HazAT

Solo-native planning workflow. Use when asked to "plan", "brainstorm", "design", "create a plan", "I want to build", or "let's build". Runs a scout, opens a planner that is interactive through approach selection, creates Solo todos, then automatically executes and reviews through Solo subagents and scratchpads.

Start a fresh Solo Pi session from the current conversation. Use when asked to hand off, continue in a clean context, or run `/handoff <new prompt>`. Writes a Solo scratchpad summary of the important current-session context, then launches an interactive Solo agent in the same project with that handoff and the new prompt.

Write clear Solo todos that workers can execute without losing architectural intent. Use when asked to "create todos", "write todos", "break into tasks", "plan todos", or create work items from a plan. Ensures each todo has outcomes, examples, constraints, and verification criteria.

Read this skill before making git commits

Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.

Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, planning, writing, registration, and verification.

Efficiently read and analyze pi agent session JSONL files. Use when asked to "read a session", "review a session", "analyze a session", "what happened in this session", "load session", "parse session", "session history", "go through sessions", or given a .jsonl session file path.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Write knowledge-transfer git commits for Manifest projects. Use when making git commits. Commits include a typed subject line and a detailed body explaining what changed, why, and how.

Contribute framework improvements back to the upstream Manifest repo via PR. Use when the user says "contribute back", "open a PR upstream", "send this fix upstream", or wants to share a framework improvement.

Work with Manifest's frontend system — building, serving, dev workflow, debugging, and presets. Use when creating pages, components, debugging frontend errors, or configuring the build.

Structured implementation flow for Manifest features — from investigation through execution with subagents. Follows the full chain: investigate → clarify → explore → validate → plan → todos → branch → execute → review. No shortcuts. Invoke manually when building a new feature or significant change in a Manifest project.

Reflect on recent large changes and check if the rest of the codebase needs to catch up. Use after adding features, installing extensions, changing services, updating schemas, or making any significant structural change.

Resolve merge conflicts from upstream syncs or other merges. Preserves application identity while accepting framework and tooling improvements. Use when you see merge conflict markers or the user says "resolve conflicts", "fix merge", or "merge conflict".

Code review guidelines and quality rubric for Manifest projects. Covers framework conventions, feature structure, schema quality, and security. Shared by the reviewer subagent and available for manual reviews. Use when reviewing code changes.

Update your Manifest project from the upstream base repository. Use when the user says "manifest update", "update from upstream", or "pull upstream changes". Computes the aggregate diff since last sync and applies it atomically.

Create a release, publish to npm, and create a GitHub release. Use when asked to "release", "cut a release", "publish", "bump version", "create release", "npm publish".

Show native UI from scripts and agents — dialogs, forms, visualizations, floating widgets, cursor companions. Supports macOS, Linux, and Windows. Use when you need to display HTML to the user, collect input, show a chart, render markdown, or create any visual interaction without a browser.

Run the integration test suite and verify all sessions end-to-end. Use when asked to "run integration tests", "run e2e tests", "test before release", "verify integration", "run the full test suite", "check everything works".

Create a GitHub release with changelog. Use when asked to "release", "cut a release", "publish version", "bump version", "create release".

Cut a new release of the badge gem — verify via make smoke, build, tag, push, publish to rubygems, and write a GitHub release matching the project's 2018-era house style. Use when asked to "release", "cut a release", "publish a new version", "tag a release", "new release", "/release", "ship it", or "prepare a release".

Create a GitHub release with changelog. Use when asked to "release", "cut a release", "publish version", "bump version", "create release".

Create a GitHub release with changelog. Use when asked to "release", "cut a release", "publish version", "bump version", "create release".

Guides end-to-end onboarding for the Word Fixer app from a clean checkout to a working installed app. Use when asked to "onboard word fixer", "set up word fixer", "install word fixer", "get word fixer working", "configure word fixer", or "help me set up this app". Checks repo state, pi availability, config, auth, installation, and macOS Accessibility permission, then proposes and executes the next actions with user confirmation.

Use when testing UI changes, verifying builds work, or validating extension behavior on PoE trade website or Storybook

Create a GitHub release with changelog. Use when asked to "release", "cut a release", "publish version", "bump version", "create release".