Find the perfect skill
inference.sh CLI for AI applications
Development
Use inference.sh CLI to run 150+ AI applications including image/video generation, LLMs, web search, and Twitter automation, no GPU required.
Create Podcast Show Notes
Content
Generates timestamped show notes, key takeaways, and formatted transcripts from podcast episodes. Ideal for summaries and publishing.
Data Flow Tracer
Development
Trace how data moves through the engine for named flows like render, tick, or entity spawn. Maps each step with file and line references.
Expert C for Systems and Performance
Development
Expert C for efficient, reliable code. Covers memory management, pointers, system calls, embedded, and pthreads.
Vexor: Vector-powered semantic search CLI
Data & AI
Skill for using Vexor, a vector-powered CLI for semantic file search with Claude/Codex.
Web QA and bug fixing
Testing
Systematically test a web app, fix bugs with atomic commits, and re-verify. Produces health scores and a ship-readiness report.
Threat Modeling for Architectures
Security
Disciplined threat modeling loop for software architectures and APIs: map assets, apply STRIDE, classify impact, and recommend mitigations. All responses must be in Portuguese.
dbt Model Versioning
Development
Load when task involves dbt model versioning, creating v2 of a model, or backward-compatible model changes. Covers versions YAML config, defined_in, latest_version, and ref() with version pins.
ADK Bidi-streaming Expert
Development
Expert in ADK Bidi-streaming, covering Live API integration, FastAPI WebSocket implementations, and production best practices.
Read web pages in reader mode
Content
Fetches raw text from a web page in reader mode, without AI summarization. Use for reading stories or articles slowly.
Diagnosing Bugs
Development
Diagnosis loop for hard bugs and performance regressions. Use when the user reports something broken, throwing, failing, or slow.
Heal skill documentation
Documentation
Analyze conversation to detect and fix issues in skill documentation with user approval.