🔌
Plugins
Loading...
Showing 30 of 22815 results
Knowledge base agent: compiles PDFs, markdown, and repos into a structured wiki, and compounds the agent's own work-lessons (corrections, playbooks, insights, patterns) across projects
Generate and maintain an entity-based knowledge wiki with contradiction management
"CLAUDE.md 구성 골라 담아줘"로 조합형 구성 카탈로그를 제시하고 결정적 설치기(마커 멱등 append·코너 배타)로 대상 폴더에 설치. flavor(claude·codex=AGENTS.md)·반품(--remove, 코너 스왑)·doctor 진단 지원. 새 구성 추가 = 조각 폴더 하나(입점 양식 포함).
Comprehensive loan officer assistant for mortgage and lending professionals — covering borrower intake, pre-qualification, document collection, pipeline management, compliance tracking, rate quoting, and closing coordination across residential, commercial, and consumer lending
面向抵押贷款与信贷从业人员的综合贷款专员助理——覆盖借款人接洽、资格预审、文件收集、管道管理、合规跟踪、利率报价与交割协调，横跨住宅、商业与消费信贷
from IsmaelMartinez/local-brain
Local inter-session IPC channel for Claude Code — lets two or more Claude Code sessions on the same machine exchange messages via a filesystem queue. Each session is identified by LOCAL_IPC_AGENT_NAME env var.
docs/issue/ を低コストモデルのサブコマンド群 (write/list/read/update/migrate) として回す。issue CRUD・INDEX 保守・VCS commit をメインセッションのコンテキストから隔離する。Run docs/issue/ as low-cost-model sub-commands; isolate CRUD/index/commit from the main session.
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).
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
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.
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).