Interactive code review for agent iterations. Captures comments, tracks resolution status, and integrates with git diffs.

Create/update .agent/constitution.md. Use when commands/boundaries/constraints must be confirmed before baseline or code changes. Draft v0 from repo evidence, then interview user.

Create new AgentOps skills via interactive interview. Supports from-scratch and clone modes with tiered complexity.

Create focused, specific technical documentation for codebase sections. Analyzes code, identifies topics, presents options before writing. Supports code blocks with line numbers.

Deep, excruciating code review. Use anytime to analyze code for correctness, edge cases, security, performance, and design issues. Not tied to baseline—this is pure code analysis.

Dependency management, updates, and security advisory handling. Use when adding, updating, or auditing project dependencies.

Docker image reviews, optimization, and step-building guidance. Analyzes Dockerfiles for best practices, security issues, and anti-patterns.

Documentation management for README, CHANGELOG, API docs, and user-facing documentation. Use when creating or updating project documentation.

Analyze issues to identify the next work item and update focus.md. Enforces issue-first workflow and confidence-based batch limits.

Generate narrative summaries from git history for onboarding, retrospectives, changelogs, and exploration. LLM-enhanced when available, works without LLM too.

Manage git operations safely. Includes stale state detection, branch/commit management. Never pushes without explicit user confirmation.

Comprehensive project hygiene: archive issues, validate schema, clean clutter, align docs, check git, update ignores.

Implement only after a validated/approved plan. Use for coding: small diffs, frequent tests, no refactors, stop on ambiguity.

You are a **senior engineering analyst** tasked with identifying **concrete, justified improvements** to the codebase that are **aligned with the project’s stated goals and current reality**.

---name: agent-ops-lint-instructionsdescription: "Validate and lint AgentOps instruction files (skills, prompts, agents). Checks formatting, structure, and consistency."category: extended []invoked_by

Migrate a project into another, ensuring functionality and validating complete content transfer. Use for monorepo consolidation, template upgrades, or codebase mergers.

Optimize agent instruction files by extracting sections into separate files and referencing them. Reduces context size while preserving information.

Identify and map different sections of a software project (API, frontend, database, CLI, domain). Use for context scoping and architecture documentation.

Ruthlessly audit project features for justification. Challenge every feature to prove its value with evidence or face removal. Uses MCP tools for research.

Handle failures and errors during workflow. Use when build breaks, tests fail unexpectedly, or agent gets stuck. Semi-automatic recovery with user confirmation for destructive actions.

Generate markdown reports from issues. Filter by type, priority, epic, date range. Supports summary, detailed, progress, completion, velocity, and backlog analysis views.

Deep topic research with optional issue creation from findings. Use for researching technologies, patterns, libraries, or any topic requiring investigation.

Scan the current chat session for durable learnings (clarifications, corrections, decisions, pitfalls) and update .agent/memory.md. Use after critical review and before concluding work.

Create clean git branches from feature work, excluding agent-ops files. Use for PR preparation.

Create, refine, and manage issues. Use for creating new issues from loose ideas, refining ambiguous issues, bulk operations, or JSON export.

Detect available development tools at session start. Saves to .agent/tools.json and warns about missing required tools. Works with or without aoc CLI installed.

Pre-commit and pre-merge validation checks. Use before committing changes or declaring work complete to ensure all quality gates pass.

Manage semantic versioning, changelog generation, and release notes. Auto-generates entries from completed issues or git diff.

agent-orchestration

Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.

Automatically applies when designing multi-agent systems. Ensures proper tool schema design with Pydantic, agent state management, error handling for tool execution, and orchestration patterns.

This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.

Orchestrates multi-agent workflows by delegating ALL tasks to spawned subagents via /spawn command. Parallelizes independent work, supervises execution, tracks progress in UUID-based output directories, and generates summary reports. Never executes tasks directly. Triggers on keywords: orchestrate, manage agents, spawn agents, parallel tasks, coordinate agents, multi-agent, orc, delegate tasks

Coordinate multiple AI agents and skills for complex workflows

Generate standardized .agent-os directory structure with product documentation, mission, tech-stack, roadmap, and decision records. Enables AI-native workflows.

Track and report agent invocation metrics including usage counts, success/failure rates, and completion times. Use for understanding which agents are utilized, identifying underused agents, and optimizing agent delegation patterns.

Human and agent coordination protocol for repos using .agentprotocol. Use to manage TODO intake, open and archived work items, and plan/build docs with deterministic indexes.

A two-phase repair skill that analyzes errors and suggests fixes before executing repairs. Phase one: user describes error, agent analyzes and proposes solution. Phase two: upon approval, executes the repair action.

Get external agent review and feedback. Routes Anthropic models through Claude Agent SDK (uses local subscription) and other models through OpenRouter API. Use for code review, architecture feedback, or any external consultation.

Ensure agent safety - guardrails, content filtering, monitoring, and compliance

Agent SDK development utilities for creating, testing, and managing AI agents with comprehensive tooling and debugging capabilities.

Comprehensive knowledge of Claude Agent SDK architecture, tools, hooks, skills, and production patterns. Auto-activates for agent building, SDK integration, tool design, and MCP server tasks.

Guidance for selecting appropriate AI model (sonnet vs haiku) based on task complexity, reasoning requirements, and performance needs. Use when implementing agents or justifying model selection.

Systematic framework for selecting the optimal specialized agent for any task. Use when delegating to subagents via the Task tool to ensure the most appropriate specialist is chosen based on framework, domain, task type, and complexity. Applies decision tree logic to match tasks with agent expertise.

Facilitates seamless integration between Claude Skills and the existing Agent framework, enabling skills to invoke agents and vice versa with proper context handoffs.

Creates new agent skills following modern best practices with proper structure and documentation. Use when asked to build a new skill, organize skill resources, design skill descriptions, or validate skill structure for portability across Copilot platforms.

Automatically evaluate the security, safety, and trustworthiness of agent skills from GitHub repositories, websites, or direct .skill file URLs. This skill performs comprehensive assessments including

Comprehensive templates, patterns, and best practices for creating Claude Code subagents and skills. Use when building new agents/skills or need reference examples for proper structure and formatting.

Guide creation of focused single-purpose agents following the One Agent One Prompt One Purpose principle. Use when designing new agents, refactoring general agents into specialists, or optimizing agent context for a single task.

Test agent delegation patterns to verify hierarchy and escalation paths. Use after modifying agent structure.