Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By ai-hero
Automate the full development lifecycle for AI Hero agents: scaffold projects, manage git workflows with conventional commits and PR automation, run quality checks (linting, tests, security scans), and generate architecture documentation with Mermaid diagrams.
npx claudepluginhub ai-hero/hero-skills --plugin hero-skillsAudit the hero-skills plugin. Checks skill quality, consistency, DRY violations, HERO.md field coverage, and readability. Use before releasing changes to the plugin.
Check pipeline status or cluster health. Default is CI/CD for the current branch.
Smart commit - reviews changes, groups logical changesets, and creates conventional commits. Runs pre-commit hooks if available.
Create a feature branch from a short description of what you'll do. Names the branch using the repo's branch convention from HERO.md.
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 CLAUDE.md.
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Implementation planning, execution, and PR creation workflows with multi-agent collaboration
Language-agnostic development process harness implementing the Stateless Agent Methodology (SAM) 7-stage pipeline with ARL human touchpoint model and Voltron-style language plugin composition. Provides orchestration, workflows, planning, verification, and testing methodology that any language plugin can compose with.
Helder's personal SDLC toolbelt for AI coding agents — from PRD to ship. Bundles the tracer-bullet workflow alongside TDD, code review, audits, and shipping skills.
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
AI-powered agents for specialized development tasks
Persona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
An opinionated development workflow for Claude Code — customizable to your opinions.
Install • Quick Start • Commands • Config • Extending
Most dev work follows the same loop: grab a ticket, plan, implement, test, review, commit, push, monitor. But every team does it slightly differently — different PM tools, different CI, different deploy targets.
Hero Skills gives you slash commands for the entire dev lifecycle that adapt to your stack. Configure once with HERO.md, then every skill knows your conventions, your tools, and your preferences.
git clone https://github.com/ai-hero/hero-skills.git ~/.claude/plugins/hero-skills
Skills are immediately available in any Claude Code session. No restart needed.
Three pieces ride along with one-shot — install them so Steps 7 (push-draft), 8 (self-review), 4 (e2e), and 12 (ship) work out of the box:
1. GitHub CLI (gh) — required by push-pr, review-pr, respond-to-pr, and ship-pr for every PR / comment / workflow operation. Without it, every step from push-draft onward fails immediately.
# macOS (Homebrew)
brew install gh
# Linux (Debian/Ubuntu)
sudo apt install gh
# Other platforms: https://cli.github.com/
Then authenticate with the repo scope (required for PR creation, merge, and gh secret set):
gh auth login -s repo
hero-skills:preflight verifies both presence and the repo scope.
2. pr-review-toolkit plugin — provides the five review agents that hero-skills:review-pr runs in parallel (code-reviewer, silent-failure-hunter, pr-test-analyzer, comment-analyzer, type-design-analyzer). From inside Claude Code:
/plugin install pr-review-toolkit
Or from the host shell:
claude plugins add pr-review-toolkit@claude-plugins-official
If you skip this, hero-skills:review-pr still runs but produces a much thinner review.
3. Playwright MCP server — drives the browser smoke test in hero-skills:smoke-ui (Step 4 e2e). Requires Node.js 18+ (check with node --version):
claude mcp add playwright npx @playwright/mcp@latest
Use --scope user to share the registration across every project on the machine, or --scope project to commit it to the repo. Without this, the e2e step renders (–) (skipped) and you lose the UI regression check before commits land.
# 1. Configure your project (run once per repo)
hero-skills:init-hero
# 2. Plan work from a ticket — Plan Mode drafts the approach,
# approve it, and Claude implements in the same conversation
hero-skills:plan-work PROJ-123 # Steps 1–2: plan, implement
# 3. Verify, simplify, commit, push as draft, then review your own PR
hero-skills:test-changes # Step 3: lint/typecheck/unit tests
hero-skills:smoke-ui # Step 4: Playwright smoke (UI projects only)
/simplify # Step 5: tidy the dirty diff
hero-skills:commit-changes # Step 6: conventional commit
hero-skills:push-pr # Step 7: opens a DRAFT PR
hero-skills:review-pr # Steps 8–9: parallel review agents, fixes, then mark-ready gate
# 4. Wait for the review bot, address its feedback, then ship
# (the wait in Step 10 is implicit — respond-to-pr only runs once the bot replies)
hero-skills:respond-to-pr # Step 11: address Copilot/CodeRabbit/Greptile inline comments
hero-skills:ship-pr # Step 12: @auto-approve, merge, reset to default branch