This skill provides guidance for training FastText text classification models with constraints on accuracy and model size. It should be used when training fastText supervised models, optimizing model size while maintaining accuracy thresholds, or when hyperparameter tuning for text classification tasks.
LangGraph development for stateful multi-agent applications, cyclic workflows, conditional routing, human-in-the-loop patterns, and persistent state management. Use for complex AI orchestration, agent coordination, and production-grade agentic systems.
Personal knowledge management for Obsidian combining GTD, Zettelkasten, and PARA. Six workflows: (1) Capture - "capture this", "remember this", "save this thought", "note this down" - saves thoughts/tasks to daily inbox without categorization; (2) Process inbox - "process my inbox", "organize captures", "GTD processing" - clarifies items and routes to projects or permanent notes; (3) Daily plan - "plan my day", "what should I work on", "morning planning" - creates prioritized task list based on energy and context; (4) Daily closeout - "daily closeout", "review my day", "evening reflection" - marks progress and drafts tomorrow's plan; (5) Setup - "set up my second brain", "configure vault" - configures vault path and user goals; (6) Excalidraw - "create a diagram", "visualize this", "draw flowchart", "sketch this" - creates .excalidraw.md files with rectangles, ellipses, diamonds, arrows, lines, and text. Proactively offers to capture valuable insights during research conversations.
Agentic Workflow Pattern
Upgrade any skill to v5 Hybrid format using decision theory + modal logic
Create GitHub issues following Pollinations team conventions. Use when asked to create issues, track work, or plan features.
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
Feature planning with 4 phases - Specify requirements, Design architecture, break into granular Tasks, Implement and Validate. Creates atomic tasks that agents can implement without errors. Triggers on "plan feature", "design", "new feature", "implement feature", "create spec".
Expert developer experience optimizer specializing in build performance, tooling efficiency, and workflow automation. Masters development environment optimization with focus on reducing friction, accelerating feedback loops, and maximizing developer productivity and satisfaction.
Conduct structured interviews with the user. Use when multiple decisions need user input: ask ONE question at a time, wait for response, record answer, then proceed to next question.
Redis-backed SSE stream management with stream registry, heartbeat monitoring, completion store for terminal events, and automatic orphan cleanup via background guardian process.
Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.
Structured multi-perspective debate for important architectural decisions and complex trade-offs
Amazon Bedrock AgentCore Policy for defining agent boundaries using natural language and Cedar. Deterministic policy enforcement at the Gateway level. Use when setting agent guardrails, access control, tool permissions, or compliance rules.
Use to package upsell, cross-sell, and advocacy motions tied to customer outcomes.
python's package managing
Comprehensive guide to integrating DSPy with Microsoft Agent Framework in AgenticFleet, covering typed signatures, assertions, routing cache, GEPA optimization, and agent handoffs.
Autonomous task execution from GTD.md items. Use when processing GTD tasks, call prep, outreach, or podcast preparation.
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).
Analyze Google Sheets data, plan range-precise edits, and help with formulas or tabular transformations through connected Google Sheets data. Use when the user wants to inspect tabs or ranges, summarize spreadsheet contents, propose formulas, clean or restructure tables, or update cells with explicit range-level intent.