By jbaham2
Turn any service's documentation into a Claude Code expert plugin: map the docs, fill the builder prompt, then build the plugin — as guided slash commands.
Stage 3 — execute a filled <topic>-plugin-prompt.md to build the actual Claude Code plugin.
Stage 2 — research a service and fill the plugin-builder template into a runnable prompt.
Run the full docs→plugin pipeline (map-docs → build-prompt → build-plugin) from a documentation URL.
Stage 1 — interactively map a documentation site into a complete coverage roadmap.
This skill should be used when the user asks to "run the plugin-prompt", "execute the builder prompt", "create the expert plugin from this prompt", or wants the actual Claude Code plugin built from an already-filled <topic>-plugin-prompt.md (Stage 2 output MUST exist). This is Stage 3 of the plugin-forge pipeline. Precondition: a filled <topic>-plugin-prompt.md is present. If the user only has docs and no filled prompt, use `forge` (full pipeline) or `build-prompt` (Stage 2) instead.
This skill should be used when the user asks to "build the plugin prompt", "fill in the plugin-creator template", "turn these docs into a builder prompt", "research this service for a plugin", or wants a ready-to-run plugin-builder prompt generated from docs (or a doc roadmap) — Stage 2 only, producing a prompt rather than the built plugin. This is Stage 2 of the plugin-forge pipeline. If the user gives a bare docs URL and wants an end-to-end docs→plugin run (not just the builder prompt), use `forge` instead.
This skill should be used when the user asks to "forge a plugin from these docs", "turn this documentation into a Claude Code plugin", "run the full plugin pipeline", "go from docs URL to plugin", or gives a documentation link and wants the entire docs→plugin workflow run end-to-end. Orchestrates the three plugin-forge stages in sequence.
This skill should be used when the user asks to "map the docs", "build a doc roadmap", "crawl this documentation site", "create a coverage map of these docs", or wants an exhaustive inventory/coverage map of a documentation website (overviews, features, guides, examples, cookbooks, API reference, and in-page headers) — Stage 1 only. This is Stage 1 of the plugin-forge pipeline. If the user gives a bare docs URL and wants an end-to-end docs→plugin run (not a roadmap specifically), use `forge` instead.
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 Claude Code plugin marketplace hosting plugin-forge — a plugin that turns any service's documentation into a Claude Code expert plugin.
This repository is a marketplace catalog. The plugin itself lives in
plugin-forge/ — see its README for full docs.
.
├── .claude-plugin/
│ └── marketplace.json # the marketplace catalog (source → ./plugin-forge)
└── plugin-forge/ # the plugin (manifest, commands, skills)
└── README.md # full plugin documentation
From inside Claude Code:
/plugin marketplace add jbaham2/plugin-forge
/plugin install plugin-forge@plugin-forge-marketplace
Give it a documentation URL and it builds a complete expert plugin for that service through a three-stage pipeline:
map-docs <docs-url> → <topic>-doc-roadmap.md (Stage 1: map the docs)
build-prompt <docs-url> → <topic>-plugin-prompt.md (Stage 2: fill the builder prompt)
build-plugin <topic>-plugin-prompt.md → ./<topic>-plugin/ (Stage 3: build the plugin)
forge <docs-url> → runs all three end-to-end
Full usage, a worked example, and design notes are in the plugin README.
MIT — see plugin-forge/LICENSE.
npx claudepluginhub jbaham2/plugin-forge --plugin plugin-forgeMakes Claude an expert at LlamaCloud (Parse, Extract, Classify, Split, Sheets, Cloud Index), LiteParse, and the LlamaIndex framework + agentic Workflows. Skills hold durable judgment; the wired LlamaIndex docs MCP fetches current API facts live.
Makes Claude an expert at herdr, the agent-aware terminal multiplexer: herding fleets of agents, designing and restoring workspace/tab/pane layouts, monitoring agent state, managing sessions, and authoring configuration. Vendors the official herdr agent skill and complements it with workflow judgment.
Expert system for Langfuse setup, observability, prompt management, evaluation, and monitoring. Bundles distilled knowledge, skills, agents, commands, and hooks.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
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.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.