handoff
Use when explicitly asked to compact the current Pi session into a local handoff document that a fresh agent can use to continue the work.
manage-scheduled-tasks
Use when creating, editing, validating, manually running, or debugging Pi scheduled task Markdown files managed by the scheduled-tasks extension.
agent-engineering
Use when designing, building, debugging, or reviewing AI coding agent harnesses — single-agent shape (tools, prompts, context, hooks, model selection) or multi-phase workflows (orchestration, subagents, verifiers, ticket-to-PR pipelines). Covers model-specific guidance for Claude 4.x and GPT-5.x families, and platform-specific patterns for Claude Code, the Claude Agent SDK, and Pi. Invoke when the user asks about harness design, scaffold patterns, agent loops, subagent orchestration, verification strategy, context compaction, plan/implement/verify pipelines, or how a particular model changes harness choices.
challenge
Use when stress-testing a concrete plan, proposal, design, architecture decision, or implementation approach before implementation. Challenges material assumptions, failure modes, alternatives, and evidence gaps; use review for completed changes.
clarify
Use when requirements, scope, product behavior, edge-case policy, acceptance criteria, or design intent are fuzzy and need an interview before planning or implementation.
create-html-artifact
Use when the user asks to create or polish a standalone HTML artifact such as an HTML report, interactive explainer, visual plan, dashboard, slide deck, diagram, prototype, or throwaway HTML tool.
create-jira-ticket
Use when creating a Jira ticket to plan upcoming work. Guides ticket drafting with clear structure, self-contained context, and testable acceptance criteria, then creates the ticket via the available Jira/Atlassian broker tool.
create-skill
Use when creating a new skill or updating an existing skill
diagnose
Use when debugging bugs, failures, exceptions, flaky behavior, regressions, or performance problems where the cause is not already proven.
frontend-design
Use when the user asks to build web components, pages, or applications that need distinctive, production-grade frontend interfaces with high design quality
handoff-to-worktree
Use when explicitly asked to hand a task to a new Pi agent in a newly created Herdr-managed Git worktree.
herdr
Use when the user explicitly mentions Herdr, asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent, or asks to create, open, list, remove, or otherwise manage a Git worktree. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires HERDR_ENV=1.
plan
Use when turning a clarified implementation request, feature idea, bugfix, refactor, workflow change, or design discussion into an execution-ready plan that a fresh coding agent can implement autonomously, especially before running /goal.
playwright
Reference skill for browser automation: web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
review
Use when reviewing code changes, a working tree, branch, commit range, pull request, patch, or implementation against acceptance criteria. Prepares evidence, runs deterministic checks, invokes the saved review workflow, and presents its findings.
test-driven-development
Use when implementing a feature or bugfix that involves writing meaningful application logic