← all publishers

aleonsa

@aleonsa source repo

24 published skills

  1. Graphify · aleonsa bundle
    Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
    0
    installs
  2. Caveman Help · aleonsa bundle
    Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
    0
    installs
  3. Caveman Compress · aleonsa bundle
    Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"
    0
    installs
  4. Iterative Retrieval · aleonsa
    Pattern for progressively refining context retrieval to solve the subagent context problem
    0
    installs
  5. GCP Debug · aleonsa
    Diagnose latency, errors, freezes and scaling issues across Cloud Run + Apigee + Pub/Sub on GCP. Use when the user reports production incidents, latency spikes, partial outages, or asks to "see logs / metrics" in a GCP project.
    0
    installs
  6. Fastapi Tdd · aleonsa
    FastAPI testing with TDD — pytest-asyncio, httpx AsyncClient, async SQLAlchemy fixtures, polyfactory, mocking external services, and coverage targets.
    0
    installs
  7. Latex Beamer · aleonsa
    LaTeX compilation and Beamer presentation patterns for macOS with TeX Live. Covers pdflatex, latexmk, bibtex, error diagnosis, and Beamer slide authoring.
    0
    installs
  8. MCP Patterns · aleonsa
    MCP (Model Context Protocol) server patterns — FastMCP server design, tool/resource/prompt definitions, authentication, testing, and deployment.
    0
    installs
  9. RAG Patterns · aleonsa
    RAG architecture patterns — document ingestion, chunking strategies, embedding models, vector stores, hybrid retrieval, re-ranking, advanced techniques (HyDE, multi-query), and evaluation with RAGAS.
    0
    installs
  10. Firebase Auth · aleonsa
    Firebase Authentication patterns — token verification in FastAPI, custom claims for RBAC, multi-tenant auth, ID token validation, service account setup, and frontend Firebase SDK integration.
    0
    installs
  11. GCP Serverless · aleonsa
    GCP serverless deployment patterns — Cloud Run, Cloud Tasks, Secret Manager, Artifact Registry, Cloud Storage, IAM, and cost-aware architecture for production Python services.
    0
    installs
  12. Twilio Extract · aleonsa bundle
    Query Twilio Conversations, Studio Flows, and Monitor/Debugger via the REST API — find conversations by phone/WhatsApp number, read messages and attributes, inspect Studio Flow executions, list debugger alerts. Use when the user wants to look up/inspect/debug Twilio conversations, or check a phone number's history in Twilio. Not for instrumenting a channel adapter — that's a coding task.
    0
    installs
  13. LLM Engineering · aleonsa
    LLM engineering patterns — prompt design, structured outputs with instructor, tool use, context management, model selection/routing, cost optimization, streaming, retry logic, and observability.
    0
    installs
  14. Autonomous Loops · aleonsa
    Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
    0
    installs
  15. Fastapi Patterns · aleonsa
    FastAPI architecture patterns, async SQLAlchemy ORM, Pydantic schemas, dependency injection, service layer, background tasks, and production-grade API design.
    0
    installs
  16. Fastapi Security · aleonsa
    FastAPI security best practices — JWT authentication with python-jose, OAuth2, role-based access, CORS, rate limiting, security headers, and input validation.
    0
    installs
  17. Langfuse Extract · aleonsa bundle
    Extract sessions, traces, observations, prompts, and scores from Langfuse via its public API. Use when the user wants to pull/export/analyze Langfuse data (not for instrumenting an app to send traces — see langfuse-observability for that).
    0
    installs
  18. Intercom Patterns · aleonsa
    Intercom integration patterns — webhook event handling, Conversations API, Contacts API, custom inbox channels, operator bot flows, and multi-tenant workspace management.
    0
    installs
  19. Multi Tenant Saas · aleonsa
    Multi-tenant SaaS patterns — tenant isolation strategies, row-level security, tenant-aware SQLAlchemy models, RBAC, subdomain routing, and Alembic migrations for shared schema.
    0
    installs
  20. Kubernetes Patterns · aleonsa
    Kubernetes production patterns — Deployments, Services, Ingress, ConfigMaps, Secrets, RBAC, HPA, health probes, resource limits, and Helm chart structure for containerized Python/Node services.
    0
    installs
  21. Fastapi Verification · aleonsa
    Verification loop for FastAPI projects: Alembic migration checks, linting, async tests with coverage, security scans, and deployment readiness before release or PR.
    0
    installs
  22. Continuous Learning V2 · aleonsa bundle
    Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
    0
    installs
  23. Langfuse Observability · aleonsa
    LLM observability with Langfuse — tracing LLM calls, spans, prompt versioning, cost tracking, evaluation datasets, and multi-tenant trace isolation in FastAPI/Python applications.
    0
    installs
  24. Cuda Kernel Optimization · aleonsa
    CUDA kernel development and GPU optimization patterns — memory hierarchy, occupancy tuning, coalescing, shared memory tiling, warp-level ops, and profiling with Nsight Compute. Use when writing or optimizing CUDA C++ kernels.
    0
    installs