Plugins

Local markdown-powered memory system for AI coding assistants

Internationalization (i18n) and localization (l10n) engineering specialists — 3 agents covering i18n architecture (string externalization, ICU MessageFormat, RTL/bidi, locale data), the l10n pipeline (extraction, TMS handoff, translation memory, continuous localization), and localization QA (pseudo-localization, l10n linting in CI, visual overflow QA, locale-coverage testing). Ships 3 skills, 3 commands, 2 templates, a decision-tree knowledge bank with a 2026 i18n/TMS capability map, 6 best-practice rules, and an advisory hook flagging i18n anti-patterns (hard-coded user-facing strings, string concatenation, if-count-1 plurals, hard-coded date/number formats). Inherits ravenclaude-core protocols (Grounding, Structured Output).

LocalStack Community Edition expertise with MCP server: local AWS development, docker-compose setup, cdklocal/awslocal tooling, init hooks, and 40 MCP tools for S3/SQS/SNS/Lambda/DynamoDB

Publishes Claude Code session context (prompt, cwd, recent files) to a local localvoxtral socket so dictation can ground technical terms. Install this on the machine running localvoxtral. Fail-open: does nothing when the app is not running.

Publishes Claude Code session context from a remote host to localvoxtral on your Mac over an SSH RemoteForward tunnel. Install this on the REMOTE host, not the Mac. Declarative HTTP hooks only — no binary, no shell shim, no dependencies. Fail-open: does nothing without a tunnel.

Lodis MCP server + memory-management skills (retrieval, capture, onboarding, session-wrap).

Plugin from ncaq/konoka

Add Logfire observability to Python applications with auto-instrumentation for FastAPI, httpx, asyncpg, SQLAlchemy, and more

Add Logfire observability to Python applications with auto-instrumentation for FastAPI, httpx, asyncpg, SQLAlchemy, and more

自動捕捉對話中的邏輯思維與決策過程，識別背後理論原理，建立可跨 session 引用的知識資產。

Classical formal logic from G. Chelpanov's textbook: concepts, judgments, syllogisms, induction, fallacies, laws of thought.

Create professional SVG logos from descriptions and design specifications. Generates multiple logo variations with different layouts, styles, and concepts.

Connect Claude Code to LogRocket to query session replays, metrics, issues, and user behavior using natural language.

Persistent memory for Claude using a dedicated Logseq graph. Save and load project context, decisions, and progress across sessions and devices.

Plugin from ccomkhj/skills

Continuous Iterative Development (CID) for long-horizon projects: an autonomous loop of four fresh-context roles (update-state, define-next, advance, review) that advances a project in small verified increments toward a human-owned target, self-determines its phase (new/poc/mvp/stable), adjusts rigor per phase, and self-improves through a learnings ledger and retro passes

Survive context loss across sessions: SessionStart context injection, cost-ceiling guard, large-edit gate, ledger templates, goal-manager workflow.

Long-task orchestration harness: brainstorming → spec → plan → a TDD subagent assembly line, human-gated throughout, with an optional dual-model adversarial review. Installs the /long-task:long-task command; the batched long-task-tdd.js Workflow() script ships alongside it.

Front-door skills for the Long-Horizon Workflow Framework: /longhorizon (four-condition reality interview + honest routing) and /longhorizon-strategize (design the instantiation for a specific task in any domain).

Connect to Looker and interact with your data using LookML.

Canon-grounded coding-discipline workflow (TDD/brainstorm/SDD/review) for Claude Code + Codex.

Key-free cross-modal (GUI/TUI/CLI) UX design generator — emits portable DESIGN.md + ui-flows.md.

Deterministic workflow driver conducting the loom principles→design→spec→code pipeline across station plugins.

Key-free generator for a PRINCIPLES.md project constitution — north star + falsifiable Product Principles, plus optional Design/Engineering Principles.

Key-free GENERATE-layer spec skills — expand a seed into a high-recall spec + critique omissions.

Loop engineering wizard for Claude Code. Answer 2 questions and Claude orchestrates a fully autonomous 7-agent team (tool-scout, researcher, developer, qa-tester, verifier, auditor, memory-keeper) until your goal is met.

Diagnose a repetitive task into one of 5 loop shapes (Batch/Pipeline/Refine/Watch/Explore), interview for the blanks, and auto-inject an independent verifier (maker ≠ checker) and a hardstop, then stamp it as a reusable slash command.

Stack-agnostic loop-engineering harness: pwsh hooks (session context, Bash/PowerShell deny-list guard, Stop+SubagentStop gate on build/verify.ps1 with a real round-trip cap and ledger logging), maker/checker/explorer/verifier sub-agents with real effort routing, /init-harness bootstrap, /work-next automation, per-stack verify templates that fail loudly until wired, and harness-audit/claude-code-hook-facts/verify-gate-authoring skills.

Guardrails, verification patterns, goal-condition templates, and loop discipline for Claude Code loops. Complements ralph-loop with the discipline that makes loops trustworthy.

Turn any task description into a ready-to-paste six-part agentic loop prompt. /loopgen <your task>.