Plugins

from mlaugharn/plugin-marketplace

Sync project-locally installed (vendored) plugins with the upstream mekari-tools marketplace repo. Three-way merges upstream changes into local plugin copies while preserving project-specific tailoring. Update-only: never adds or removes plugins.

Topic-Synergy Outreach Engine — find the people writing about your topics (and the people you cited) and reach them without pitching. Builds a topic fingerprint from your own content, then runs THREE discovery centers. AUTHOR center (named profiles via Apify harvestapi/linkedin-profile-posts) and CONTENT center (keyword/hashtag search via Apify harvestapi/linkedin-post-search) are comment-first, starting from who's posting; discovered posts are scored against the fingerprint, deduped against an xlsx tracker, and queued, then /synergy-run executes the comment-first decision tree (like + a practitioner comment, the cite-then-tell lever, and a connection note) with a hard human gate and a guard against the LinkedIn 'Post as' identity selector. The new CITATION center starts from who you cited: /synergy-cite-harvest parses your paper's bibliography, triages by reachability, resolves authors via OpenAlex/ORCID, dedups against Clarify, enriches person + org via Apollo (LinkedIn-first match + a verify gate against wrong-person matches), verifies LinkedIn identity via Apify, and drafts a 'we cited you' email + a hook-free connect note into a citation registry; /synergy-cite-run sends email first (Mailtrap as you, BCC you) then the LinkedIn connect, with the hard-won send discipline (type the note in separate click+type calls to beat the focus-race truncation bug, zoom-verify the note's start and end before Send, 2nd/3rd/high-follower button geography, the email-verification gate, never withdraw to re-send); /synergy-cite-accept-check follows through on accepted invites. /synergy-schedule stands up an every-other-day prep task. Cadence + guardrails baked in: comment same-day/connect later, the ~20-25/day LinkedIn connect ceiling, cite-don't-pitch, voice (no em-dashes, contractions, practitioner register), verified citations only. The plugin never auto-sends. v0.2.0.

Multi-agent deliberation system with 3-round structured debate, SID confidence scoring, CortexDebate Trust Score, and 5 specialized modes (review, design, debug, idea, general)

Pre-release multi-language impact, native enforcement, secure sandbox, reversible compression, durable sessions and paired benchmarking

General-purpose synthetic data toolkit — generate, extract, extend, and anonymize tabular datasets across domains

Interactive synthetic data generator. Builds a data model through dialog, generates with Faker + NL extras, outputs CSV/XLSX/SQLite.

Deploy and operate synthkit: first-run onboarding, deployment verification, blueprint authoring, PDC and Fleet Management setup.

Design production-grade software systems with expert knowledge of architecture patterns, distributed systems, cloud platforms, and operational excellence. Use this skill when architecting complex systems, evaluating technology choices, designing scalable infrastructure, or making critical architectural decisions requiring trade-off analysis.

System design knowledge for AI coding agents. 1 skill, 13 self-contained commands, and 14 original-prose reference files — no external links.

from ghostmind-dev/system

Skills that operate and maintain the skill system itself.

Cloud-agnostic system design across AWS, Azure, Google Cloud, and Cloudflare: a six-step Well-Architected loop, grounded in each cloud's live documentation MCP when connected. Auto-engages for architecture and service-selection work.

System-design interview frameworks and 28 worked designs, loaded on demand. Invoke with /system-design or ask a system-design question.

Run a structured system design interview that turns a rough product idea into a complete, installable Claude skill capturing everything needed to build the system.

4-phase root cause investigation methodology: investigate, analyze patterns, test hypotheses, implement fix. Prevents random fix attempts.

Systems programming with Rust, Go, C, and C++ for performance-critical and low-level development

Systems programming with Rust, Go, C, and C++ for performance-critical and low-level development

Systemic root-cause analysis via the Questions of a Systems Thinker and Causal Loop Diagrams. By Agile Pain Relief (CC BY-SA 4.0), packaged for this marketplace.

Apply systems thinking to a problem or decision — classify it as clear, complicated, complex, or chaotic, diagnose it with the DART framework, surface hidden parts/connections/patterns and incentive/feedback traps, and recommend the action protocol that fits the system type

Systemic root-cause analysis via the Questions of a Systems Thinker and Causal Loop Diagrams. By Agile Pain Relief (CC BY-SA 4.0), packaged for this marketplace.

Systems-thinking toolkit (Sherwood 2002) — CLDs, archetypes, simulation, and more across 7 skills.

Wyszukiwanie orzeczen PL przez SAOS API + opcjonalne grupowanie tematyczne (klastrowanie, text mining, raport DOCX). Komenda /szukaj-orzeczen "fraza". v2.1.0: refaktor SKILL.md 460->60 linii + 4 pliki references/.

macOS 기반 T-View 장애 메일 모니터링, Excel 자동 기록, 일일보고 자동 발송 시스템

Drive a non-custodial Sui Agent Wallet: fund, check balance, send (gasless USDC/USDsui), swap any token via Cetus, discover x402 services, and pay any API in USDC. Includes the MCP wiring + the cross-cutting AGENTS.md ops layer.

Shows Claude's status in the terminal tab: green idle, red working, yellow when background agents are still running, plus the project folder name.

from nthplusio/functional-claude

Tableau analytics team — specialist agents for Tableau Desktop/Cloud/Server, Tableau Prep, and the developer surface: VizQL and chart-type selection, calculations (LOD expressions, table calcs, FIXED/INCLUDE/EXCLUDE), data modeling (relationships vs joins vs blends, extracts vs live), workbook/extract performance, Server/Cloud governance and permissions, content/ALM promotion, embedding (Embedding API v3, Connected Apps/JWT), and the next-gen surface (Tableau Pulse, Tableau Next, CRM Analytics, Einstein/Agent). Citation-grounded knowledge bank with Mermaid decision trees + a best-practices library. Seams: Salesforce platform data → salesforce; warehouse/semantic modeling → data-platform/microsoft-fabric; Power BI comparison → power-platform; methodology/security-review → ravenclaude-core. Requires ravenclaude-core@>=0.7.0.

Tint iTerm2 tabs from local agent lifecycle state.

Specialist Claude Code plugin — 45 specialist skills across DDD, FPF, Rust, MCP, security, git operations, wiki, session analytics, task lifecycle, 5 design skills (palette, typography, principles, examples, PDF), evaluating-skills (8-stage skill evaluation with behavioral JSONL review), self-correcting (post-failure meta-analysis for tool-usage cascades), rendered-web-search (rendered browser for JS-rendered and auth-gated web searches with screenshot/PDF evidence), and orchestrating-workflows (Claude Code Workflow tool — JS orchestration with agent()/pipeline()/parallel()/phase()/log()/workflow()/args/budget() globals, hard-gated to v2.1.160+ via compatibility frontmatter + body-time textual probe). Pairs with superpowers for the complete development toolkit.