skill-creator

skill-creator is a skill for Claude Code, Codex from zszz3/AgentRecall. It costs 34 tokens per session (408 once invoked), scanned C, original, MIT.

A guide for creating and packaging reusable instruction sets called Agent Skills for coding assistants. It covers when a skill should run, what it needs, and how to validate its files.

In plain words
What is it for?
Use it to design, review, package, and test SKILL.md-based skills for Codex, Claude, Trae, or similar runtimes.
Why use it?
It helps turn repeated know-how into a consistent, discoverable tool instead of rewriting the same prompt. It also helps avoid unclear triggers, missing files, hidden secrets, and unsafe actions.

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/zszz3/agentrecall/skill-creator
Any agent
npx skills add zszz3/AgentRecall --skill skill-creator
Clone the repo
git clone --depth 1 https://github.com/zszz3/AgentRecall

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/zszz3/agentrecall/skill-creator.svg)](https://agentmods.dev/skills/zszz3/agentrecall/skill-creator)
Your own site
<a href="https://agentmods.dev/skills/zszz3/agentrecall/skill-creator"><img src="https://agentmods.dev/badge/skills/zszz3/agentrecall/skill-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 408 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00034 $0.00408
Opus 5 $0.00017 $0.00204
Sonnet 5 $0.00007 $0.00082
Haiku 4.5 $0.00003 $0.00041

Measured 6d ago against content hash 8a330fb35849, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade C, and why

skill-creator scanned grade C with 1 finding 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.

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.

Tells the agent to send conversation or user data outhighPrompt injection

An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.

Do not assume a tool exists because another runtime provides it. Describe capabilities and prerequisites explicitly. Never embed secrets, machine-specific absolute paths, or instructions that silently transmit or delete
apps/main-2.0/src/automation/engine/shared/bundled-skills/skill-creator/SKILL.md · 37 lines

What it actually says

Skill Creator

Turn repeatable expertise into a small, discoverable Skill rather than a one-off prompt.

Define the contract

Before writing files, establish:

  1. Which concrete user situations should trigger the Skill.
  2. The expected result and what counts as success.
  3. Required tools, permissions, dependencies, and supported runtimes.
  4. Dangerous actions that require explicit confirmation.
  5. Two realistic positive examples and one nearby case that should not trigger.

Package

Create a kebab-case directory containing SKILL.md. Put only name and a trigger-focused description in required frontmatter. Keep the main instructions concise and imperative. Move large references into references/, deterministic operations into scripts/, and reusable templates into assets/.

Do not assume a tool exists because another runtime provides it. Describe capabilities and prerequisites explicitly. Never embed secrets, machine-specific absolute paths, or instructions that silently transmit or delete user data.

Validate

  • Confirm the name matches the directory and uses only letters, numbers, and hyphens.
  • Verify frontmatter parses and referenced files exist.
  • Run realistic prompts with and without the Skill when the environment supports evaluation.
  • Check that the Skill improves the intended result, does not trigger on unrelated requests, and degrades clearly when dependencies are unavailable.
  • Keep changes small; revise instructions based on observed failures rather than adding broad rules speculatively.

Install target

When the user requests direct installation, choose the runtime explicitly: ~/.codex/skills/<name>, ~/.claude/skills/<name>, or ~/.trae/skills/<name>. Refuse to overwrite an unrelated existing directory without confirmation. For this application, user-created Skills remain user resources and must not be written into the bundled official catalog.

Files

What ships with it

2 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 · 37 lines · 34 tokens per session scan C 8a330fb35849

Subscribe to this mod's changes

skill-creator is a skill published in the GitHub repository zszz3/AgentRecall (762 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 408 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). 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-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 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