← Back to list
🛠️

skill-builder Checked

Automatically detect source types and build AI skills using Skill Seekers. Use when the user want…
🛠️ Developer Tools skills By yusufkaraaslan Version v1.0.0 Added 2026-10-13 Updated 2026-10-13 Source ↗
8.5Overall rating
0Views
0Downloads
15.1kStars

Installation

🤖 Install via AI

Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.

Install the "skill-builder" skill by following the instructions at https://skill123.me/install/skill-builder.
⌨️ Command line install

Run in your terminal — downloads and installs to ~/.claude/skills/.

curl -fsSL https://skill123.me/install/skill-builder.sh | bash
📦 Download ZIP

Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.

⬇ Download v1.0.0 · 2 KB
📊 Static rating
8.5/10
Trigger
6.0
Structure
9.3
Workflow
8.4
Content
10.0
Engineering
10.0
Security
9.0

Six-dimension rubric with reviewer rationale.

View scorecard ↓
🛡 Dynamic test
—

Not live-tested yet — this skill is rated on static analysis only.

About this skill

Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.

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.

Documentation

Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.

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

Score breakdown

Trigger
6.0
Description covers What+When but no When Not; several trigger intents (create skill from docs/repos/PDFs/videos, convert documentation, sync skills, export to vector DB, scraping/packaging) yet limited synonyms and English-only phrasing; no explicit exclusion boundary. 1.1=4, 1.2=5, 1.3=3, 1.4=0.
Structure
9.3
Single SKILL.md at 91 lines, well under limits; no resource-type misuse and no redundant docs (README/CHANGELOG absent). Nothing to offload so progressive disclosure is trivially satisfied; slight room for a references file documenting the 40 tools. 2.1=4, 2.2=5, 2.3=3, 2.4=2.
Workflow
8.4
Task-oriented detection table + 7-step workflow (Tool Wrapper pattern, appropriate). Deterministic tool mapping table gives low freedom where needed; strong error guard: detects unconnected MCP server, tells user the two install steps, and provides a CLI fallback instead of stopping. Verification is weak: only 'read the generated SKILL.md and summarize'. 3.1=5, 3.2=6, 3.3=5, 3.4=3, 3.5=2.
Content
10.0
Concise, no filler; CLI examples carry concrete arguments (pip install "skill-seekers[mcp]", skill-seekers create <source>, --target claude, --enhance-level 0); consistent imperative style and clean tables. 4.1=4, 4.2=3, 4.3=3.
Engineering
10.0
Frontmatter has valid name+description YAML; no scripts (N/A, full marks); no file-path references that could dangle. 5.1=3, 5.2=4, 5.3=3.
Security
9.0
Capability manifest: data reads = user-specified sources; side effects = skill-seekers writes generated skill directories; network = user-specified scrape targets, PyPI package install, and upload_skill to an unspecified 'platform API'; credentials = none; persistence = none. Capabilities match declared scope (scraping/packaging/upload is the declared purpose); the opaque upload destination is a minor transparency gap. No scripts, no eval/base64, no injection text, no secrets, external deps are PyPI/GitHub (trusted). No veto.
Single-file tool-wrapper skill (91 lines) that routes knowledge sources (docs/GitHub/PDF/video/codebase) to Skill Seekers MCP tools, with a CLI fallback if the MCP server is not connected. Strengths: crisp source-type detection table, ordered workflow, good degradation path (MCP -> CLI fallback with user-facing remediation steps), valid frontmatter, clean imperative writing with directly runnable commands. Weaknesses: no When-Not/boundary exclusion in description (1.4=0), trigger coverage is English-only with moderate synonym variety, no verification step beyond 'read the generated SKILL.md and summarize'. Capability manifest: reads user-supplied sources (URLs/repos/local paths), writes generated skill dirs, network egress limited to user-specified scrape targets plus PyPI install and an opaque 'platform API' upload tool; no credential access, no persistence. Capabilities match declared scope; no veto.