .claude/skills/<name> .codex/skills/
    cp -r .claude/skills/<name> .cursor/skills/
    

Read the full file on GitHub · 84 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 · 84 lines · 40 tokens per session scan A 38ee7f6d21d8

Subscribe to this mod's changes

skill-creator is a skill published in the GitHub repository stacklok/toolhive-studio (163 stars, last pushed 4d ago), licensed Apache-2.0. It adds 40 tokens to every session and 712 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 2026-08-30.