Use when a design spec or approved requirements need to become a concrete, step-by-step implementation plan before code changes.
Use when a design discussion is ready to be written into a spec document, before any implementation planning. Synthesizes the conversation into a spec, runs a fresh-eyes self-review subagent, and gates on user approval before handing off to writing-plans.
Autopilot for autonomous feature shipping from brainstorm to PR using .workbench/autopilot.md.
Use before creative work to clarify intent, requirements, and design through sequential question and answer.
Use when facing two or more independent tasks that can be worked on concurrently without shared state or sequential dependencies.
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 personal plugin marketplace for Claude Code and Codex.
The two runtimes use separate plugin metadata, but the skills are single sourced. Claude Code reads .claude-plugin metadata. Codex reads .codex-plugin metadata and .agents/plugins/marketplace.json. Both point at the same plugins/<plugin>/skills/ directories.
| Skill | Plugin | What it does |
|---|---|---|
jira | atlassian | Search Jira issues, create and update tickets, transition workflows, comment, manage sprints, run bulk operations |
confluence | atlassian | Search Confluence pages, read documentation, create and update pages, browse spaces |
gmail | google-workspace | Triage inbox, search and read messages, send mail, manage drafts, labels, and filters via the gws CLI |
calendar | google-workspace | View agenda, create and manage events, check availability, manage calendars via the gws CLI |
research | research | Research complex topics and produce sourced reports |
writing | writing | Draft, review, and finish long form prose |
pyramid | writing | Structure analytical documents with the Pyramid Principle |
tech-doc | writing | Draft, review, and finish technical documentation |
claude-codex-bridge | runtime-bridge | Align Claude Code and Codex project files |
improving-instructions | agent-system-management | Audit and improve agent instruction files |
capturing-session-learnings | agent-system-management | Capture session learnings into the right instruction file |
brainstorming | workbench | Sequential Q&A to clarify design intent |
writing-spec | workbench | Synthesize a design discussion into a spec doc |
visualizing-options | workbench | Browser-based visual companion for layout choices |
using-workbench | workbench | Load Workbench skill rules and routing |
terse-mode | workbench | Explicit session switch for compact token-saving replies |
autopilot | workbench | Ship a feature from brainstorm to PR using a project profile |
verification-before-completion | workbench | Require fresh verification evidence before completion claims |
writing-plans | workbench | Turn approved specs into concrete implementation plans |
test-driven-development | workbench | Enforce test-first RED-GREEN-REFACTOR implementation discipline |
dispatching-parallel-agents | workbench | Split independent tasks across concurrent agents |
subagent-driven-development | workbench | Execute implementation plans with fresh agents and review gates |
systematic-debugging | workbench | Enforce root-cause investigation before proposing bug fixes |
tmux | terminal | Control interactive terminal programs through isolated tmux sessions |
creating-skills | agent-system-management | Scaffold, iterate, pressure-test, and tune skills across the full lifecycle |
frontend-design | frontend-design | Generate distinctive, production-grade frontend interfaces that avoid generic AI aesthetics |
emil-design-eng | frontend-design | Emil Kowalski's design engineering philosophy: animation timing, component polish, and the invisible details that make UI feel right |
Jira and Confluence skills for Atlassian Cloud.
Skills:
/pgoell-claude-tools:jira: Search issues, update tickets, transition status, add comments, and manage sprints/pgoell-claude-tools:confluence: Search pages, read documentation, update pages, and browse spacesGmail and Calendar skills for Google Workspace, powered by the gws CLI.
Skills:
/pgoell-claude-tools:gmail: Search, read, send, and manage Gmail messages, drafts, labels, and filters/pgoell-claude-tools:calendar: View agendas, manage events, check availability, and manage calendarsResearch complex topics and produce sourced reports.
Skills:
/pgoell-claude-tools:research: Plan focused investigations, gather sources, synthesize findings, review conclusions, and write reports.Writing skills for prose, analytical structure, and technical documentation.
Skills:
/pgoell-claude-tools:writing: Draft, review, and finish long form prose./pgoell-claude-tools:pyramid: Structure memos, recommendations, briefings, and decision documents with the Pyramid Principle./pgoell-claude-tools:tech-doc: Draft, review, and finish tutorials, how to guides, references, and explanations.Aligns Claude Code and Codex project configuration.
Skills:
/pgoell-claude-tools:claude-codex-bridge: Align project files, settings, hooks, agents, and plugin availabilityManage the host agent's instruction layer and skill layer: audit AGENTS.md / CLAUDE.md, capture session learnings, and scaffold or iterate on Claude Code / Codex skills.
npx claudepluginhub pgoell/pgoell-claude-tools --plugin workbenchUse Gmail and Calendar through gws.
Use Jira and Confluence from agent workflows.
Research complex topics and produce sourced reports.
Draft, structure, review, and finish prose and technical docs.
Align Claude Code and Codex project configuration.
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
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
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability, user-decision questions, and plan-mode assessment
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).