Skill Builder
You have access to the Skill Seekers MCP server which provides 40 tools for converting knowledge sources into AI-ready skills.
Overview
Build new agent skills with proper structure, triggers, and verification.
When NOT to Use
- You need to edit an existing skill (use the skill's own editing workflow)
- The source is a conversational transcript with no clear structure (use manual writing)
- You're looking for pre-built skills (use
skill_view or search the 1ai-skills library)
Anti-Rationalization Table
| Rationalization |
Reality |
| "I'll figure it out as I go" |
A structured approach saves time and reduces errors. Follow the workflow in this skill rather than improvising. |
| "I already know this topic" |
Familiarity breeds shortcuts. Use the checklist to verify you haven't missed critical steps. |
| "This doesn't apply to my situation" |
The patterns here generalize across contexts. Adapt, don't skip — the underlying principles hold. |
| "One more tool will fix it" |
Adding complexity rarely solves process gaps. Master the core workflow first. |
When to Use
Trigger phrases:
- "skill builder"
- "Wants to create an AI skill from a documentation site, GitHub repo, PDF, video,"
- "Needs to convert documentation into a format suitable for LLM consumption"
- "Wants to update or sync existing skills with their source documentation"
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 |
Recommended Workflow
- Detect source type from the user's input
- Generate or fetch config using
generate_config or fetch_config if needed
- Estimate scope with
estimate_pages for documentation sites
- Scrape the source using the appropriate scraping tool
- Enhance with
enhance_skill if the user wants AI-powered improvements
- Package with
package_skill for the target platform
- Export to vector DB if requested using
export_to_* tools
Available MCP Tools
Config Management
generate_config — Generate a scraping config from a URL
list_configs — List available preset configs
validate_config — Validate a config file
Scraping (use based on source type)
scrape_docs — Documentation sites
scrape_github — GitHub repositories
scrape_pdf — PDF files
scrape_video — Video transcripts
scrape_codebase — Local code analysis
scrape_generic — Jupyter, HTML, OpenAPI, AsciiDoc, PPTX, RSS, manpage, Confluence, Notion, chat
Post-processing
enhance_skill — AI-powered skill enhancement
package_skill — Package for target platform
upload_skill — Upload to platform API
install_skill — End-to-end install workflow
Advanced
detect_patterns — Design pattern detection in code
extract_test_examples — Extract usage examples from tests
build_how_to_guides — Generate how-to guides from tests
split_config — Split large configs into focused skills
export_to_weaviate, export_to_chroma, export_to_faiss, export_to_qdrant — Vector DB export
Commands
# Detect source type from input
# URL → scrape_docs
# owner/repo → scrape_github
# file.pdf → scrape_pdf
# video URL → scrape_video
# Basic workflow pipeline
python3 -c "
from skill_seekers import scrape_docs, enhance_skill, package_skill
# Step 1: Scrape
config = scrape_docs('https://example.com/docs', output_dir='./scraped')
# Step 2: Enhance
enhanced = enhance_skill(config, target_platform='hermes')
# Step 3: Package
package_skill(enhanced, format='SKILL.md', output='./output/')
"
Dependencies
- Python 3.10+
skill-seekers package (tools for scraping and packaging)
- Internet access for documentation scraping
- API keys for vector DB exports (optional)
Process
- Design — Define interface, identify patterns, plan implementation
- Implement — Write code following existing conventions, add tests
- Verify — Run tests, check integration, validate behavior
Verification
1---2name: skill-builder3description: Use when automatically detect source types and build AI skills using4 Skill Seekers. Use when the user wants to create skills from documentation, repos,5 PDFs, videos, or other knowledge sources.6domain: core7author: oyi778license: Apache-2.09subdomain: core-platform10tags:11- ai-infrastructure12- automation13- parsing14- scraping15- rag16version: 1.0.017category: core18metadata:19 source: https://skillmd.com/skills/oyi77/skill-builder20---212223# Skill Builder2425You have access to the Skill Seekers MCP server which provides 40 tools for converting knowledge sources into AI-ready skills.2627## Overview2829Build new agent skills with proper structure, triggers, and verification.3031## When NOT to Use3233- You need to edit an existing skill (use the skill's own editing workflow)34- The source is a conversational transcript with no clear structure (use manual writing)35- You're looking for pre-built skills (use `skill_view` or search the 1ai-skills library)3637## Anti-Rationalization Table3839| Rationalization | Reality |40|---|---|41| "I'll figure it out as I go" | A structured approach saves time and reduces errors. Follow the workflow in this skill rather than improvising. |42| "I already know this topic" | Familiarity breeds shortcuts. Use the checklist to verify you haven't missed critical steps. |43| "This doesn't apply to my situation" | The patterns here generalize across contexts. Adapt, don't skip — the underlying principles hold. |44| "One more tool will fix it" | Adding complexity rarely solves process gaps. Master the core workflow first. |4546## When to Use4748**Trigger phrases:**49- "skill builder"50- "Wants to create an AI skill from a documentation site, GitHub repo, PDF, video,"51- "Needs to convert documentation into a format suitable for LLM consumption"52- "Wants to update or sync existing skills with their source documentation"535455Use this skill when the user:56- Wants to create an AI skill from a documentation site, GitHub repo, PDF, video, or other source57- Needs to convert documentation into a format suitable for LLM consumption58- Wants to update or sync existing skills with their source documentation59- Needs to export skills to vector databases (Weaviate, Chroma, FAISS, Qdrant)60- Asks about scraping, converting, or packaging documentation for AI6162## Source Type Detection6364Automatically detect the source type from user input:6566| Input Pattern | Source Type | Tool to Use |67|---------------|-------------|-------------|68| `https://...` (not GitHub/YouTube) | Documentation | `scrape_docs` |69| `owner/repo` or `github.com/...` | GitHub | `scrape_github` |70| `*.pdf` | PDF | `scrape_pdf` |71| YouTube/Vimeo URL or video file | Video | `scrape_video` |72| Local directory path | Codebase | `scrape_codebase` |73| `*.ipynb`, `*.html`, `*.yaml` (OpenAPI), `*.adoc`, `*.pptx`, `*.rss`, `*.1`-`.8` | Various | `scrape_generic` |74| JSON config file | Unified | Use config with `scrape_docs` |7576## Recommended Workflow77781. **Detect source type** from the user's input792. **Generate or fetch config** using `generate_config` or `fetch_config` if needed803. **Estimate scope** with `estimate_pages` for documentation sites814. **Scrape the source** using the appropriate scraping tool825. **Enhance** with `enhance_skill` if the user wants AI-powered improvements836. **Package** with `package_skill` for the target platform847. **Export to vector DB** if requested using `export_to_*` tools8586## Available MCP Tools8788### Config Management89- `generate_config` — Generate a scraping config from a URL90- `list_configs` — List available preset configs91- `validate_config` — Validate a config file9293### Scraping (use based on source type)94- `scrape_docs` — Documentation sites95- `scrape_github` — GitHub repositories96- `scrape_pdf` — PDF files97- `scrape_video` — Video transcripts98- `scrape_codebase` — Local code analysis99- `scrape_generic` — Jupyter, HTML, OpenAPI, AsciiDoc, PPTX, RSS, manpage, Confluence, Notion, chat100101### Post-processing102- `enhance_skill` — AI-powered skill enhancement103- `package_skill` — Package for target platform104- `upload_skill` — Upload to platform API105- `install_skill` — End-to-end install workflow106107### Advanced108- `detect_patterns` — Design pattern detection in code109- `extract_test_examples` — Extract usage examples from tests110- `build_how_to_guides` — Generate how-to guides from tests111- `split_config` — Split large configs into focused skills112- `export_to_weaviate`, `export_to_chroma`, `export_to_faiss`, `export_to_qdrant` — Vector DB export113114## Commands115116```bash117# Detect source type from input118# URL → scrape_docs119# owner/repo → scrape_github120# file.pdf → scrape_pdf121# video URL → scrape_video122123# Basic workflow pipeline124python3 -c "125from skill_seekers import scrape_docs, enhance_skill, package_skill126# Step 1: Scrape127config = scrape_docs('https://example.com/docs', output_dir='./scraped')128# Step 2: Enhance129enhanced = enhance_skill(config, target_platform='hermes')130# Step 3: Package131package_skill(enhanced, format='SKILL.md', output='./output/')132"133```134135## Dependencies136137- Python 3.10+138- `skill-seekers` package (tools for scraping and packaging)139- Internet access for documentation scraping140- API keys for vector DB exports (optional)141142## Process1431441. **Design** — Define interface, identify patterns, plan implementation1451. **Implement** — Write code following existing conventions, add tests1461. **Verify** — Run tests, check integration, validate behavior147148## Verification149150- [ ] Skill has SKILL.md with frontmatter151- [ ] Has ## When to Use with triggers152- [ ] Has ## Process section153- [ ] Has ## Verification checklist154- [ ] Lint passes with 0 errors