adrielp/ai-engineering-harness
Skill Claude CodeCodex
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 CodeCodex
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.
adrielp/ai-engineering-harness
Skill Claude CodeCodex
OTTL (OpenTelemetry Transformation Language) reference — syntax, contexts, common patterns (redaction, normalization, enrichment, filtering), error handling, and complete function reference for Collector processors.
adrielp/ai-engineering-harness
Skill Claude CodeCodex
OpenTelemetry semantic conventions — attribute naming, placement across telemetry levels, stability/versioning, legacy→current migration, and registry namespace reference.
adrielp/ai-engineering-harness
Skill Claude CodeCodex
Generates comprehensive pull request descriptions following repository templates. Use when creating or updating PR descriptions, when user mentions pull requests, or when asked to describe changes for review.
adrielp/ai-engineering-harness
Skill Claude CodeCodex
Break a PRD into independently-workable, vertical-slice issues written as local markdown files in issues/. Use when the user wants to turn a PRD into a list of concrete, demoable tasks ordered by dependencies.
adrielp/ai-engineering-harness
Skill Claude CodeCodex
Conduct comprehensive codebase research by spawning parallel sub-agents and synthesizing findings.
adrielp/ai-engineering-harness
Skill Claude CodeCodex
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", asks for test-first development, or wants integration-style tests that survive refactors.
adrielp/ai-engineering-harness
Skill Claude CodeCodex
Validate that an implementation plan was correctly executed, verifying all success criteria.
adrielp/ai-engineering-harness
Skill Claude CodeCodex
Validate locally-emitted telemetry against a written narrative spec, or run a generic health check on the local OTel stack. Delegates to the observability-driven-development skill's Validation section.
adrielp/ai-engineering-harness
Skill Claude CodeCodex
Manage git worktrees for parallel development workflows integrated with the harness ticket system. Use when the user mentions worktrees, wants to work on multiple branches simultaneously, asks about parallel development, or wants to create an isolated workspace for a ticket or feature.
adrielp/ai-engineering-harness
Skill Claude CodeCodex
Generate a PRD from a client brief and write it as issues/prd.md. Interviews the user about problem and solution, sketches deep modules, and writes a structured PRD. Use when the user wants to turn a client request or rough idea into a structured PRD.
adrielp/ai-engineering-harness
Agent
The specialized tool for codebase analysis, architectural mapping, and understanding system-wide dependencies. Invoke this tool for tasks like vague requests, bug root-cause analysis, system refactoring, comprehensive feature implementation or to answer questions about the codebase that require investigation. It…
adrielp/ai-engineering-harness
Skill Claude CodeCodex
Handles experimental features that lack proper ticketing by retroactively creating Linear tickets and PRs from commits. Utilizes git and gh commands via Gemini CLI's runshellcommand to formalize experimental work.
adrielp/ai-engineering-harness
Skill Claude CodeCodex
Creates well-structured git commits by analyzing changes, drafting messages, and executing commits using Gemini CLI's runshellcommand for git operations.
adrielp/ai-engineering-harness
Skill Claude CodeCodex
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 CodeCodex
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 CodeCodex
Generates comprehensive pull request descriptions following repository templates. Utilizes Gemini CLI tools including runshellcommand for git and gh commands.
adrielp/ai-engineering-harness
Skill Claude CodeCodex
Break a PRD into independently-workable, vertical-slice issues written as local markdown files in issues/. Use when the user wants to turn a PRD into a list of concrete, demoable tasks ordered by dependencies.
adrielp/ai-engineering-harness
Skill Claude CodeCodex
Generate a PRD from a client brief and write it as issues/prd.md. Interviews the user about problem and solution, sketches deep modules, and writes a structured PRD. Use when the user wants to turn a client request or rough idea into a structured PRD.
adrielp/ai-engineering-harness
Agent
Orchestrates the full harness workflow (research → plan → implement → validate plan → validate telemetry → commit) by delegating each phase to subagents and skills, holding only artifact paths in context. Use as the top-level driver when starting from a ticket or feature request.
adrielp/ai-engineering-harness
Command
You are tasked with creating git commits for the changes made during this session.
adrielp/ai-engineering-harness
Command
You are an expert technical planning assistant. Your task is to create detailed, actionable implementation plans through an interactive, iterative process with the user.
adrielp/ai-engineering-harness
Command
You are tasked with helping debug Kubernetes issues. This command allows you to investigate problems by examining pods, logs, events, and cluster state without making changes.