Plugins

Plugin from gemini-cli-extensions/spanner

12 standalone-safe skills including the SPARC methodology, from ruvnet/ruflo.

from memcoai/marketplace

Community shared memory of proven solutions to problems.

Community shared memory of proven solutions to problems.

Generative deep-dive conversation — one question at a time — to surface your best thinking. Supports /later to capture sparks mid-session.

Community shared memory of proven solutions to problems for Teams.

Pulls live SparkPost metrics, runs DNS authentication checks (SPF/DKIM/DMARC), correlates with application logs, and produces evidence-graded deliverability briefs. Includes a first-run customization interview that adapts the skill to the operator's platform name, logging tool, docs publishing system, and tier-routing model.

Generic background-session fan-out (spawn skill + /spawn command)

Spin up coordinated teams of agents in split panes

Text-to-speech that reads Claude's last response aloud

Text-to-speech with conversation context for better humanization

Complete Speak integration skill pack with 24 skills covering AI language learning, speech recognition, conversation practice, and education technology. Flagship tier vendor pack.

from rjmoggach/claude-plugins

Spec-driven development plugin: the full research → ask → propose → HARD GATE → apply → verify → archive flow, enforced by 4 hooks (TBD scan / approval gate / archive audit / verify reminder), with scope-dispatched dev agents and a fresh-context verifier agent

from mrsekut/mrsekut-cc-marketplace

from mll-lab/claude-plugin-marketplace

Write the implementation spec (context, approach, files to modify, utilities to reuse, and verification) that drives execution after design is chosen.

ユニバーサルな原則に基づくコードレビュー。計画ドキュメントがあれば仕様整合性も検証する

Backlog.md as the kanban view over GitHub Spec Kit specs: link a task to a spec dir, sync status one-way from spec artifacts, and gate 'status can't exceed proven artifacts'.

Spec-driven development skills: create and revise requirements/basic-design documents, implement from spec, and debug systematically

Creating or amending specifications for software projects or features

Multi-LLM adversarial spec debate. Refines PRDs and tech specs through iterative critique until all models reach consensus.

Spec-driven development toolkit: create, review, and iterate on feature specifications with an expert review panel.

Prowadzi całą budowę bloga dla klienta od zera do wdrożenia metodą spec-driven (specyfikacja → plan → implementacja fazami → CMS przez MCP → QA → deploy → instrukcja dla klienta), zamiast vibe codingu.

Idea to shipped software as a sequence of reviewable artifacts: refine the spec, architect it, break it into tasks, then build under a working agreement with real gates. Includes the phase-boundary ritual, the issue-review loop, and a catalogue of the ways a green test suite lies to you.

Agentic workflow factory — compile project-specific planners, builders, and specialist agents for any codebase.

Design and run a Spec-Driven Development (SDD) pipeline for AI software factories — where structured specifications are the input, AI agents generate the code, and quality gates enforce correctness at each phase: SPECIFY → DECOMPOSE → IMPLEMENT → VERIFY → DELIVER. Use when building or refining a spec-driven pipeline any AI coding tool (Claude Code, Cursor, Hermes Agent, Devin, OpenHands, droid) can follow, or when you need spec quality gates, phase-gate verdicts, NFR encoding, or format translation. Do not use for a single small change with a clear goal (classify first via bmad), for the control-plane protocol of intent contracts, autonomy gating, and failure routing around a pipeline (bmad), or for unvalidated problems (product-discovery).

A Rails-focused spec-driven development workflow for building features with AI agents through systematic planning and self-contained specs

Hybrid pipeline for spec-driven development from Japanese design docs (基本設計/詳細設計) + Figma. Wraps GitHub Spec Kit with a design-intake agent and a code-reviewer agent.