skill-builder

A workflow for turning documentation, code repositories, PDFs, videos, and other sources into AI skills—structured instructions and reference material for an AI assistant.

In plain words
What is it for?
Building or updating skills from knowledge sources, and exporting them for AI assistants or search databases.
Why use it?
It provides a repeatable way to collect source information and prepare it for AI use, even when the dedicated connection is unavailable.

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/yusufkaraaslan/skill_seekers/skill-builder
Any agent
npx skills add yusufkaraaslan/Skill_Seekers --skill skill-builder
Clone the repo
git clone --depth 1 https://github.com/yusufkaraaslan/Skill_Seekers

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,111 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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.01111
Opus 5 $0.00019 $0.00556
Sonnet 5 $0.00008 $0.00222
Haiku 4.5 $0.00004 $0.00111

Measured yesterday against content hash 869cb6078939, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-builder 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 yesterday.

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.

distribution/claude-plugin/skills/skill-builder/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Builder

This skill uses the Skill Seekers MCP server, which provides 40 tools for converting knowledge sources into AI-ready skills. If the MCP tools are not available, use the CLI fallback at the bottom of this file instead — do not stop.

Prerequisites

The MCP tools below only work when the Skill Seekers MCP server is connected:

  1. Install the package: pip install "skill-seekers[mcp]"
  2. Connect the server:
    • Installed as the Skill Seekers plugin? Nothing to do — the plugin's bundled .mcp.json starts the server automatically (it still needs step 1).
    • Installed standalone (e.g. copied into ~/.claude/skills/)? Register the server once: claude mcp add skill-seekers -- python -m skill_seekers.mcp.server_fastmcp

If tools like scrape_docs or package_skill are not in your tool list, the server is not connected. Tell the user about the two steps above, and use the CLI fallback in the meantime.

When to Use This Skill

Use this skill when the user:

  • Wants to create an AI skill from a documentation site, GitHub repo, PDF, video, or other source
  • Needs to convert documentation into a format suitable for LLM consumption
  • Wants to update or sync existing skills with their source documentation
  • Needs to export skills to vector databases (Weaviate, Chroma, FAISS, Qdrant)
  • Asks about scraping, converting, or packaging documentation for AI

Source Type Detection

Automatically detect the source type from user input:

Input Pattern Source Type Tool to Use
https://... (not GitHub/YouTube) Documentation scrape_docs
owner/repo or github.com/... GitHub scrape_github
*.pdf PDF scrape_pdf
YouTube/Vimeo URL or video file Video scrape_video
Local directory path Codebase scrape_codebase
*.ipynb, *.html, *.yaml (OpenAPI), *.adoc, *.pptx, *.rss, *.1-.8 Various scrape_generic
JSON config file Unified Use config with scrape_docs

Read the full file on GitHub · 92 lines

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. yesterday First seen · 92 lines · 38 tokens per session scan A 869cb6078939

Subscribe to this mod's changes

skill-builder is a skill published in the GitHub repository yusufkaraaslan/Skill_Seekers (14,860 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,111 once invoked, about $0.0002 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.

Related

Other skills, from other repositories