agentmods.dev

skills-creator

skills-creator is a skill for Claude Code, Codex from Stack-Cairn/LiveAgent. It costs 53 tokens per session (708 once invoked), scanned A, original, MIT.

A guide for creating or updating LiveAgent skills, which are reusable instructions for handling specific tasks. It covers writing the instructions, adding supporting files, validating them, and packaging them.

In plain words
What is it for?
Use it to create a new skill, revise an existing one, or prepare a skill for the LiveAgent skills system. It helps define the trigger, workflow, references, and required files.
Why use it?
It helps turn a workflow into a consistent skill that agents can follow and reuse. It also keeps the main instructions concise and separates reference material and helper files where needed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 2.3krepo +1 today A scan SkillSpector: pass 53 tokens original MIT

Good fit Use it to create a new skill, revise an existing one, or prepare a skill for the LiveAgent skills system. It helps define the trigger, workflow, references, and required files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stack-cairn/liveagent/skills-creator
View source ↗ Stack-Cairn/LiveAgent
About the project

LiveAgent is a local-first desktop client for using AI agents with multiple models, local tools, MCP connections, skills, and remote gateways. It is for people who want to run and customize AI-agent workflows from a desktop application.

Stack-Cairn/LiveAgent · 2,262 stars · on GitHub

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.

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

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 skills-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/stack-cairn/liveagent/skills-creator/github.svg)](https://agentmods.dev/skills/stack-cairn/liveagent/skills-creator)
Your own site
<a href="https://agentmods.dev/skills/stack-cairn/liveagent/skills-creator"><img src="https://agentmods.dev/badge/skills/stack-cairn/liveagent/skills-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.

agentmods 80×15 button for skills-creator

Your own site · 80×15
<a href="https://agentmods.dev/skills/stack-cairn/liveagent/skills-creator"><img src="https://agentmods.dev/badge/skills/stack-cairn/liveagent/skills-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 708 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00053 $0.00708
Opus 5.5 $0.00021 $0.00283
Sonnet 5.5 $0.00011 $0.00142
Haiku 4.5 $0.00005 $0.00071

Measured 2mo ago against content hash e71e22376220, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skills-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 2mo 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.

crates/agent-gui/src-tauri/prompt/skills/skills-creator/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skills Creator

Create LiveAgent-compatible skills in the fixed runtime skills root by keeping the entrypoint concise, moving long guidance into references, and using helper files only when the workflow truly needs them. Prefer English for generated skill documentation so skills stay broadly reusable, but other languages are accepted.

Workflow

  1. Confirm the target skill name, trigger description, captured workflow, and any required reference/helper files.
  2. Read references/agent-skill-format.md and references/authoring-patterns.md through file tools before shaping long instructions. Use path="skill://skills-creator/references/agent-skill-format.md" and path="skill://skills-creator/references/authoring-patterns.md", or use the exact pathRef returned by a prior tool.
  3. Draft the SKILL.md body in imperative form. Keep frontmatter to name and description unless a compatibility reason requires an optional key.
  4. Move deterministic or reusable details into files only when they are truly needed; keep explanatory material in references/; keep output-only resources in assets/.
  5. Use SkillsManager(action=create) to write the skill into the fixed user skills root. Keep conflict=fail unless the user explicitly wants replacement.
  6. Use SkillsManager(action=validate) after creation. Fix validation errors before packaging.
  7. Use SkillsManager(action=package) only after validation passes and a distributable archive is required.
  8. After creation, the new skill is enabled for the current conversation automatically; ask LiveAgent to rescan skills or reopen the Skills menu only if the new skill does not appear immediately.

Rules

  • Keep one skill per directory.
  • Name the directory exactly after the skill name.
  • Prefer English for generated skill documents, including SKILL.md, Markdown files in references/, and example documentation; follow the user's language preference when they state one.
  • Do not add README-style files such as README.md, INSTALLATION_GUIDE.md, QUICK_REFERENCE.md, or CHANGELOG.md inside a skill.
  • Prefer one-hop references from SKILL.md; do not build deep reference chains.
  • Keep the SKILL.md body short enough to read comfortably through SkillsManager.
  • When inspecting or optimizing files inside an enabled installed skill, use Read, List, Glob, Grep, Write, Edit, or Delete with the exact path you see: prefer skill://<baseDir>/... or a pathRef returned by a tool. Do not use Bash for workspace or Skill file operations.
  • Create new skill directories through SkillsManager(action=create) or SkillsManager(action=install). Use conflict=backup or conflict=overwrite only when the user has accepted replacement.
  • Creating a skill automatically enables it for the current conversation.

Read the full file on GitHub · 40 lines

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. 2mo ago First seen · 40 lines · 53 tokens per session scan A e71e22376220

Subscribe to this mod's changes

skills-creator is a skill published in the GitHub repository Stack-Cairn/LiveAgent (2,262 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 708 once invoked, about $0.0002 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.

Building agentsClaude Codeai-agentsai-toolsclaude-desktopcodexcodex-app
Related

skills-creator compared with skills from other repositories

skills-creator next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
skills-creatorStack-Cairn/LiveAgentSkill2.3ktodayMITA53Claude Code, Codex
himalayas-employerHimalayas-App/himalayas-mcpSkill21todayMITA37Claude Code, Codex
verify-cliNimbleBrainInc/mpakSkill14todayApache-2.0A23Claude Code
diagnose-domainoborseth/Porkbun-MCPSkill362d agoMITA72Claude Code
change-dns-safelyoborseth/Porkbun-MCPSkill362d agoMITA93Claude Code
publish-websiteoborseth/Porkbun-MCPSkill362d agoMITA65Claude Code
move-dns-to-porkbunoborseth/Porkbun-MCPSkill362d agoMITA75Claude Code