Plugins

Write Makefiles adhering to SuperScript standards

from ZhangHanDong/makepad-skills

The Make role of the PMCR-O loop — passive, composable. Provides: maker.

Personal skills for Corey Haines — decision-making, research, brainstorming, social rotation, paste utility, YouTube transcripts, and the meta skill that scaffolds new skills. Sibling to marketingskills and cf-skills.

Holds Claude Code to its word — every claim checked against the agent's own logged record; faked checks blocked, not warned (four narrow advisory self-checks excepted). Two-tier catalog (14 pre-checks, 16 Stop gates), each shipped at measured zero false positives.

MCP server for sending approval requests and notifications through Discord.

Identify and investigate malicious sending behavior on your ESP.

Build MaluDB memory applications. Three skills: integrate the REST API (maludb-api-client), query the PostgreSQL extension via SQL (maludb-sql-client), and scaffold the PHP API server (maludb-api-server).

Operate the management-portal MCP with the full agent discipline — the core loop, the three gates (read-after-write, completeness, task-breakdown), bottom-up completion, never-fabricate-ids, and board-first. Bundles the MCP server, the management-portal skill, the portal-operator subagent, the /portal command, and the read-after-write hooks. On Claude Code Desktop you are prompted for your API key on install (stored in the OS keychain) — no terminal needed.

from manifestdocs/claude-plugins

Create mathematical animations with Manim Community Edition.

Manim 数学动画创建插件，提供代码生成、工具函数库和编译渲染功能。支持函数可视化、几何图形、动画变换和数学公式。

from y-ymmt/cc-manim-video-creator-plugin

Write ManimGL math explainer code without hallucinating Manim Community Edition APIs. Covers equations, coordinate systems and graphs, geometry, ValueTracker-driven animation, plus the install traps on Windows/MiKTeX and headless Linux.

Manolii AI framework for Claude Code — specialist sub-agents, slash-commands, skills, and lifecycle hooks for PR review, persistent memory, planning, and model-routing governance.

Upload local/chat image files into a Mantle site through upload sessions and signed URLs, without sending large base64 payloads through MCP tool arguments.

from flexion/claude-domestique

Sphinx 기반 프로그램 문서화 도구: CHM/MD/DOCX 파일을 Sphinx 문서로 변환하고, 다국어(한/영/일) 사용자 매뉴얼을 생성하며, 품질 리뷰까지 지원합니다. sphinx-rtd-theme 기본 테마. 4개 스킬 + 4개 에이전트.

Turn attached UI screenshots and screen descriptions into a polished A4 user manual PDF, no Figma required

대용량 매뉴얼(PDF/HTML/EPUB/DOCX/CHM/MD) 및 소스코드 디렉토리(codebase) 다이제스트 플러그인: 한 번 추출→요약하면 이후 작업은 ~0.3% 압축된 마크다운 다이제스트만 참조하고, 디테일 필요 시 원본의 특정 페이지/섹션(문서) 또는 파일/심볼(코드)만 핀포인트로 추출. PDF는 @sylphx/pdf-reader-mcp MCP, 코드베이스는 Read/Grep/Glob(MCP 불필요) 사용. project/global 두 스코프 지원, CLAUDE.md 마커 자동 주입으로 Claude가 매뉴얼/코드 질문에 자동으로 다이제스트를 1차 참조하도록 가이드. 2개 스킬: manual-digest(인제스트/갱신/목록/삭제) + manual-digest-setup(환경 1회 초기화).

from petekp/agent-skills

Automotive market intelligence for OEMs and brand managers. Market share tracking, competitive positioning, EV adoption monitoring, regional demand intelligence.

Manufacturing-operations team for discrete and process manufacturing — 3 agents (production-planner, shop-floor-and-oee-analyst, quality-and-capa-lead) for the plan / make / control loop on the factory floor: MRP/MPS and demand-vs-capacity planning, S&OP, BOM management, lot sizing and finite scheduling (production-planner); OEE (availability x performance x quality), throughput, takt vs cycle time, Theory-of-Constraints bottleneck analysis, and MES/shop-floor downtime data (shop-floor-and-oee-analyst); SPC, nonconformance (NCR) and CAPA, inspection plans, FMEA, supplier quality, and control plans (quality-and-capa-lead). 5-tree decision-tree bank, 12 best-practices, 3 skills, 3 commands, 2 templates, 1 advisory hook, a stdlib OEE/takt/capacity calculator, scenarios. Seams: Lean/Six Sigma -> process-improvement; inferential stats / Gage R&R -> applied-statistics; sourcing -> procurement-sourcing; distribution -> fleet-logistics. Requires ravenclaude-core@>=0.7.0.

Academic manuscript toolkit: literature review (multi-phase citation-traceable + single-pass thematic), peer review, writing, journal-specific formatting for submission, and humanizer pass to remove AI-writing tells

Routes to the right AI slide-deck skill and names a style id you can ask for, backed by sample imagery read from the projects' own repositories.

MAOS (Multi-Agent OS) - Coordination Framework for AI Agents with Orchestration, Sentinel Protocol, Worktree Policy, Status Maps

Mapbox skills and MCP servers for building location-aware applications with AI. Includes geospatial tools, style management, and patterns for web, iOS, Android, and AI agent frameworks.

Semantic code search using maproom CLI

Marc Andreessen — software eats the world, it's time to build, techno-optimism. Grounded in his essays at a16z.com.

/marcom-best-practices [target] finds and applies best practices for any MARCOM project, idea, channel, or campaign, on the premise that we're probably doing it wrong and should consult the full toolbox before changing direction. Classifies the target into 13 MARCOM domains (lifecycle email/outreach expanded into onboarding -> nurturing -> upgrade -> retention, not one bucket), then sweeps three tiers: our installed plugins/skills via a curated domain->skill capability map; the Workforce Automation Supabase catalog of ~580K catalogued Claude skills/plugins/MCPs (with an 'installed' source for a real have/don't-have diff) to surface adoption candidates we don't have; and heavy external web research. Benchmarks current MoxyWolf practice against all three using live analytics (GA4/PostHog/Ahrefs/CRM), writes a prioritized best-practices brief to the target's MARCOM folder, lists adoption candidates, and auto-runs the top applicable installed skills to produce starter deliverables.