Html Artifacts
Create or revise polished, standalone HTML documents for direct human reading. Use for technical documents, proposals, reports, specifications, guides, and review artifacts when the user wants a clear, attractive HTML deliverable.
Swe Plan
Create an optional delivery plan from a specification. Use only when implementation needs multiple independently verifiable slices, sessions, agents, migrations, backfills, or rollout coordination.
Swe Review
Review an SWE brief, research report, spec, delivery plan, execution state, implementation diff, branch, or pull request. Use for fresh-context, evidence-backed findings before the human chooses the next action.
Swe Worktree
Create an isolated git worktree for an SWE change workspace. Use before implementation when the user wants the change isolated from the current working tree.
Swe Execute
Implement a spec or delivery plan by dispatching each slice to a fresh sub-agent, verifying the result, and maintaining execution state. Use when the user chooses to implement from `spec.html` or an optional `plan.md`.
Swe Spec
Create and progressively deepen a single evolving specification document for a change, from high-level structure down to exact contracts
Git
Use when user asks for git operations: branch creation, committing changes, creating pull requests.
Handoff Session
Use when the user asks to summarize, compact, hand off, or create an end-of-session summary for the next agent.
Swe Shape
Turn a software change idea into a concise, repository-grounded product brief. Use before designing or implementing non-trivial features, fixes, refactors, or migrations.
Swe Research
Answer a concrete repository, dependency, external-system, feasibility, behaviour, or impact question and preserve the evidence for reuse. Use when the answer is worth keeping — codebase inspection, authoritative sources, live probes, or disposable experiments.
Prompt Writer
Use when creating, reviewing, or revising prompts, system prompts, developer instructions, agent policies, prompt templates, eval prompts, or skill files consumed by LLMs and AI agents. Routes to OpenAI, Anthropic/Claude, or generic prompt-writing guidance based on the target model/provider.