adrielp

adrielp/ai-engineering-harness

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

Model Context Protocol (MCP) server for Kubernetes and OpenShift. Runs locally from the kubernetes-mcp-server npm package.

adrielp/ai-engineering-harness

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

MCP server "aspire-dashboard", hosted remotely at localhost, as configured in adrielp/ai-engineering-harness.

adrielp/ai-engineering-harness

Agent Claude Code

Analyzes codebase implementation details and explains how code works. Use this agent when you need to understand specific components, trace data flow, identify architectural patterns, or explain technical implementations. Provide detailed context about what you want analyzed for best results.

adrielp/ai-engineering-harness

Agent Claude Code

Specialist agent for locating files, directories, and components relevant to features or tasks. Provides organized file location mappings without content analysis.

adrielp/ai-engineering-harness

Agent Claude Code

Finds similar implementations, usage examples, and existing patterns in the codebase with concrete code details. Use this agent when you need working examples to model after, want to see how similar features are implemented, or need to identify established patterns and conventions. Provides both file locations and…

adrielp/ai-engineering-harness

Agent Claude Code

Specialized agent for deep analysis of research documents and thought notes. Extracts high-value insights, decisions, and actionable information while filtering noise.

adrielp/ai-engineering-harness

Agent Claude Code

Discovers relevant documents in the thoughts/ directory for metadata, research notes, decisions, and historical context. Specializes in locating and categorizing documentation across personal, shared, and global thought directories.

adrielp/ai-engineering-harness

Agent Claude Code

Researches information from web sources to find accurate, up-to-date answers. Use this agent when you need current information, modern best practices, or details not available in your training data. Call with a detailed research query describing what information you need.

adrielp/ai-engineering-harness

Skill Claude Code

Create well-structured git commits for changes made during the session.

adrielp/ai-engineering-harness

Skill Claude Code

Create detailed, actionable implementation plans through an interactive, iterative process.

adrielp/ai-engineering-harness

Skill Claude Code

Debug Kubernetes issues by examining pods, logs, events, and cluster state.

adrielp/ai-engineering-harness

Skill Claude Code

Debug issues during manual testing or implementation by examining logs, state, and git history.

adrielp/ai-engineering-harness

Skill Claude CodeCodex

Write, refactor, restructure, edit, or audit technical documentation using the Diátaxis framework (tutorials, how-to guides, reference, explanation). Produces clear, concise, scannable docs and fights the default tendency toward bloated, over-explained AI prose. Use this skill for ANY documentation work — README and…

adrielp/ai-engineering-harness

Skill Claude Code

Handles experimental features that lack proper ticketing by retroactively creating Linear tickets and PRs from commits. Use when user has made commits without tickets, mentions "founder mode", or asks to formalize experimental work.

adrielp/ai-engineering-harness

Skill Claude Code

Creates well-structured git commits by analyzing changes, drafting messages, and executing commits. Use when the user asks to commit changes, save work, create a commit, or mentions committing their code.

adrielp/ai-engineering-harness

Skill Claude CodeCodex

Query GitHub for pull requests, issues, notifications, and project boards using the gh CLI. Use this skill whenever the user asks about their GitHub activity, PRs needing review, open issues, project board status, or wants to summarize GitHub conversations. Trigger on phrases like: "what PRs need my attention", "show…

adrielp/ai-engineering-harness

Skill Claude Code

Implement an approved technical plan from thoughts/plans/ with phase-by-phase execution.

adrielp/ai-engineering-harness

Skill Claude Code

Explore a codebase to find architectural friction, propose deep-module refactors as RFC issues. Use when the user wants to improve architecture, find refactoring opportunities, deepen shallow modules, or make a codebase more AI-navigable and testable.

adrielp/ai-engineering-harness

Skill Claude Code

Initialize the AI Engineering Harness in a repository by creating CLAUDE.md and thoughts/ directory structure.

adrielp/ai-engineering-harness

Skill Claude Code

Interview the user relentlessly about a plan or design until reaching shared understanding. Walks down each branch of the decision tree, resolving dependencies one-by-one. Use when the user wants to stress-test a plan, asks to be interviewed, says "drill in", "ask me questions", or wants to validate design decisions…

adrielp/ai-engineering-harness

Skill Claude Code

Observability Driven Development (ODD) — design the trace before the feature. Auto-activates when the user wants to "drive with observability", "ODD", "instrument first", "narrative-first", "telemetry-driven", or wants to set up a local OTel feedback loop with the Aspire dashboard. Pairs with /validatetelemetry to…

adrielp/ai-engineering-harness

Skill Claude Code

OpenTelemetry Collector configuration — receivers, processors, exporters, pipelines, sampling, deployment. Covers OTLP, Prometheus, filelog, hostmetrics; processor ordering; pipeline design; head/tail sampling; and RED metric derivation via signaltometrics.

adrielp/ai-engineering-harness

Skill Claude Code

OpenTelemetry orchestrator — auto-activates on observability, telemetry, tracing, metrics, logging, OTel SDK, Collector, semantic conventions, or OTTL requests. Routes to the correct sub-skill.

adrielp/ai-engineering-harness

Skill Claude Code

Application-side OpenTelemetry SDK setup — traces, metrics, structured logging across Node.js, Go, Python, Java, .NET, Ruby. Prescriptive guidance for resource attributes, span design, metric instrument selection, sensitive data handling, and validation.