research

Build reproducible Showboat demo documents that prove repo behavior with executable markdown. Use when asked to create demos, proof-of-work walkthroughs, or verification artifacts with showboat, especially for tests, CLIs, local services, Aspire AppHosts, and HTTP APIs.

Build reproducible Showboat demo documents that prove repo behavior with executable markdown. Use when asked to create demos, proof-of-work walkthroughs, or verification artifacts with showboat, especially for tests, CLIs, local services, Aspire AppHosts, and HTTP APIs.

Balanced skill for typical development tasks, code review, and implementation work

Coordinator-only agent for orchestrating multi-change runs

Fast, cost-effective skill for simple tasks, quick queries, and small code changes

Read-only researcher for Ito orchestration context gathering

High-capability skill for complex reasoning, architecture decisions, and difficult problems

Implements Ito orchestration work packets and remediation tasks

Apply a Change Proposal. Triggered by the user saying "Apply change <change-id>" or "Implement change <change-id>". Use when implementing, executing, applying, building, coding, or developing a feature, change, requirement, enhancement, fix, or modification. Use when running tasks from a spec, proposal, or plan.

Archive a completed change and update main specifications. Use when the user has finished implementing and wants to integrate the change into the main codebase.

Use for open-ended design exploration and idea refinement before scoping a concrete Ito change.

Create atomic git commits aligned to Ito changes. Use when you want to commit work after applying a change, optionally with auto-mode.

Start a feature-oriented Ito change proposal with feature-biased intake and schema recommendations.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work — presents structured options for merge, PR, or cleanup

Start a fix-oriented Ito change proposal with fix-biased intake and schema recommendations.

List Ito changes, archived changes, specs, or modules with status summaries and intelligent interpretation.

Run an ito ralph loop for a change, module, or repo-ready sequence, with safe defaults and automatic restart context on early exits.

Use Ito's configured memory provider to capture, search, and query project knowledge. Activate when users ask to remember, recall, search memory, query memory, save learnings, or use Ito memory. Provider-agnostic: routes through `ito agent instruction memory-capture`, `memory-search`, and `memory-query` rather than calling ByteRover or another backend directly.

Set up orchestration defaults, presets, and workflow guidance for a repo.

Coordinate multi-change runs with gates, run state, and remediation.

Repo-specific workflow conventions consumed by the orchestrator.

Use when you need stable absolute paths (project/worktree/.ito/worktrees) without embedding machine-specific paths into committed files

Clarify a requested change before scaffolding a proposal, then recommend the next workflow lane and schema.

Use when creating and writing an Ito change proposal (new change or existing change id). Delegates to Ito CLI instruction artifacts.

Conduct structured research for feature development, technology evaluation, or problem investigation. Use when the user needs to explore options, analyze trade-offs, or investigate technical approaches.

Review and validate Ito changes, specs, or implementations. Use when the user wants a quality check, code review, or validation of project artifacts.

Unified entry point for ito commands with intelligent skill-first routing and CLI fallback.

Use when executing implementation plans with independent tasks in the current session using subagents

Use Ito tasks CLI to manage tasks.md (status/next/start/complete/shelve/add).

Use when tests need to be run with minimal output noise and delegated execution; routes test runs through the dedicated ito-test-runner subagent and returns curated pass/fail evidence.

Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output.

Refresh Ito-managed assets in a project and prune stray skills/commands left behind by renames or deprecations. Use when the user asks to "update Ito", "refresh Ito templates", "update repo to latest Ito", or says the project is on an older Ito. NOT for editing individual skills, authoring new templates, or shipping Ito releases.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when discovering, finding, invoking, or loading skills. Ensures skills are invoked BEFORE responding.

Use before claiming work is complete, finished, fixed, or passing — requires running verification commands and confirming output before making success claims

Ito workflow delegation - delegates all workflow content to Ito CLI instruction artifacts.

Optional repo-specific supplement for orchestrators after `ito agent instruction orchestrate` has been loaded.

Use for sequential per-task subagent delegation within one Ito change in the current session.

Refresh Ito-managed assets in a project, prune stray skills/commands left behind by renames or deprecations, and wire `ito validate repo` into the project's pre-commit hook (auto-detected framework, dry-run + approval). Use when the user asks to "update Ito", "refresh Ito templates", "update repo to latest Ito", "wire pre-commit", or says the project is on an older Ito. NOT for editing individual skills, authoring new templates, or shipping Ito releases.