From philschmid-self-learning-skill
Generates reusable skills for unfamiliar technologies by web searching docs, extracting content with browser tools, and synthesizing instructions. Invoke via `/learn <topic>`.
npx claudepluginhub joshuarweaver/cascade-ai-ml-agents-misc-1 --plugin philschmid-self-learning-skillThis skill uses the workspace's default tool permissions.
Autonomously research and learn new technologies from the web, then generate a reusable skill.
Conducts multi-round deep research on GitHub repos via API and web searches, generating markdown reports with executive summaries, timelines, metrics, and Mermaid diagrams.
Dynamically discovers and combines enabled skills into cohesive, unexpected delightful experiences like interactive HTML or themed artifacts. Activates on 'surprise me', inspiration, or boredom cues.
Generates images from structured JSON prompts via Python script execution. Supports reference images and aspect ratios for characters, scenes, products, visuals.
Autonomously research and learn new technologies from the web, then generate a reusable skill.
/learn <topic>
If <topic> is missing, show usage. If topic is ambiguous, ask to clarify:
Normalize to kebab-case for filenames.
Use web search tool to find authoritative documentation:
Search queries to try:
<topic> official documentation<topic> getting started guide<topic> API reference<topic> GitHub repositorySource prioritization:
Select 3–5 high-quality URLs maximum.
If no credible sources found, ask user to provide a URL.
For each selected URL, read the content:
Extract only relevant sections:
Skip irrelevant content:
If reading the content fails (JavaScript-heavy sites), fall back to browser agent:
Task: Navigate to <URL> and extract the main content including:
- Installation instructions
- Core concepts and API reference
- Code examples
Return the extracted content as markdown.
Record scrape timestamp for each source (use current date: YYYY-MM-DD format).
Skills are modular, self-contained packages. Every skill consists of a required SKILL.md file and optional bundled resources:
skill-name/
├── SKILL.md (required)
│ ├── YAML frontmatter metadata (required)
│ │ ├── name: (required)
│ │ └── description: (required)
│ └── Markdown instructions (required)
└── Bundled Resources (optional)
├── scripts/ - Executable code (Python/Bash/etc.)
├── references/ - Documentation intended to be loaded into context as needed
└── assets/ - Files used in output (templates, icons, fonts, etc.)
references/skill_creation_guide.md to understand the format and principles.Antigravity supports two types of skills, save a global-workspace if asked.
.agent/skills/<skill-folder>/ Workspace-specific~/.gemini/antigravity/skills/<skill-folder>/ Global (all workspaces)Create directory if it doesn't exist, warn user before overwriting existing skill.
Report:
✓ Created skill: <topic>
Sources scraped: <N>
Saved to: .agent/skills/<topic>/SKILL.md
This skill will auto-trigger when working with <topic>.
search_web: Discover documentation URLsread_url_content: Extract content from static pagesbrowser_subagent: Extract content from JavaScript-heavy siteswrite_to_file: Save the generated skill