An AI skill is a structured system prompt or set of custom instructions that gives AI assistants like ChatGPT, Claude, and Gemini specialized capabilities. It includes a clear role definition, specific knowledge areas, step-by-step processes, and quality criteria that help AI perform specific professional tasks.

How does Skill This work?

Simply describe your professional expertise in plain text. Our free AI skill generator analyzes your input and transforms it into a structured system prompt. The skill is then graded on clarity, specificity, and usefulness. You can share your skill via a unique URL or copy it to use as custom instructions with any AI assistant like ChatGPT, Claude, or Gemini.

Is Skill This free to use?

Yes, Skill This is completely free. No account or payment is required. You can create unlimited skills and share them with anyone.

How is my skill graded?

Skills are graded on a scale from A+ to F (0-100 points). The grade reflects how clear, specific, and actionable your skill is. Higher grades indicate skills that AI assistants can use more effectively.

How do I use my skill with an AI assistant?

Copy your generated skill and paste it into the system prompt or custom instructions of any AI assistant. For ChatGPT, use Personalization > Custom Instructions. For Claude, add it to a Project's instructions. For Cursor or other IDEs, save it as a .cursorrules or CLAUDE.md file. The AI will then adopt that skill and perform tasks according to your expertise.

AI Skill Report Card

Beading 3D Figure Patterns

B74·Oct 8, 2026·Source: Web

Quick Start13 / 15

Given a raw list of URLs pointing to beading patterns/tutorials, produce a structured, deduplicated index:

Recommendation▾

Name should be gerund form, e.g. 'curating-beading-patterns' or 'organizing-3d-bead-patterns' to match convention

Dragons

Babydrachen 01 — perlentiere.com, PDF pattern
S-Dragon Tutorial — DeviantArt, step-by-step tutorial

Insects & Arachnids

Beaded Spider Instructions — DeviantArt
Skorpion — kidsaction.de, HTML diagram

Workflow14 / 15

Progress:

Step 1: Ingest the full URL list; classify each as PDF pattern, HTML/image diagram, blog post, forum thread, gallery index, or social/contact page (non-pattern)
Step 2: Discard or separately flag non-pattern URLs (homepages, FAQ, contact, search/index pages, social media profiles) unless specifically requested
Step 3: Extract the subject from the URL/filename/title (animal, dragon, character/figure, plant, object/ornament) using naming conventions (German "vorlagen/tiername01.pdf", Russian biserok.org slugs, DeviantArt art titles)
Step 4: Deduplicate — same subject hosted at multiple domains (e.g., perlentiere.com vs www.perlentiere.com, or old vs new CMS paths) should be merged with all source links kept as alternates
Step 5: Group into categories: Animals (by type: mammals, birds, fish, reptiles, insects), Dragons/Fantasy creatures, Pokémon/characters/pop-culture figures, Plants/Trees, Decorative objects/ornaments, Techniques/Grundlagen (base techniques), Galleries/Indexes (meta-resources)
Step 6: Note language and format for each entry (German, Russian, Spanish, French, English; PDF vs webpage vs image)
Step 7: Output as a categorized markdown index with source attribution

Recommendation▾

Description is good but slightly long; consider tightening the parenthetical examples

Categorization Rules

File naming heuristics: perlentiere.com/.../vorlagen/{subject}{NN}.pdf → subject is the animal/object name in German (translate for clarity: drachen=dragon, vogel=bird, schnecke=snail, eichhoernchen=squirrel)
Numbered variants (drachen01 through drachen38) represent different pattern designs of the same creature type — list as variants under one heading, not separate top-level entries
Domain = source, not category: a single site (perlentiere.com, biserok.org, perlentiere-forum.de) hosts many unrelated subjects; never group by domain alone, always re-group by subject
PDF collections from forums (e.g., perlentiere-forum.de/.../01_Venom-Dragon.pdf) often belong to a dated "advent calendar" or contest series — preserve the series name and date if present in the path
DeviantArt / blog tutorials are usually full technique write-ups (stitch-by-stitch), weight these higher as "primary tutorials" vs. a bare pattern-chart PDF
Gallery/index pages (index.php?link=kategorie, search2&suche=A) are navigational, not individual patterns — list once under "Site Indexes," don't enumerate per-letter search pages

Examples15 / 20

Example 1: Input: http://www.perlentiere.com/03_anleitungen/anleitungen/vorlagen/drachen01.pdf through drachen16.pdf, plus https://perlentiere.com/index.php?...&motiv=drachen36 Output:

Recommendation▾

Examples are fairly concrete but somewhat niche/domain-specific — a brief 'bad output' example (e.g., ungrouped, duplicated entries) would strengthen the examples section

Dragons (perlentiere.com "drachen" series — 30+ numbered variants)

Patterns 01–16: direct PDF downloads, vorlagen/drachen{NN}.pdf
Patterns 20, 21, 25, 26, 28–30, 36–38: gallery-only (no PDF found), view via motiv=drachen{NN}


**Example 2:**
Input: `http://rrkra.deviantart.com/art/Axolotl-tutorial-580727616`
Output:

Amphibians

Axolotl Tutorial — DeviantArt, full written tutorial by rrkra


**Example 3:**
Input: two URLs for the same creature on old and new CMS paths: `http://www.perlentiere.com/03_anleitungen/.../schnecke01.pdf` and site relaunch equivalent
Output: merge into one entry, note "mirrored/legacy path — verify which is live before linking."

Best Practices

Always preserve the original URL verbatim (these sites rot fast — dead links are still useful provenance/citation even if content must be fetched via archive.org)
Flag .pdf vs .htm/.gif/.jpg so users know if they need a PDF reader or just an image viewer
For non-English sources, give an English gloss of the subject name alongside the native term (don't just translate and drop the original — searchability depends on the original slug)
Treat DeviantArt gallery/search query URLs (?q=gallery%3A...) as pointing to a single artwork; strip query cruft when citing but keep it if needed to resolve ambiguous/renamed pages
When a site has both a /index.php?pfad=...&motiv=X (gallery thumbnail) and a vorlagen/X.pdf (actual pattern), prefer linking the PDF as primary and the gallery page as "preview image"
Identify series/collections (advent calendars, monthly project pages like beadjewelrymaking.com/2010/project/april.html) and keep them chronologically ordered within their own sub-list

Common Pitfalls

Don't create one entry per URL without deduplication — many of these lists contain the same creature pattern linked from a gallery page, a PDF, and a forum post
Don't treat utility pages (FAQ, Impressum/contact, Facebook/Instagram profile, forum root, search-by-letter pages) as patterns
Don't assume domain reflects current ownership — perlentiere.com vs www.perlentiere.com vs perlentiere-forum.de are related but distinct; note the relationship rather than silently merging
Don't translate subject names so loosely that the original search term is lost (e.g., keep "Pummeluff" alongside "Jigglypuff" since the pattern file is named in German)
Don't flatten numbered variant series into a single bullet — collectors want to know how many distinct designs exist for a popular subject like dragons or Pikachu