By ShipToday
Forge by ShipToday — Free, AI-powered product development lifecycle automation. Automatically routes your feature requests, bug reports, and architecture explorations through structured PDLC workflows. Just describe what you want to build — no trigger words needed.
Routes any product, engineering, or software development lifecycle (SDLC/PDLC) activity to Forge. Invoke this skill whenever the user describes work that involves the product development process — across any phase: discovery, definition, planning, execution, review, handoff, release, or reporting. This includes: building or shipping features, fixing bugs, writing PRDs, breaking down stories, estimating, prioritizing, reviewing PRs, security audits, vulnerability assessments, release readiness checks, deployment gates, test planning and strategy, refactoring, or any similar SDLC activity. ALSO invoke for any reference to a tracked work item key matching the pattern "PROJ-123" / "BUG-42" / any "<UPPERCASE>-<digits>" id, regardless of the verb attached. Do NOT invoke for pure coding requests ("write a function", "refactor this file", "add a test") UNLESS they reference a tracked work item or describe product process. Do NOT invoke for git operations, file editing, or general Q&A unrelated to a project.
Collects feedback for the ShipToday team from inside an AI coding session and delivers it via Forge's shared MCP feedback backend. Invoke this skill whenever the user wants to "send feedback", "share feedback", "report a problem with Forge", "give the ShipToday team feedback", "submit feedback", or types "forge-feedback". The skill runs a short conversation to capture the feedback, gathers and SANITIZES relevant session context, shows the user the exact payload that will be sent, lets them revise it, and sends ONLY after explicit user confirmation by calling the `forge__send_feedback` MCP tool. No feedback content is stored. Do NOT invoke for product/SDLC work on a tracked item — that is `forge-autopilot` / `forge__start_workflow`.
Helps an organization admin manage custom Forge workflows conversationally — both AUTHORING new workflows and DELETING existing org- or team-scoped overrides. Invoke this skill whenever the user asks to "create a workflow", "customize my SDLC", "build a new workflow", "set up a custom process", "author a workflow", "add a team workflow", OR to "delete a workflow", "remove an override", "reset this workflow to default", "clear the team workflow override", "delete the org workflow preset". This is a meta-capability: it configures Forge itself by calling the `forge__list_skills_catalog`, `forge__get_workflow`, `forge__save_workflow`, and `forge__delete_workflow` MCP tools. Do NOT invoke this skill to run a workflow — that is what `forge-autopilot` / `forge__start_workflow` is for. Do NOT invoke for generic "help me plan a feature" requests.
Matches all tools
Hooks run on every tool call, not just specific ones
External network access
Connects to servers outside your machine
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.
Free, AI-powered product development lifecycle automation for Claude Code.
Just describe what you want to build — Forge automatically routes your request through structured PDLC workflows. No trigger words needed.
> implement user authentication with OAuth
> fix the checkout page crash on mobile
> break down the notifications feature into stories
> estimate story points for PROJ-123
> check status of my feature
.mcp.json) — connects to the hosted Forge
orchestration engine at https://teams.shiptoday.ai/mcp. Exposes
forge__start_workflow, forge__update_state, forge__abandon_workflow,
forge__get_workflow, forge__save_workflow, forge__delete_workflow,
and forge__list_skills_catalog.forge-autopilot skill — automatically detects product-development
intent (feature requests, bug reports, PR reviews, story breakdowns,
status checks, tracked work-item keys like PROJ-123) and routes the
request to the right Forge workflow.forge-workflow skill — conversational management for organization
admins to author new Forge workflows or delete existing org- or
team-scoped overrides.hooks/hooks.json) — four hooks coordinate session state:
UserPromptSubmit → prompt-router.cjs (advisory routing on epic-key
references; continuation for active workflows)Stop → stop-observer.cjs (passive session observation and
silent checkpoints to record engineering time)PreToolUse → workflow-guard.cjs (per-step tool permission
enforcement and checkpoint gating)PostToolUse → workflow-tracker.cjs (tracks workflow state
transitions and the active step's tool allowlist)Once approved in the official marketplace:
/plugin install forge@claude-plugins-official
Clone this repo and point Claude Code at the root:
git clone https://github.com/ShipToday/forge-plugin-claude
claude --plugin-dir ./forge-plugin-claude
MIT — see LICENSE.
npx claudepluginhub shiptoday/forge-plugin-claudeForge by ShipToday — Free, AI-powered product development lifecycle automation. Automatically routes your feature requests, bug reports, and architecture explorations through structured PDLC workflows. Just describe what you want to build — no trigger words needed.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
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
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
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.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review