ork

Query cross-project usage analytics. Use when reviewing agent, skill, hook, or team performance across OrchestKit projects. Also replay sessions, estimate costs, and view model delegation trends.

Assesses and rates quality 0-10 with pros/cons analysis. Use when evaluating code, designs, or approaches.

Full-codebase audit using 1M context window. Security, architecture, and dependency analysis in a single pass. Use when you need whole-project analysis.

Audits all OrchestKit skills for quality, completeness, and compliance with authoring standards. Use when checking skill health, before releases, or after bulk skill edits to surface SKILL.md files that are too long, have missing frontmatter, lack rules/references, or are unregistered in manifests.

Design exploration with parallel agents. Use when brainstorming ideas, exploring solutions, or comparing alternatives.

Rate-limit-resilient pipeline with checkpoint/resume for long multi-phase sessions. Saves progress to .claude/pipeline-state.json after each phase. Use when starting a complex multi-phase task that risks hitting rate limits, when resuming an interrupted session, or when orchestrating work spannin...

Creates commits with conventional format and validation. Use when committing changes or generating commit messages.

Configures OrchestKit settings. Use when customizing MCP servers, plugin options, or preferences.

Creates GitHub pull requests with validation. Use when opening PRs or submitting code for review.

Creates polished demo videos for skills, tutorials, and CLI demonstrations. Use when producing video showcases, marketing content, or terminal recordings.

OrchestKit doctor for health diagnostics. Use when running checks on plugin health, diagnosing problems, or troubleshooting issues.

explore — Deep codebase exploration with parallel agents. Use when exploring a repo, discovering architecture, finding files, or analyzing design patterns.

Manages OrchestKit feedback system. Use when providing feedback or viewing usage analytics.

Fixes GitHub issues with parallel analysis. Use to debug errors, resolve regressions, fix bugs, or triage issues.

Complete git workflow patterns including GitHub Flow branching, atomic commits with interactive staging, merge and rebase strategies, and recovery operations using reflog. Essential patterns for clean history. Use when managing branches, defining branching strategy, or recovering git history.

OrchestKit skill directory. Use when you want to see available skills or need help.

Full-power feature implementation with parallel subagents. Use when implementing, building, or creating features.

Auto-updates GitHub issues with commit progress. Use when starting work on an issue, tracking progress during implementation, or completing work with a PR.

Read-side memory operations: search, recall, load, sync, history, visualize. Use when searching past decisions, loading session context, or viewing the knowledge graph.

Visualize planned changes before implementation. Use when reviewing plans, comparing before/after architecture, assessing risk, or analyzing execution order and impact.

Creates zero-dependency, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web slides, or create a slide deck for a talk, pitch, or tutorial. Generates single self-contained HTML files with inli...

Walks through the OrchestKit release checklist — build, test, validate counts, changelog, version bump, commit, tag, push. Use when preparing a release, cutting a version tag, or verifying release readiness before pushing to main.

Stores decisions and patterns in knowledge graph. Use when saving patterns, remembering outcomes, or recording decisions.

PR review with parallel specialized agents. Use when reviewing pull requests or code.

Evolves skills based on usage patterns. Use when improving or rolling back skill definitions.

Assess platform upgrade readiness for Claude model and CC version changes. Use when evaluating upgrades.

Validates hook, skill, and agent counts are consistent across CLAUDE.md, hooks.json, manifests, and source directories. Use when counts may be stale after adding or removing components, before releases, or when CLAUDE.md Project Overview looks wrong.

Comprehensive verification with parallel test agents. Use when verifying implementations or validating changes.

Coordinates multiple Claude instances across worktrees. Use when managing parallel development.