By yo-steven
Your AI development teammate. Turns a story file into a shipped, reviewed, and tested feature via orchestrator → architect → developer → PR reviewer → QA → Playwright.
Initialises the ShipMate pipeline in the current project. Creates the stories folder, sets up the pipeline state directory, and runs the initial codebase scan to generate project-doc.md and AGENTS.md.
Master pipeline entry point. Routes requirements from a story file through scan → orchestrate → architect → implement → review → QA → playwright stages. Use /ship stories/foo.md to start, /ship status to check progress, /ship resume to continue.
Architect agent. Reads orchestrator-output.md, AGENTS.md, and project-doc.md to produce a numbered step-by-step implementation plan. Pauses for human approval before implementation begins.
Developer agent. Implements the architect plan step-by-step, guided by AGENTS.md guardrails. Writes tests, leaves no TODOs, and flags plan deviations rather than silently skipping them.
Product Orchestrator agent. Reads the active story file, asks clarifying product questions one at a time, confirms task type (FRONTEND/BACKEND), and produces a complete unambiguous spec in orchestrator-output.md.
Playwright testing agent. Only runs for FRONTEND tasks. Verifies acceptance criteria in a real browser using the page object pattern. Passes on success, routes back to developer on failure.
QA Agent. Tests all acceptance criteria and edge cases from orchestrator-output.md. Generates a structured qa-report.md with pass/fail per criterion and bug triage. Loops back to implement if bugs found (max 2 iterations).
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This repo is a learning experiment by Steven Li based on wshobson/agents.
It is not affiliated with the original project. It records one day's experiment with the codebase.
tools/validate_agent_unique_names.py (+98 lines). Scans all .md files under plugins/, extracts the name field from YAML frontmatter with a lightweight regex-based parser, and reports any name that appears in more than one file. Exits with code 1 if duplicates exist, otherwise 0.tools/tests/test_validate_agent_unique_names.py (+121 lines). Five unit tests covering:
Total: 2 new files, ~219 lines added, 0 lines removed.
This repo is not maintained. Issues filed here will not be addressed. If you want the maintained version of the project, use the upstream repo.
If something here is useful, port it upstream yourself or open an issue on the upstream repo with a link to this work.
The original project workflow files are stored in UPSTREAM_WORKFLOWS_DISABLED/ for reference. They are not active in this snapshot.
The original LICENSE file is preserved verbatim in this repository.
Original project: wshobson/agents Upstream commit at fork time: cbcde3f1f4309f023095181d3e591f983ec7c95d
npx claudepluginhub yo-steven/agents-exploration-20260523 --plugin ship-mateSelf-contained GEO (Generative Engine Optimization) plugin: 7 slash commands orchestrate the pipeline (/01-intake → /07-reaudit), 7 vendored open-source skills supply commodity capabilities (audit, content writing, schema, internal linking, keyword expansion, quality scoring, frontend design) plus one original skill (geo-review-html) that renders interactive client-review HTML, 8 JSON schemas. Zero external deps, zero API keys for the default flow. Per-client folder convention.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.6 and GPT-5.4
Self-improving Claude Code plugin — learns from corrections across sessions via reflexio
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code