skill-creator

skill-creator is a skill for Claude Code, Codex from tallesborges/zdx. It costs 173 tokens per session (2,433 once invoked), scanned A, original, MIT.

A guide for creating or updating a skill, a reusable set of instructions that teaches an agent when and how to handle a type of task.

In plain words
What is it for?
It is for authoring, editing, reviewing, and packaging SKILL.md files and their supporting resources.
Why use it?
It helps determine whether a skill is the right format and keeps its instructions scoped, reusable, and correctly structured.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code.

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

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/tallesborges/zdx/skill-creator.svg)](https://agentmods.dev/skills/tallesborges/zdx/skill-creator)
Your own site
<a href="https://agentmods.dev/skills/tallesborges/zdx/skill-creator"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/skill-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,433 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 5.1 $0.00173 $0.02433
Opus 5 $0.00086 $0.01216
Sonnet 5 $0.00035 $0.00487
Haiku 4.5 $0.00017 $0.00243

Measured 6d ago against content hash b2faa3fe4bad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/init_skill.py, scripts/package_skill.py, scripts/quick_validate.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

crates/zdx-assets/bundled_skills/skill-creator/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Creator

Build skills: SKILL.md modules that auto-invoke when their description matches the situation. The format is the same across runtimes (Anthropic Claude apps, zdx, etc.); save location and packaging differ. This skill covers deciding whether a skill is the right shape, drafting it, and writing it to the right place.

Step 0: Is a skill the right shape?

Skills earn their context tax (the description sits in every prompt) by being auto-invoked when the model recognizes the situation. Before drafting, check the alternatives:

  • Custom command / slash command (e.g. zdx .zdx/commands/<name>.md, Claude Code custom commands) — the workflow is user-fired at a chosen moment (/skillify, /release-notes). Suggest a command and stop.
  • Standalone script — deterministic transform with no decision-making. Drop it in the repo or a bin dir.
  • One-off ask — the user just wants the thing done now, not a reusable artifact. Do the work; don't make a skill.
  • Skill — the agent needs to recognize a class of situations and apply procedural knowledge it doesn't already have, without the user remembering to invoke anything.

If "skill" wins, continue.

Anatomy

<skill-name>/
├── SKILL.md          # required
├── references/       # optional; loaded into context only when needed
├── scripts/          # optional; deterministic helpers, may run without being read
└── assets/           # optional; files used in skill output, not loaded into context

Most skills are a single SKILL.md. Add references/, scripts/, or assets/ only when the content is too big or too deterministic to live inline.

Frontmatter rules

---
name: <kebab-case>
description: <see formula below>
---
  • name: lowercase letters, digits, hyphens; ≤64 chars; no leading/trailing/double hyphens; matches the directory name.
  • description: ≤1024 chars; no < or >; this is the single most important field because it's the only thing the agent matches against to decide whether to load the skill.
  • Allowed extra keys (rarely needed): license, metadata, compatibility, allowed-tools. Anything else is invalid.

Read the full file on GitHub · 196 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 196 lines · 173 tokens per session scan A b2faa3fe4bad

Subscribe to this mod's changes

skill-creator is a skill published in the GitHub repository tallesborges/zdx (20 stars, last pushed yesterday), licensed MIT. It adds 173 tokens to every session and 2,433 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens