agentmods.dev

create-agent-skills

create-agent-skills is a skill for Claude Code from Vibe-Marketer/plugins-and-skills. It costs 132 tokens per session (2,087 once invoked), scanned A, original, MIT.

A guide for creating and maintaining Claude Code skills, which are reusable instruction sets for specialized work. It covers their file structure, instructions, workflows, references, templates, scripts, and testing approach.

In plain words
What is it for?
Use it to write, modify, upgrade, or audit SKILL.md files, organize supporting resources, and design skills with evaluation in mind.
Why use it?
It helps turn a repeated process or area of expertise into a skill that activates when needed and remains manageable over time.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the create-plugins plugin — 12 skills, 6 commands, 9 agents shipped together

not rated 2repo 6mo ago A scan 132 tokens original MIT

Good fit Use it to write, modify, upgrade, or audit SKILL.md files, organize supporting resources, and design skills with evaluation in mind.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vibe-marketer/plugins-and-skills/create-agent-skills
View source ↗ Vibe-Marketer/plugins-and-skills
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 Vibe-Marketer/plugins-and-skills --skill create-agent-skills
Clone the repo
git clone --depth 1 https://github.com/Vibe-Marketer/plugins-and-skills

Made for: Claude Code.

Or install create-plugins, the plugin that ships this one along with the rest of its 12 skills, 6 commands, 9 agents.

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 create-agent-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/vibe-marketer/plugins-and-skills/create-agent-skills/github.svg)](https://agentmods.dev/skills/vibe-marketer/plugins-and-skills/create-agent-skills)
Your own site
<a href="https://agentmods.dev/skills/vibe-marketer/plugins-and-skills/create-agent-skills"><img src="https://agentmods.dev/badge/skills/vibe-marketer/plugins-and-skills/create-agent-skills/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 create-agent-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/vibe-marketer/plugins-and-skills/create-agent-skills"><img src="https://agentmods.dev/badge/skills/vibe-marketer/plugins-and-skills/create-agent-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,087 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.
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 $0.00132 $0.02087
Opus 5 $0.00066 $0.01043
Sonnet 5 $0.00026 $0.00417
Haiku 4.5 $0.00013 $0.00209

Measured 9d ago against content hash d16299034796, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

create-agent-skills 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 9d 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.

create-plugins/skills/create-agent-skills/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<essential_principles>

Skills are modular, filesystem-based capabilities that extend Claude with domain expertise on demand. They follow the Agent Skills open standard (agentskills.io). This skill teaches how to create effective skills.

  1. Skills Are Prompts -- All prompting best practices apply. Use pure XML tags in the skill body, never markdown headings. Keep markdown formatting (bold, lists, code blocks) within tag content. Required tags: <objective>, <quick_start>, <success_criteria>.

  2. SKILL.md Is Always Loaded -- When a skill triggers, Claude reads SKILL.md. Essential principles go inline (cannot be skipped). Workflow-specific procedures go in workflows/. Reusable domain knowledge goes in references/. Output structures go in templates/. Executable code goes in scripts/.

  3. Conciseness -- Assume Claude is smart. Only add context Claude does not already have. Challenge every line: "Does removing this reduce effectiveness?" If not, cut it. Never explain git, file I/O, or standard programming.

  4. Degrees of Freedom -- Match instruction specificity to task fragility. Low freedom for migrations and security. Medium freedom for API integrations. High freedom for creative tasks and architecture decisions. One default approach + one escape hatch, not a menu of options.

  5. Progressive Disclosure -- SKILL.md stays under 500 lines. Token usage scales with task complexity. Simple tasks load SKILL.md only. Complex tasks load SKILL.md + workflow + references. Structure: metadata (~100 tokens, always loaded) > SKILL.md body (when triggered) > workflows/references (when needed).

  6. Description-First Design -- The description determines whether Claude selects the skill. Write third-person, trigger-rich, specific descriptions. Target 90%+ trigger rate on relevant queries.

  7. Eval-Driven Development -- Identify what Claude does poorly without the skill. Create 3+ test scenarios. Measure baseline. Write minimal instructions. Test. Iterate based on observation, not assumption.

  8. Baseline-Before-Building -- Test Claude WITHOUT any skill first. Document specific failures on 3-5 representative tasks. Only build content that fixes observed failures — not imagined ones. If Claude already handles it, don't add instructions for it.

  9. Examples-First Development -- 3-5 gold-standard examples teach more than 30 lines of prose. Add examples BEFORE writing explanatory text. Content priority order: constraints > examples > proprietary knowledge > format > process.

  10. Constraint-First Authoring -- NEVER/ALWAYS rules deliver outsized ROI. A single constraint eliminates an entire failure mode with ~10 tokens. Place constraints at the TOP of the skill body where Claude pays most attention.

</essential_principles>

  1. Create a new skill -- Build a task-execution skill from scratch
  2. Create a domain expertise skill -- Build a comprehensive knowledge-base skill (5K-10K+ lines)
  3. Upgrade to router pattern -- Convert a simple skill to the router pattern
  4. Add a workflow -- Add a workflow to an existing router skill
  5. Add a reference -- Add a reference file to an existing skill
  6. Add a template -- Add an output template to an existing skill
  7. Add a script -- Add an executable script to an existing skill
  8. Get guidance -- Help deciding what kind of skill to build, or whether a skill is the right solution

If intent is clear from context, skip the question and route directly.

Read the full file on GitHub · 140 lines

Files

What ships with it

16 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. 9d ago First seen · 140 lines · 132 tokens per session scan A d16299034796

Subscribe to this mod's changes

create-agent-skills is a skill published in the GitHub repository Vibe-Marketer/plugins-and-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 132 tokens to every session and 2,087 once invoked, about $0.0007 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 2026-08-31.

Building agents
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

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…

vercel/next.js · 83 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