Every Claude Code tool you need :)
2,583 plugins. 18,852 skills, agents, commands and MCP servers. 103 of them get Auto-invokedWhat is this?This plugin ships a FLOW.md router the engine fires, so the matching skill runs itself. No slash command to remember.Learn how → and fire as you prompt. Only on Flowy.
agent-common
Shared preamble loaded by all cc10x agents — memory protocol, contract format, output rules.
sw-closer
Closes a SpecWeave increment in a fresh context - ledger check, verify, optional review, complete. Use after the implementing session finishes, to keep closure…
gem
Hand any OKF task to the okf skill — search, author, curate, or doctor a bundle
architect
System design, tradeoffs, and complex technical decisions.
cassette-model
Show or change the Cassette model and thinking level for the current media session
debug-that
Debugger CLI built for AI agents. Fast, token-efficient, no fluff. Why? Agents waste tokens on print-debugging. A real debugger gives precise state inspection in minimal output — variables, stack, breakpoints — all via short @ref handles.
ig-audience-insights
Read your Instagram niche and profile from real data via Apify, no login. Scan a hashtag for the posts traveling now (likes, comments, owner) to see the format…
interviewer
Conducts deep behavioral interviews to understand a person's work patterns, communication style, decision-making, and expertise. Delegates to this agent when…
atdd
Start the ATDD workflow for a new feature. Optionally provide a feature description as an argument.
yusuke710-manim-skill
Create videos like you write code with Claude Code Claude autonomously generates 3Blue1Brown-style video following a structured workflow: Plan → Code → Render → Iterate.
e2e-browser-tester
Tests web applications end-to-end using Glance browser MCP. Navigates pages, fills forms, clicks buttons, takes screenshots, runs assertions, and reports bugs.…
default
Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification.
vnsh
One workspace all your AI agents can read and write. Encrypted client-side, model-agnostic, gone 24h after the last edit.
contextual-commit
Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user…
architecture-drift-rev…
Read-only checkpoint reviewer. Surfaces drift between the codebase and accepted ADRs in .codearbiter/decisions/. Informational — never blocks.
coder-eval-code-review
Run a multi-model code review on uncommitted changes or a described set of files
