This-HW

agent-teams

Large-scale parallel work guidance. Routes 10+ parallel independent tasks to native dynamic workflows (ultracode), with legacy experimental Agent Teams as fallback.

auto-dev

Automated development pipeline. Runs a completed Planning Work through Development and Validation phases end-to-end.

Code & Development Listed

debug

Analyze errors and apply fixes. Use when you have an error message, traceback, or failing log to diagnose.

doc-coauthoring

AI-assisted documentation authoring. Use when writing, reviewing, or updating technical documents and READMEs.

mcp-builder

Build and configure MCP servers. Use when scaffolding a new Model Context Protocol server or adding tools to an existing one.

Code & Development Listed

multi-perspective-review

Multi-perspective collaborative review of plans or documents. Ten expert viewpoints deliberate in 3 rounds to reach consensus.

plan-task

Structured task planning using Work files. Use for any new feature, bug fix, or project that needs a task breakdown before implementation.

Code & Development Listed

review

Run a full code review on current changes or specified files. Runs ruff lint, review-code agent, and security scan in sequence.

Propose improvements to agent/skill/rule definitions from accumulated feedback-ledger defects and eval reports. Proposal-only - applies changes exclusively after evals show no regression AND the user approves. Trigger with /self-improve.

skill-creator

Create new Claude Code skills. Applies standard templates and best practices to scaffold a skill file automatically.

web-research

Research external information using MCP servers. Use when users need to find documentation, compare technologies, or research best practices.

child-session

Discipline a worker session loads at dispatch time — verify the brief's premises before implementing, work only on its own branch, and report in the fixed completion format. Use when a session has been dispatched as a worker (child) with a brief from a parent control session.

control-loop

Multi-session control discipline for delegating work to worker sessions — investigate, decide, dispatch, verify, and merge. Use when a session is coordinating separate worker sessions or worktrees and needs to know when to delegate versus decide, and how to verify before merging.

eval-forge

Turn an observed agent defect into a machine-checkable eval scenario, generated and self-validated in one step. Use after a defect lands in the feedback ledger, or before changing an agent definition that has no eval coverage. Trigger with /eval-forge.

harness-export

Export the kit's host-neutral rules to AGENTS.md so non-Claude-Code harnesses (Codex, OpenCode, Copilot, Pi, Hermes) follow the same discipline. Use when a repo is worked by more than one agent harness, or after changing rules/. Trigger with /harness-export.

skill-forge

Distill a hard problem you just solved into a reusable skill draft - proposal-only, behind a three-condition threshold. Use after finishing a non-trivial task whose procedure would otherwise die with the session. Trigger with /skill-forge.

agent-creator

Create Claude Code sub-agents with optimal configuration. Use when users ask to create a new agent, custom agent, specialized assistant, or want to configure task-specific AI workflows.

native-watch

Audit Claude Code native feature absorption. Use to compare the kit's components against the latest Claude Code releases and propose absorption-ledger updates. Trigger with /native-watch or on a schedule.

brainstorming

Design and spec before any planning or code. MUST USE before new features, creative work, or any implementation. Explores requirements, proposes approaches, gets design approval, then chains to plan-task.

using-claude-code-kit

Session-start meta-skill. claude-code-kit-specific workflow chain, agent map, and Work system rules (generic skill-invocation discipline is shared with superpowers when present).