What is create-a-skill?

A workflow for creating and improving skills for coding agents. It covers drafting, testing, evaluation, user feedback, benchmarking, and packaging skills for distribution.

Use it to gather requirements, write or edit SKILL.md files, test skills on realistic prompts, compare performance, tune when they activate, and create a distributable .skill file.

It gives skill authors a repeatable way to check whether a skill works and improve it based on results.

create-a-skill — Skill for Claude Code by psenger

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 psenger/ai-agent-skills --skill create-a-skill

Clone the repo

git clone --depth 1 https://github.com/psenger/ai-agent-skills

Made for: Claude Code.

Or install psenger-skills, the plugin that ships this one along with the rest of its 14 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/psenger/ai-agent-skills/create-a-skill/github.svg)](https://agentmods.dev/skills/psenger/ai-agent-skills/create-a-skill)

Your own site

<a href="https://agentmods.dev/skills/psenger/ai-agent-skills/create-a-skill"><img src="https://agentmods.dev/badge/skills/psenger/ai-agent-skills/create-a-skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/psenger/ai-agent-skills/create-a-skill"><img src="https://agentmods.dev/badge/skills/psenger/ai-agent-skills/create-a-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,046 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.

Model	Per session	Once invoked
Fable 5.1	$0.00115	$0.04046
Opus 5	$0.00057	$0.02023
Sonnet 5	$0.00023	$0.00809
Haiku 4.5	$0.00012	$0.00405

Measured 9d ago against content hash fcd86a192fd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

create-a-skill 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.

The scan reads SKILL.md. This mod also ships 10 executable files (eval-viewer/generate_review.py, scripts/__init__.py, scripts/aggregate_benchmark.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.

skills/create-a-skill/SKILL.md · 467 lines

How it starts

The opening of the file, as written. The whole thing — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a Skill

A skill for creating new skills from scratch and iteratively improving them through testing, user feedback, and evaluation.

Overview

The process of creating a skill follows this loop:

Gather requirements — interview the user, research the domain
Write a draft — create SKILL.md and any bundled resources
Test — run Claude-with-the-skill on realistic prompts
Evaluate — help the user review outputs qualitatively and quantitatively
Improve — rewrite based on feedback
Repeat until the user is satisfied
Optimize description — tune triggering accuracy
Package — create a distributable .skill file

Your job is to figure out where the user is in this process and jump in. Maybe they say "I want to make a skill for X" — help them from step 1. Maybe they already have a draft — go straight to testing. Always be flexible: if the user says "just vibe with me", skip the formal eval loop.

Phase 1: Gather Requirements

Capture Intent

Start by understanding what the user wants. The conversation might already contain a workflow they want to capture (e.g., "turn this into a skill"). If so, extract answers from the conversation history first — tools used, sequence of steps, corrections the user made, input/output formats observed.

Ask these questions (skip any already answered):

What should this skill enable Claude to do? — the core capability
What task or domain does it cover? — scope and boundaries
What specific use cases should it handle? — concrete scenarios
When should this skill trigger? — user phrases, contexts, keywords
What's the expected output format? — files, text, structured data
Does it need executable scripts or just instructions? — deterministic operations
Any reference materials to include? — docs, APIs, schemas
Should we set up test cases? — skills with objectively verifiable outputs (file transforms, data extraction, code generation) benefit from test cases; subjective skills (writing style, art) often don't. Suggest the appropriate default, but let the user decide.

Read the full file on GitHub · 467 lines

Files

What ships with it

19 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.

9d ago First seen · 467 lines · 115 tokens per session scan A fcd86a192fd6

Subscribe to this mod's changes

create-a-skill is a skill published in the GitHub repository psenger/ai-agent-skills (10 stars, last pushed 3mo ago), licensed MIT. It adds 115 tokens to every session and 4,046 once invoked, about $0.0006 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 Claude Code agent-skills ai-agent claude codex developer-tools

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

printing-press-import

Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…

mvanhorn/cli-printing-press · 104 tokens

create-a-skill