Plugins

Plugin to support herb-lsp in Claude Code.

Expert at understanding and working with Hermes Agent — its memory system, skills, cron jobs, tools, and behavioral conventions

Long-running agent harness + scheduling + messaging front door for Claude Code.

Maintainer tool: file GitHub issues via a configured GitHub App bot identity.

Guide anyone through building a distinctive personal 'hero' website — gather their content conversationally, pick sections by persona, choose a look in a live browser preview, then deploy to Vercel on a custom domain.

Gestión de Herramientas del repo: las tools del Propósito (script/skill local/MCP local) en .claude/herramientas/ con registro INDICE.md (columna Tipo) + lint. Los lints de subsistema no son herramientas. Depende de memoria-local.

管理 Hetzner Cloud 資源 — 建立伺服器、SSH 金鑰、規格查詢（17 個 MCP 工具）

from gaarutyunov/dev-skills

Hexagonal architecture (ports and adapters) applied pragmatically: the dependency rule, primary and secondary ports and adapters, the application core, composition-root wiring, and its relationship to Onion and Clean Architecture, with TypeScript specifics. Composable with your own conventions.

Claude Code plugin for HGF monthly close P&L package ingestion, audit, and workbook generation.

Per-session prompt stack: push/pop/list/drop prompts across a session.

hicode Claude Code plugin for insurance and financial core system Coding Agent workflows

Play a legendary text adventure by talking to your AI — no commands to memorize. The Hidden Empire puts a full underground world of puzzles, treasures, and trolls inside your conversation. Speak naturally: say 'head north,' 'grab the lantern,' or 'what am I carrying?' and your AI handles the rest. Execute multi-move plans in one shot, undo mistakes instantly, and save up to 20 named playthroughs you can resume from any session. Based on the MIT-licensed Zork I source, rebuilt from the ground up for AI-native play.

from towc/claude-marketplace

from cloud-atlas-ai/unified-hifi-control

Produce a reliable, high-stakes-grade result for any task by treating the work as guilty until independent skeptics fail to break it — runs a dynamic adversarial-verification Workflow that hunts ten failure modes and loops until two consecutive clean rounds

Higher-education administration operations team — 3 agents (higher-ed-administration-lead, enrollment-management-strategist, student-success-advisor) across the three engines of a college/university admin operation: institutional strategy (enrollment strategy, the budget/net-tuition-revenue model, retention/completion, cross-functional coordination, accreditation), enrollment management (the inquiry->apply->admit->yield->melt funnel, yield & discount-rate modeling, financial-aid leveraging), and student success (persistence, early-alert, advising, at-risk intervention, DFW-course analysis). Ships 4 skills, a decision-tree knowledge bank (4 Mermaid trees + a dated 2026 reference), 5 best-practices, 2 templates, 2 commands. ADVISORY operations knowledge, not legal, financial-aid-compliance, or academic-policy advice; volatile specifics (funnel benchmarks, discount-rate norms, metric definitions) carry a retrieval date + verify-at-use; FERPA-aware — no student PII. Requires ravenclaude-core@>=0.7.0.

Long-term memory for Claude Code via Hindsight with HindClaw server-side access control. Auto-recall on every prompt, auto-retain after responses, bank creation from templates.

from abix5/memory-hindsight

Local, git-native memory for Claude Code — your repo is the store, recall is $0/prompt (no LLM, no network), staleness is git-drift (the cited code moved), and team memory ships through review.

from dherman/claude-plugins

from gentritbiba/history-context

A plugin built for agent interactions with the hive-mind knowledge system.

Hannah Labs methodology (v3) — collaborative development workflow with session lifecycle (start/stop), red-team/blue-team scope refinement, a batch/wave shipping pipeline (ship), an optional autri Dev Memory loop (sessions recall and record their own decisions), and pipeline-shaped progression from drafts through requirements to implementation and deploy. Third iteration after OpenClaw and lean.

Universal AI harness engineering: 6-layer architecture with SDD pipeline, ambiguity-gated shaping, 6-dimension review, lifecycle (GC/evolve/diet/audit), doctor health-check, enforcement hooks, context routing, and doc generation

from s4na/cc-plugins

Hokusai task routing for Claude Code - get an Anthropic model recommendation before you spend inference budget.

Core skills library for Claude Code: SDLC, Tooling, and Development

from cdcore09/holoviz-claude

Interact with Home Assistant via the REST API — get entity states, call services, fire events, render Jinja2 templates, and query state history.