Find plugins

by Evidence Lab

Reproducible systematic-search and screening workflow with explicit eligibility criteria, stable record deduplication, and an auditable decision trail.

by Wondel.ai

Systems architecture and distributed systems skills including Designing Data-Intensive Applications (Martin Kleppmann), System Design Interview (Alex Xu), Clean Architecture (Robert C. Martin), Release It! (Michael Nygard), High Performance Browser Networking (Ilya Grigorik), and Team Topologies (Skelton & Pais)

by Seth Hobson

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

by Arthur Zakirov

SystemSmith turns recurring engineering judgment into reusable agent skills.

by Stephen Zhao

Project-agnostic agentic SDLC framework: entities are the single source of truth, every index is generated, and the deterministic operations are script calls with fixed token cost.

by Bobby Mac

Turn reference folders and public URLs into deep, portable T3 Code themes and Windows builds.

by Loai Elattar

Nexika tabib: finds out why CI failed, with evidence. Reads the failed run (GitHub Actions or GitLab CI), pulls out the failing tests and errors, sorts the failure (code, one Python or OS only, flaky, infrastructure, dependencies), compares with the last green run, reproduces the failing tests in a throwaway git worktree, and reports the cause with its evidence. Diagnoses only: it never edits code, pushes or re-runs CI. English and Arabic.

by gigun

TablePlus MCP server (database GUI integration)

by tabnas

Tabnas parser-fleet skills and MCP servers: author, debug, test and ship grammars for the tabnas engine.

by 743v45

管理「代码表达不了的隐性关联」。用 per-project 关联登记表 + 三档自动化(审计/捕获/呈现)防止「改 A 忘改 B」。核心:发现关联时优先转成可强制形态(测试/代码生成/注册表),文档永远是最后手段;编辑耦合文件时自动把关联重新注入上下文。

by Luiz Tadeu Mendonça

The knowledge layer of a public agent-harness reference: 15 dense, opinionated engineering skills covering AWS infrastructure, React/Vite frontends, BFF-on-Lambda backends, CI/CD, the development loop and its quality gates. Written project-agnostically with <project> / <apex-domain> placeholders. This Power ships skills only — the harness's personas, permission hooks and merge gates are deliberately not exported.

by Luiz Tadeu Mendonça

A Claude Code harness: 8 subagent personas — two leads that disagree by design (product-and-market, tech) and consolidate one demand, a tool-less scrum-master that ranks the eligible pool and names who acts next in a selection record the main session executes, one fullstack developer, a content pair that argues against one shared ruler at most twice (a content-writer that drafts published prose in the owner's voice and a content-reviewer that may block only on a clause it can quote, both contained the same way as product-lead — neither posts to a public surface directly), one gatekeeper (a quality-assurance that holds the merge gate and reviews both technical delivery and whether the change can break production), and an agents-lead that stress-tests proposed changes to the harness itself and, per ADR-0002, may implement the harness changes it reviews (never merging, never gating an MR) — PreToolUse hooks that mechanically deny the irreversible floor (force-push, terraform apply, rm -rf, secret writes), and 15 generic skills for AWS infrastructure, React/Vite frontends and CI/CD (<project>/<apex-domain> placeholders).

by 태전 Core

태전 Core의 권한 내 업무 데이터를 조회하는 MCP 플러그인. Includes 1 MCP server.

by Jack Blacketter

The tagteam handoff contract for Claude — the /handoff skill and a SessionStart hook that surfaces the current cycle. The engine is the tagteam CLI (uv tool install tagteam).

by AGENTS.STORE

Taiga project-management ops plugin. Drive the full Taiga REST API by curl — projects, memberships, roles, milestones (sprints), epics, user stories, tasks, issues (with statuses, types, priorities, severities, points, custom attributes), wiki, history, attachments, comments, webhooks, notify policies, search, resolver, stats, and import/export. Authenticates with TAIGA_ADMIN_USERNAME + TAIGA_ADMIN_PASSWORD to obtain TAIGA_AUTH_TOKEN against TAIGA_API_URL.

by AGENTS.STORE

Taiga project-management ops plugin. Drive the full Taiga REST API by curl — projects, memberships, roles, milestones (sprints), epics, user stories, tasks, issues (with statuses, types, priorities, severities, points, custom attributes), wiki, history, attachments, comments, webhooks, notify policies, search, resolver, stats, and import/export. Authenticates with TAIGA_ADMIN_USERNAME + TAIGA_ADMIN_PASSWORD to obtain TAIGA_AUTH_TOKEN against TAIGA_API_URL.

by AGENTS.STORE

Taiga project-management ops plugin. Drive the full Taiga REST API by curl — projects, memberships, roles, milestones (sprints), epics, user stories, tasks, issues (with statuses, types, priorities, severities, points, custom attributes), wiki, history, attachments, comments, webhooks, notify policies, search, resolver, stats, and import/export. Authenticates with TAIGA_ADMIN_USERNAME + TAIGA_ADMIN_PASSWORD to obtain TAIGA_AUTH_TOKEN against TAIGA_API_URL.

by t12e

A read-only Takealot shopping assistant for product research and balanced buying guidance.

by Shonik Agarwal

Drive LinkedIn Recruiter and Juicebox through a browser to size and map talent pools — each tool's filter inventory, which counts are free, and the validation rules that stop it reporting a silently wrong number. Includes a Playwright MCP server configured with a persistent browser profile so tool logins survive between sessions.

by utomore

演講內容產生流程 skills，三層階梯（Level 1 語意 / Level 2 內容 / Level 3 呈現，視覺數值唯一真相是 theme.css）：主軸設計（topic-design，風格基底、分層語意、Marp 鷹架與文字規範）、段落設計（section-design，含 status 掃描與圖形選型）、段落實作（section-impl，Marp 排版 + 視覺引導 + 逐頁背景 + SVG 圖形 + 頁內備註，在上層規範內有完全呈現自主權）、頁面調整 (page-adjust)、整體審查（review，build 後逐頁目視 + 十四項指標含文案語感，產出 review/ 報告）、架構圖排版量測（svg-layout，normalize/inspect/lint 三支腳本），投影片以 marp-cli 建置輸出；全流程共用文案語感規範（wording.md：禁對比翻轉句與人稱代名詞，標題一句話寫出這頁的重點主軸）

by Ghast AI

Manage workflow tasks, business processes and approvals through Tallyfy.

by Anas Hammo

Turn a project description into a validated, traceable, execution-ready planning & handoff package for Claude Code to implement.

by Ghast AI

Search Tana content, read meeting context and prepare updates to documents and structured items.

by recursivecurry

Skills for disciplined agent work: minimal code, clean Git history, natural writing.