Generate a structured placeholder skill with machine-parseable metadata fields.
npx skills add https://github.com/plurigrid/asi --skill shadow-goblin
Please help me install this Agent Skill. Skill: shadow-goblin Source: https://github.com/plurigrid/asi/tree/main/skills/shadow-goblin Command: npx skills add https://github.com/plurigrid/asi --skill shadow-goblin
This unit serves as an auto-generated placeholder skill, providing a scaffold for future content and testing Claude integration workflows.
This is a placeholder. No operational commands until content is added.
High-intent search queries and answers about installing and using this skill.
A skill placeholder is an auto-generated structured template that serves as a scaffold for future implementation. It provides a minimal metadata contract with machine-parseable fields, enabling testing of vector-based retrieval systems, RAG workflows, and schema validation before populating it with actual content.
Placeholder skills are designed for evaluation and discovery testing. They define a consistent metadata structure with fields like request, description, is_toxic, and toxic_reason, allowing you to validate integration requirements and formatting flows without requiring operational implementation.
Yes. Placeholder skills function as test fixtures for vector-based retrieval systems and RAG workflows. Their structured metadata contract ensures your catalog ingestion, schema validation, and AI agent integration workflows handle the required fields correctly before deploying production skills.
Placeholder skills include a minimal metadata contract with fields such as request, description, is_toxic, and toxic_reason. This structure satisfies integration requirements for AI agents and allows you to test schema validation and data flow without full skill implementation.
Use a placeholder skill during development and testing phases to validate your skill discovery infrastructure, vector retrieval systems, and agent integration pipelines. It provides a lightweight template for evaluation and formatting flows before committing to full implementation.
mindmorassIngest PDFs, websites, code repos, and notes into vector databases with chunking and metadata schemas.
djankiesGenerate structured content from templates with placeholder replacement and validation.
llama-farmAudit and optimize RAG pipelines with LlamaIndex, ChromaDB, and Celery best practices.
jassicsValidate per-user and per-tenant authorization in RAG retrieval systems.
