hero-skills

Create and converge a single root ARCHITECTURE.md — boundaries, dependency rules, invariants, decisions the code cannot state. sync converges (propose-confirm-write); review reports drift read-only.

Initialize Hero for a project. Investigates the repo, auto-detects the stack, confirms findings with smart questions, and creates HERO.md that all skills use.

Drive a small task end-to-end — plan, implement, simplify, push (tests included), self-review, mark ready, await review, respond, ship. No args: resume the current goal (gated). Small, low-risk PRs only.

Brainstorm and grill an idea one question at a time into principal-level shared understanding, captured as dependency-aware work-items.

Sync a feature roadmap between the source repo and the HERO.md-configured target-design repo; features are SLC vertical slices with subtasks, definition of done, design feedback, and staleness flags.

Abandon or pause work on a branch that hasn't merged — stash uncommitted changes, switch to the default branch, and clear conversation context.

Run pre-flight checks for the hero-skills pipeline. Catches missing tooling, stale HERO.md, .env mismatches, busy ports — before any step does destructive work.

Distill the current conversation into one self-contained work-item — context, decisions, remaining work, acceptance criteria — for a downstream agent with zero context from this session.

Audit the codebase for hardening opportunities — dependency CVEs, container CVEs (Scout + Trivy), code-level robustness — read-only, and emit execution-ready plans as .plans items. Never edits source.

Test (verify + smoke), commit, push, and open a draft PR with a CI report. Pass test to run only the test phase, ready for a non-draft PR, or a target branch to merge into.

Refactor a project's UI into atomic components (atoms/molecules/organisms/templates), sourcing primitives from a design-system registry when one is configured (default @aihero) or stock shadcn otherwise, and codemod off-token styling. Use when asked to recomponentize, refactor UI, adopt a design system, or clean up component structure.

Trigger auto-approve on a PR, wait for the verdict, merge if it passes, and reset to the default branch. Use after hero-skills:review-pr and any bot review when the PR is ready to ship.

Scaffold a new project. Supports standalone repos or monorepo subprojects. Creates Python (FastAPI/CLI/library), full-stack (FastAPI + Next.js/Vite), or Node.js projects with AGENTS.md.

Read PR review comments, fix the code issues they raise, and resolve the conversations on GitHub. Handles the full respond-to-feedback cycle.

Review a PR with the pr-review-toolkit agents plus a security pass. No argument reviews your own draft PR and applies fixes. A PR number reviews the author's code via inline comments, no edits.

Audit the hero-skills plugin. Checks skill quality, consistency, DRY violations, HERO.md field coverage, and readability. Use before releasing changes to the plugin.

Create a new Claude Code skill, subagent, rule, or hook. Guides through trigger conditions, success criteria, and writes a well-structured SKILL.md. Use when extending Claude.

Set up a developer's local environment. Reads HERO.md, checks required tools, guides through git config, CLI auth, and missing dependencies. Per-developer — never modifies shared files.