NLP

Design production-grade Helm charts through architectural reasoning rather than patternretrieval. Activate when designing new Helm charts for Kubernetes deployments, evaluatingchart architecture, making decisions about component packaging, or reviewing charts forextensibility and maintainability. Guides decision-making about dependencies, lifecyclehooks, configuration surface, and multi-environment deployment through context-specificreasoning rather than generic best practices.

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

Advanced Context Management Principles adapted from NeoLabHQ/context-engineering-kit. Teaches the agent to treat Context as a scarce resource, use "Commands" over "Skills", and proactively prune/offload tasks.

Handle template comparison and optimization workflows including backup detection, smart merging, and update completion reporting. Enhanced with Context7 MCP for up-to-date documentation.

Handles user authentication, profile management, and personalized features using BetterAuth for the Physical AI & Humanoid Robotics textbook.

Match file paths against steering file glob patterns to determine applicable steering guidance. Use when orchestrator needs to inject context-aware guidance based on files being modified.

Run the SYSopGPTWSL operator kernel (repeatable sysop pipeline + diffable report + learning ledger). Use when asked to run sysop checks, collect Windows/WSL snapshots, benchmark, or produce the operator report.

Write comments explaining WHAT and WHY, never temporal context or history

Memory layer integration patterns for FastAPI with Mem0 including client setup, memory service patterns, user tracking, conversation persistence, and background task integration. Use when implementing AI memory, adding Mem0 to FastAPI, building chat with memory, or when user mentions Mem0, conversation history, user context, or memory layer.

Use this skill to start work on an assigned GitHub issue. This is the core implementation loop of the SynthesisFlow methodology. Guides the AI to load full context (specs, plans, retrospective), create a feature branch, and begin implementation. Triggers include "start work on issue", "implement issue

AI-assisted development workflow system for feature planning, session management, and quality assurance (v2.3). WORKTREE-CENTRIC - automatically scopes to current worktree's feature (worktree name = feature name). In feature worktrees, shows only relevant feature context. In main branch, shows dashboard of all worktrees. AUTO-ACTIVATES for session start (show priorities/NBA with Explore agent), feature work (load plan context with LSP symbol grounding), new features (spike mode with parallel sub-agents), context >70% (create handoff), UI changes (run Playwright tests), completed features (suggest archive), errors or failures (trigger RCA-PCA). Works with agent-docs/ folder structure. Modes are nba, work, spike, test, validate, sync, status, handoff, archive, rca-pca, tidyup. Use when working in codebases with agent-docs/ directory.

Coordination documentation synchronization patterns. Covers .hestai/ structure management, worktree-based doc PRs, PROJECT-CONTEXT/APP-CONTEXT updates, and documentation placement rules. Use for HO delegation to system-steward for doc updates.

This skill creates ephemeral pods cloned from existing deployments for interactive shell access with full application context. Use this when you need Rails console, database access, or debugging with env vars and secrets without affecting production pods.