What is create-skill?

A command that turns a source such as a website, code repository, PDF, video, or notebook into an AI skill—a set of instructions and reference material an AI assistant can use.

Creating a skill from documentation or other source material, then optionally packaging it for a specific AI platform.

It avoids manually collecting and rewriting information before an AI assistant can work with it.

create-skill — Command by yusufkaraaslan

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 commands/yusufkaraaslan/skill_seekers/create-skill

Clone the repo

git clone --depth 1 https://github.com/yusufkaraaslan/Skill_Seekers

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 545 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00020	$0.00545
Opus 5	$0.00010	$0.00272
Sonnet 5	$0.00004	$0.00109
Haiku 4.5	$0.00002	$0.00055

Measured 3d ago against content hash 481f6f2d64ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

create-skill — 100% identical, 0 lines differ

distribution/claude-plugin/commands/create-skill.md · 63 lines

What it actually says

Create Skill

Create an AI-ready skill from a source. The source type is auto-detected.

Usage

/skill-seekers:create-skill <source> [--preset <level>] [--output <dir>]

Instructions

When the user provides a source via $ARGUMENTS, run the skill-seekers create command to generate a skill.

Parse the arguments: extract the source (first argument) and any flags.
If no --preset is specified, default to quick for fast results.
If no --output is specified, default to ./output.

Run the create command:

skill-seekers create "$SOURCE" --preset quick --output "$OUTPUT"

After completion, read the generated SKILL.md and summarize what was created.
If the user wants to target a specific platform (e.g., Claude, OpenAI, LangChain), run the package command after:
```
skill-seekers package "$SKILL_DIR" --target "$PLATFORM"
```

Presets

-p quick — 1-2 minutes, basic skill
-p standard — 5-10 minutes, good coverage
-p comprehensive — 20-60 minutes, full analysis

Source Types (auto-detected)

URL (https://...) — Documentation scraping
owner/repo or github.com URL — GitHub repo analysis
file.pdf — PDF extraction
file.ipynb — Jupyter notebook
file.docx — Word document
file.epub — EPUB book
YouTube/Vimeo URL — Video transcript
./directory — Local codebase analysis
file.yaml with OpenAPI — API spec
file.pptx — PowerPoint
file.adoc — AsciiDoc
file.html — HTML page
file.rss — RSS/Atom feed
cmd.1 — Man page

Examples

/skill-seekers:create-skill https://react.dev
/skill-seekers:create-skill pallets/flask -p standard
/skill-seekers:create-skill ./docs/api.pdf
/skill-seekers:create-skill https://youtube.com/watch?v=abc123

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.

3d ago First seen · 63 lines · 20 tokens per session scan A 481f6f2d64ec

Subscribe to this mod's changes

create-skill is a command published in the GitHub repository yusufkaraaslan/Skill_Seekers (14,878 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 545 once invoked, about $0.0001 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 2026-08-30.

Building agents ai-tools automation claude-ai claude-skills documentation documentation-generator

create-skill

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

Copies of this mod

What it actually says

Create Skill

Usage

Instructions

Presets

Source Types (auto-detected)

Examples

What this file has done since we first saw it

Other commands, from other repositories

session-init

permissions

role-clear

codex-exec

build

codex