Development plugins

Plan, implement, review, and merge substantial changes with Claude and Codex together.

1 skill · 4 commands · 10 agents

DEPRECATED: moved to Software-Improvement-Group/agent-integrations. Prevent and fix technical debt with Sigrid: guardrails against new issues, and skills to diagnose and auto-fix existing ones.

10 skills · 2 agents · 1 MCP server · hooks

General software delivery skills for API design, REST implementation, cleanup, specs, tests, DevOps, and Supabase.

13 skills

Points to all AI skill catalog entities in the rh-sre agentic pack for Red Hat Site Reliability Engineering workflows.

13 skills

Self-running Claude Code loops on a throwaway worktree: hooks hold the budget, and done is released only when the hook itself re-runs your checks green.

1 skill · 10 commands · hooks

Send work to GitHub without knowing git: five commands (publish, update, new, cancel, my-prs) covering the whole loop from local changes to a merged pull request. Bundles the GitHub and Playwright MCP servers, PAT lifecycle, and the reusable git building blocks used underneath.

10 skills · 2 MCP servers

AI coding assistant toolkit - git workflow protection, verification, shipping, research, and development automation

10 skills · 1 agent · hooks

Micro project management - acceptance criteria and defects as markdown checklists with permanent ids, author handles, severity triage, and computed reports

6 skills · 5 commands · hooks

Coordinate specialist software-engineering agents with TDD, debugging, and verification practices.

2 skills · 1 command · 9 agents

Essential developer skills including Git workflows, SQL optimization, error handling, code review, E2E testing, authentication, debugging, and monorepo management

11 skills · 1 agent

Core development workflow skills: brainstorming, spec and plan writing, code review, and subagent-driven execution (uses me for TDD and debugging)

12 skills

Core development workflow skills: brainstorming, spec and plan writing, code review, and subagent-driven execution (uses core for TDD and debugging)

12 skills

Requirements discovery for Claude Code. Turn a vague feature request into a structured, versioned requirements model that separates what is known, what is assumed and what is still open, then write a decision brief, a PRD, user stories, an estimate, acceptance criteria, a delivery epic or release notes from it, or a go-to-market plan from a go-to-market request -- every one reasoned in your Claude Code session, so there is no API key to configure. The requivo CLI can also produce every one of them itself, in its own optional API mode, which does need one -- useful for automation outside a Claude Code session.

12 skills

Governance skills for AI-assisted development: /tierward:commit (Conventional Commits), /tierward:arch-audit, /tierward:security-audit, /tierward:perf-audit, /tierward:simplify, /tierward:skill-dev, /tierward:skill-security, /tierward:humanize. Includes a soft session bootstrap reminder.

10 skills

Subagents that take one work ticket to a reviewed pull request: verified spec, build, review before push, and a browser check for page changes.

2 skills · 2 commands · 6 agents

Points to all AI skill catalog entities in the rh-virt agentic pack for Red Hat OpenShift Virtualization management.

10 skills

Force Claude Code to use Rider's MCP symbol/reference/file index instead of Bash grep, with token-flood summarization. Bundles gamedev-log-analyzer.

1 skill · 5 commands · 1 agent · 1 MCP server · hooks

The toil skill: how an agent installs toil, a structured-JSON CLI and MCP server for enterprise tools and databases, and the reference for every command it has.

9 skills

Small, composable skills for an agentic engineering workflow — building, reviewing, and shipping software with AI coding agents.

9 skills

The integration layer a product needs once it has users: Stripe subscription billing reconciled into your own database, crypto payments that survive over-payment and duplicate webhooks, ad and conversion tracking under Consent Mode v2, Google sign-in with the account-linking guards, the wider Google auth surface, and Core Web Vitals work that moves the score, and Sentry error tracking wired so it does not forward your own credentials to a third party and so a stack trace names the commit that caused it.

7 skills · hooks

Design specifications, architecture specs, requirements gathering, and technical documentation with Notion integration

7 skills · hooks

A Claude plugin for Liferay Workspace projects that provides context and skills for local development setup, including Docker and source mode configuration, client extension builds, site initializer deployments, and DXP license management.

8 skills

Development workflow: bugfix and feedback skills, and worklog time-ledger hooks.

7 skills · hooks

Points to all AI skill catalog entities in the ocp-admin agentic pack for Red Hat OpenShift administration.

8 skills

Checks what AI coding agents change before it lands: impact analysis, architecture rules, and a tamper-evident record. MCP server plus 6 skills.

6 skills · 1 MCP server

Parallel workflow orchestration using git worktrees for concurrent Claude Code sessions

3 skills · 3 agents

Autonomous build iteration orchestrator with multi-agent review, FSM-driven lifecycle, and YAML-configured workflows

4 skills · 1 command · 1 agent

Review plugin agents, skills, hooks, MCP servers and packaging against the target host conventions.

1 skill · 5 agents

Token-efficient game-engine & build log analysis (Unreal/Unity/Godot/MSVC-UBT-MSBuild + JSONL traces), CLI-first: parse, dedup, classify, diff runs, locate file:line, and extract decisive scalar fields over a time window. Also on npm. No IDE required.

1 skill · 3 commands · 1 agent · hooks

The solo maintainer's GitHub loop: an issue tracker, plan-first pull requests, in-session implementation, review rounds judged by a fresh-context reviewer, and gated squash merges, all through the gh CLI.

4 skills · 1 agent · hooks