Bo

Analyze code complexity and identify refactor targets using radon and gocyclo.

Extract knowledge from session transcripts to identify decisions, learnings, failures, and patterns.

Generates, validates, and syncs documentation for any repository type. Produces code-maps, checks doc coverage, finds missing docs, and validates existing documentation against code. Triggers: doc, documentation, code-map, doc coverage, validate docs, generate docs, sync docs, update docs, find missing docs.

Expert code review specialist. Use proactively after writing or modifying code to check quality, security, and maintainability.

One command to set up the full AgentOps product layer, filling gaps as needed.

Fork-based PR implementation with mandatory isolation checks for clean contributions.

Plan open source PR contributions with clear scope and acceptance criteria.

Quickly onboard new users to AgentOps with a streamlined setup guide.

Wrap up completed work and extract valuable insights through a structured post-mortem process.

Quickly capture insights and lessons learned for future reference.

Automate project scaffolding, component generation, and CI/CD setup with ease.

Execute a seamless test, commit, and push workflow in one go.

Provides shared reference documents for multi-agent skills, enhancing collaboration.

Meta skill for the AgentOps operating model, facilitating coding agent workflows.

Orchestrates the full validation phase to ensure implementation quality and extract learnings.

Interactive overnight operator mode for Dream, facilitating setup, runs, and reports.

Multi-model consensus council. Spawns parallel judges with configurable perspectives. Modes: validate, brainstorm, research. Triggers: "council", "get consensus", "multi-model review", "multi-perspective review", "council validate", "council brainstorm", "council research".

Compiles raw knowledge artifacts into an interlinked markdown wiki.

Safe, incremental refactoring with regression testing at each step.

Execute a single issue with full lifecycle. Triggers: "implement", "work on task", "build this", "start feature", "pick up next issue", "work on issue".

Streamline your PR preparation with automated validation and structured body generation.

Spawn isolated agents for parallel task execution with automatic runtime selection.

Cross-platform skill converter that transforms AgentOps skills into formats for Codex and Cursor.

Generate a comprehensive PRODUCT.md by interviewing users about their product's mission, personas, and competitive landscape.

Build and maintain a compounding external-knowledge wiki from clipped articles, papers, and transcripts. Triggers: "llm wiki", "ingest this", "second brain", "compile my reading", "wiki lint", "what do we know about <topic>". Based on Andrej Karpathy's LLM Wiki pattern (April 2026).

Deep codebase exploration and analysis. Use for understanding code architecture, finding patterns, and gathering context before making changes.

Operationalize a mature .agents corpus into actionable knowledge surfaces.

Monitor the health of your knowledge flywheel by checking its velocity, pool depths, and staleness.

Release your software. Pre-flight validation, changelog generation, version bumps, release commit, tag, curated release notes. Boundary: everything up to the git tag. Triggers: "release", "cut a release", "prepare release", "release check".

Comprehensive code validation tool that assesses readiness for deployment.

Manage holdout scenarios for behavioral validation, ensuring isolation from implementing agents.

Design and validate Grafana dashboards for OpenShift/Kubernetes operations to enhance platform health visibility.

Orchestrates the full discovery phase for project planning and research.

Provides language-specific coding standards and validation rules for various programming languages.

Validate pull requests for isolation, scope creep, and quality before submission.

Validate plans or specs before implementation using multi-model judgment.

Generate a gold-standard README for any project with guided interviews and validation.

Test generation, coverage analysis, and TDD workflow. Triggers: "test", "generate tests", "test coverage", "write tests", "tdd", "add tests", "test strategy", "missing tests", "coverage gaps".

Inject relevant knowledge into session context for enhanced decision-making.

Explore upstream codebases to streamline open source contributions.

Recovers context after compaction by detecting in-progress sessions and summarizing recent work.

Performance profiling and optimization tool for various programming languages.

Manage and track fitness goals with the GOALS.yaml and GOALS.md specifications.

Create structured handoff for session continuation. Triggers: handoff, pause, save context, end session, pick up later, continue later.

Consolidate knowledge across multiple rigs with a single command.

Orchestrate multiple Codex agents to execute focused tasks efficiently.

Deep codebase exploration. Triggers: research, explore, investigate, understand, deep dive, current state.

Automated skill maintenance tool that detects and fixes common skill issues.

Manage git-based issue tracking with bd CLI for efficient task organization.

Automate epic execution hands-free until all tasks are completed.

Reinstall all AgentOps skills globally from the latest source. Triggers: "update skills", "reinstall skills", "sync skills".

Composable security suite for binary and prompt-surface assurance with modular testing primitives.

Review incoming PRs, agent-generated changes, or diffs. Structured review with security, correctness, performance, and maintainability checks. Triggers: "review", "review PR", "review changes", "code review", "review this PR", "review agent output", "check this diff".

Systematically investigate bugs or perform proactive code audits.

Access up-to-date OpenAI documentation for building with APIs and products.

Continuous repository security scanning and release gating. Triggers: "security scan", "security audit", "pre-release security", "run scanners", "check vulnerabilities".

Reverse-engineer products into feature catalogs, code maps, and specifications with verification gates.

Autonomous improvement loop for continuous code evolution and issue resolution.

Manage and track progress in the RPI workflow with permanent gates.

Trace design decisions and concepts through session history, handoffs, and git.

Trace knowledge artifact lineage and identify stale citations or orphans.

Epic decomposition into trackable issues. Triggers: "create a plan", "plan implementation", "break down into tasks", "decompose into features", "create beads issues from research", "what issues should we create", "plan out the work".

Product validation gate for RPI pipeline. Validates goal alignment with PRODUCT.md before discovery. Checks: gap alignment, persona fit, competitive differentiation, precedent, scope boundaries. Council-gated with --preset=product. Triggers: "design", "product validation", "validate product fit", "design gate".

Scaffold and audit OSS documentation packs for open source projects.

Conduct persona-based adversarial validation to ensure usability of docs and skills.

Conduct dependency audits, updates, and vulnerability scans for various ecosystems.

Single-screen dashboard showing current work, recent validations, flywheel health, and suggested next action. Triggers: "status", "dashboard", "what am I working on", "where was I".

Clarify goals and explore approaches before planning a solution.

Orchestrates the full RPI lifecycle with a single command, delegating to phase-specific skills.

Manage operational contracts for autonomous development loops with ease.

Analyze PR outcomes to improve future contributions by learning from accept/reject patterns.

AgentOps enhances coding agents with bookkeeping, validation, and reusable flows.