fprochazka-claude-code-plugins

Multi-agent branch code review — conventions, architecture, design craft, bugs, performance, security, release readiness, git history, and documentation reviewed in parallel

3 skills · 9 agents

Software delivery workflow commands — gather context, write plans, file tickets, open MRs, babysit them to green, wrap them up, and brief next steps

8 skills

How Claude talks and writes — a reply style for chat with a per-prompt reminder hook, a rule set for docs, doc comments, commits, MR text and error messages, and a plain-language restate command

3 skills · hooks

Skill for searching the web using a SearXNG instance via the searxngcli CLI

2 skills · 1 agent · hooks

Git workflow skill and commit commands — vertical-slice atomic commits, the sibling/ancestor boundary test, fixups over correction commits, and dependency-ordered branch history

3 skills

Team-process conventions shared by the sdlc and code-review plugins — the workflow-identify skill that resolves the tracker, team and state names at run time, the review-handshake skill that says whose court the ball is in, and the mr-state-judge skill that says what an MR's pipeline, verdicts and threads mean for the merge

3 skills

Iterative web research agent that searches, discovers new directions, and synthesizes findings

1 skill · 1 agent · hooks

Diagram authoring skills — Mermaid diagrams written to standalone files, rendered with mermaid-cli, and visually checked by a validator subagent before they go into a plan, an MR, or a ticket

2 skills

Skill and review agent for using Gemini CLI with massive context windows (1M tokens) for codebase analysis and second opinions

1 skill · 1 agent

Forces noisy commands (builds, tests, linters, static analysis) to run inside a Sonnet subagent instead of the main context, preserving main-agent tokens

1 agent · hooks

Skill for inspecting RabbitMQ instances using the rabbitmqadmin CLI (rabbitmqadmin-ng)

1 skill · hooks

Three roles injected at the start of every agent — the top-level session orchestrates and delegates, a task worker ends its turn with findings, a resident worker stays alive and reports by message

hooks

AI-powered tool use validation using LLM backends (Vertex AI, etc.) to evaluate command safety and correctness

hooks

Skill for migrating Python projects from Poetry, pipx, or pip to uv

1 skill

Automatically reminds Claude to load relevant skills when keyword triggers appear in user prompts

hooks