By thebedcoder
Full SDLC agentic engineering workflow for Claude Code using named specialist agents — research, PRD, stories, implementation, 5-agent parallel review, end-user product docs
Answer questions about the project — searches docs, app-docs, and codebase. Ask anything like "which features lack designs?" or "how do we process payments?"
Scaffold a new project — pick your stack, install deps, create base structure and epic roadmap
Generate UI mockups for the current feature using Figma, Pencil.dev, or Markdown specs
Document multiple features. Add --full on a new project to also generate guides, index, and architecture docs
Interactively document a feature — reads code, asks clarifying questions, writes MDX
Convention and documentation consistency checker for agentic engineering reviews. Checks code against CLAUDE.md conventions and flags drift. Activate when /ae:review needs a consistency pass.
Bug hunter for agentic engineering reviews. Finds runtime errors, logic bugs, async issues, null safety violations, and concurrency problems. Runs as parallel subagent during /review. Reports only HIGH CONFIDENCE bugs — clear failure paths, not theoretical risks.
```dart
```go
```javascript
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.
A marketplace of Claude Code plugins by thebedcoder — structured SDLC workflows, product research, and decision-making tools. Installs into Claude Code as a plugin marketplace, or into any other coding agent (Cursor, Codex, Copilot, Cline, Windsurf, Aider, Gemini CLI, Zed, OpenHands) via a portable shell installer.
| Plugin | What it does |
|---|---|
agentic-engineering | Full SDLC workflow with named specialist agents — /bootstrap, /init, /feature, /ship, /review, /fix, /doc. Five-agent parallel code review (bugs, requirements, tests, conventions, security). End-user product docs kept in sync. |
jtbd | Jobs-to-Be-Done megaskill — product brief to research, personas, competitor analysis, landing page copy, and platform-native ad scripts. Five chainable modes powered by parallel specialist agents. |
premortem-skill | /premortem <plan> — assumes the target failed 6 months from now, dispatches one investigator per failure reason in parallel, synthesizes the most likely failure, hidden assumptions, and a revised plan. |
Each plugin has its own README with the full workflow and command reference.
/plugin marketplace add thebedcoder/skills
/plugin install agentic-engineering@thebedcoder
/plugin install jtbd@thebedcoder
Updates flow through the marketplace — no shell re-run needed.
The top-level install.sh writes a portable rules file (AGENTS.md, .cursor/rules/*.mdc, .clinerules, .windsurfrules, GEMINI.md, CONVENTIONS.md, .github/copilot-instructions.md, etc.) into the right place for your tool.
# One-shot, autodetect installed tools
curl -fsSL https://raw.githubusercontent.com/thebedcoder/skills/main/install.sh | bash -s -- --tool=auto
# Or pick a specific tool + skill
curl -fsSL https://raw.githubusercontent.com/thebedcoder/skills/main/install.sh | bash -s -- --skill=agentic-engineering --tool=cursor
# From a local checkout
bash install.sh --skill=jtbd --tool=codex
bash install.sh --help # full options
Supported tools: claude-code, cursor, codex, copilot, copilot-cli, cline, windsurf, aider, gemini, zed, openhands, agents-md, auto.
Scope: --scope=project (default) writes to the current directory. --scope=user writes to the tool's global config where supported (Cursor, Codex, Gemini).
Re-running the installer is idempotent — blocks are wrapped in <!-- <plugin>:start --> … <!-- <plugin>:end --> markers and replaced in place.
.
├── .claude-plugin/
│ └── marketplace.json # Claude Code marketplace manifest
├── agentic-engineering/ # plugin
├── jtbd/ # plugin
├── premortem-skill/ # plugin (not yet in marketplace.json)
├── install.sh # universal multi-tool installer
├── LICENSE
└── CLAUDE.md # contributor guidance for AI assistants
Each plugin follows the same internal layout — see CLAUDE.md for the per-plugin structure and the conventions to follow when contributing.
See LICENSE.
npx claudepluginhub thebedcoder/skills --plugin agentic-engineeringJobs to Be Done megaskill — product brief to research, personas, competitor analysis, landing page copy, and platform-native ad scripts, powered by 5 parallel specialist agents
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
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
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.
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
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.