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.
npx skills add tallesborges/zdx --skill skill-creatorgit clone --depth 1 https://github.com/tallesborges/zdxWrote 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.
[](https://agentmods.dev/skills/tallesborges/zdx/skill-creator)<a href="https://agentmods.dev/skills/tallesborges/zdx/skill-creator"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/skill-creator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tallesborges/zdx/skill-creator"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00173 | $0.02433 |
| Opus 5.5 | $0.00069 | $0.00973 |
| Sonnet 5.5 | $0.00035 | $0.00487 |
| Haiku 4.5 | $0.00017 | $0.00243 |
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 1mo 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.
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.
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.
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.
- 1mo ago Changed 0666a9c0078a
- 1mo ago First seen · 196 lines · 173 tokens per session scan A b2faa3fe4bad
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 $0.0007 per session on Opus 5.5. 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.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…