Plugins

MDClaw skills and CLI tools for preparing systems, running MD, analyzing trajectories, and packaging atomistic evidence

from BenjaminBenetti/bb-claude-plugins

Preview markdown files and export to PDF using the native macOS MarkdownViewer app

AI coding assistant toolkit - git workflow protection, session handoff, context management, and development automation

MECE decomposition of goals, tasks, and workflows into Agent SDK-ready components with interactive tree visualizer. SessionStart hook auto-injects principles when Agent SDK or decomposition files detected.

Cost-tiered mechanical subagents — two agents pinned to cheaper model versions so the premium tier (Opus / Sonnet 5) stays reserved for judgment. `mechanic` (Sonnet 4.6) for mechanical work that needs code/context comprehension (specified edits, cross-file refactors, boilerplate that must fit); `errand` (Haiku 4.5) for trivial self-contained transformations that need no codebase understanding (classify, extract, reformat, literal find/replace). Routing: needs code understanding -> mechanic; needs a decision -> general-purpose; otherwise -> errand. Invoke via the Agent tool with subagent_type "mechanic" or "mechanic:errand".

ElevenLabs AI 음성 생성, 사운드 이펙트, 음성 클론 등 오디오 제작 도구

from GGPrompts/my-plugins

Skills for interacting with Plex, Jellyfin, Audiobookshelf, and Kavita media servers - list libraries, search media, manage metadata, and trigger rescans.

Transcribe a video or audio file (URL or local) into an SRT subtitle file. Choose: fast Douban ASR (with speaker diarization) or local whisper.cpp (private). Supports YouTube, Bilibili, 小红书, 抖音, Vimeo, Twitter/X, and local files (mp3/m4a/wav/aac/flac/mp4/webm/ogg).

Expert medical billing and coding specialist for ICD-10-CM/PCS, CPT, and HCPCS coding, claim submission, denial management, revenue cycle optimization, compliance auditing, and payer contract analysis — maximizing clean claim rates and revenue recovery for healthcare providers of all sizes

精通 ICD-10-CM/PCS、CPT 和 HCPCS 编码、理赔提交、拒付管理、收入周期优化、合规审计与付款方合同分析的医疗账单与编码专家——为各种规模的医疗机构最大化清洁理赔率和收入回收

Medical Revenue Cycle specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A revenue-cycle team for a healthcare provider or RCM operator — it drives the clean-claim rate toward 98%, attacks denials before they happen (initial denials hit ~11.8% in 2024 and trend 12–15%), works the A/R by aging bucket, and reads net collection rate the way a CFO who lives the cash cycle does. Inherits ravenclaude-core protocols.

Reproducible statistical analysis, publication-ready figures, batch/cross-national/replication analysis, and meta-analysis synthesis.

Study design and validity review, literature-grounded variable operationalization, sample-size planning, data cleaning, de-identification, codebook generation, and dataset versioning.

Literature search with anti-hallucination citation verification, full-text retrieval, Zotero/Obsidian sync, and reference-integrity audits.

Clinical AI model research engineering: choose a paper-grounded architecture, scaffold a reproducible PyTorch training repo, validate the model's split and validation design, document it (Model Card / Datasheet), and evaluate models or LLMs/MLLMs on clinical tasks. Integrates MONAI / nnU-Net, never replaces them.

Academic presentation and PPTX building, PDF/document rendering, environment setup, and skill publishing.

Research orchestration, project intake and management, research-gap and meta-analysis topic discovery, and author-strategy analysis.

Pre-submission self-review, peer-review drafting, and reporting-guideline compliance audits against EQUATOR checklists.

Submission packaging, journal recommendation and profiling, institutional form filling (ICMJE COI, IRB), and grant proposals.

IMRAD manuscript and IRB-protocol drafting, AI-pattern removal, AI-search optimization, and reviewer-response letters.

Turn raw meeting transcripts, call notes, long meeting chats, product demo notes, or client implementation discussions into quick share-ready notes, build-guide style recaps, decisions, risks, and owner-tagged action items. Use for transcript cleanup, Slack/email-ready recaps, actionable build guides, priority briefs, and concise follow-up lists; use summarize-meeting for formal meeting records, templates, scoring, tracking scripts, or fuller meeting operations.

Meetings and shared knowledge. Chair-ready minutes from a corrected transcript and register (meeting-secretary), context-correction of raw Microsoft Teams transcripts (transcription-correction), and the STANLIB terminology lexicon (lexicon). General-purpose across personal and work use; lexicon and transcription-correction are work-context skills. Moved intact from everyday-toolkit.

Frontend design guidance: distinctive visual direction, typography, layout, and UX copy that don't read as templated defaults.

Greenfield Go: an opinionated stack picker plus idiomatic Go patterns.

Safety hooks and dev tooling: block destructive commands, auto-format on save, and a rich statusline (Linux-only, opt-in).

Decide the structure (inline, fan-out, delegate, best-of-N, council, autonomous run), route each role to the best model, verify across vendors, and gate irreversible actions.

Greenfield Python: an opinionated stack picker (uv, ruff, pyright, pytest, FastAPI) plus idiomatic Python patterns.

Greenfield TypeScript: an opinionated stack picker (pnpm, strict tsconfig, vitest, Hono, zod) plus idiomatic TypeScript patterns.