Find plugins

Ядро методов solution-архитектора банка для харнесса arch-ml: ADR-дисциплина, spine-инварианты, маршрутизация значимости, C4/mermaid, NFR, гейты готовности и состязательное ревью, handoff-пакеты кодовым агентам, reverse discovery, дельта-спеки, fitness functions, рубрики и мета-скилл создания скиллов.

Управление библиотекой архитектурных правил Spine: каталог из 20 готовых fitness-функций для CONSTRAINTS.yaml, фильтр включения из пяти форм правила, три волны внедрения (механизируемое → обязательное извне → смысловое), шаблон карточки дистилляции источника в правило, 9 антипаттернов расширения библиотеки и карта 15 блоков источников (решения, риск, описание, NFR, устойчивость, интеграции, API, границы, данные, безопасность, поставка, наблюдаемость, стоимость, миграции, ИИ-системы).

Офисные артефакты solution-архитектора: генерация архитектурных документов docx (аналитический отчёт для МД, solution design, концепция/vision, интеграционная спецификация, оценка текущего состояния, план миграции), презентаций pptx (для правления и архкомитета) и таблиц xlsx (каталог систем, матрица интеграций, матрица решений, реестр рисков) через python-docx / python-pptx / openpyxl с корпоративными стилями.

by Paul Ingram

Spec-to-production multi-agent coding pipeline. Takes a requirements folder (OpenSpec / Superpowers / plain markdown), drives it through a 100%-coverage planning loop, spawns parallel agent teams for backend/frontend, enforces review gates, reconciles parallel work, and verifies with live dev-API + Playwright user-flow tests.

by Jung Jiwon & Lee Jongkwan

The architecture role on contract v3: 컴포넌트 경계·의존 방향. use_when: 새 모듈 경계나 기존 경계 변경이 걸릴 때. Hand-off: 인터페이스 형태 세부는 → api-design; 성능 예산이 걸리면 → performance-engineering.

by Arcmira

Search YouTube and podcast transcripts. Mentions, momentum, sponsors, and organic recommendations.

by Jaison Erick

Publish a self-contained HTML file as a shareable artifact on artifacts.nexaedge.com. Sign in with any Google Workspace account: the artifact belongs to that account's domain, and only that domain can open it. Also issues expiring links for people outside the domain.

by AndrewYq

Verify and translate arXiv papers into compilable Chinese editions with paired English and Chinese PDFs.

by I-Ops

After every turn, says whether anything was tested after Claude's last edit, and what it could not check.

by Sascha Sertel

Live activity view for AI coding sessions — know when an agent is blocked on you, and where in the repo work is happening.

by Nery Samuel Murillo

Astro Commands gives Codex a maintained, command-first operating contract for Astro projects: inspect the installed CLI, prefer official capabilities, and verify version drift before acting.

by Mode1221

1인 개발자용 전 과정 가이드 + AI 회사 모드: 아이디어 → 기획 → 디자인 → 구현 → 보안·법률 → 출시 → 운영 → 성장, 부서 AI 가 일하고 대표는 결재만

並行作業を見渡して戻るための道具 3 本。open な PR / issue を全件走査して「誰の番か・なぜ今その人の番か」を機械で出す /whose-turn、1 件の PR / issue（今のブランチ・手元の commit も）について「前回自分が触ってから何が起きたか」を出す /catchup、いま居るセッションが何のスレッドだったかをその場に居なかった人でも追いつける形で説明する /what-am-i-doing。中心は位置——戻ったときに真っ先に失われているのは会話のどこで止まったか——で、中身は作者の本文から初見向けに説明し、実物の行を有るだけ後ろに付ける。先行例は Gerrit / Google Critique の Attention Set。

by whale_net

Streamable-HTTP MCP access to the Audience Score System server across dev/prod, plus researcher/analyst agents and loop skills for research, schedule, and outcomes

by whale_net

Postgres MCP access (crystaldba postgres-mcp) to the Audience Score System database across tilt/dev/prod

by Ryan Duguid

Australian public-practice workflow skills: BAS tie-out, FBT, Division 7A, STP finalisation, and workpapers. Prep-only. Not lodgment. Not tax advice.

by Unic AG

Auto-format and lint files when Claude Code edits them. Runs Prettier + ESLint --fix after Write/Edit/MultiEdit/NotebookEdit.

by weedmo

Autonomous code improvement loop - autocode: hypothesis-driven parallel experiments with model routing (strategist on the expensive tier, experimenters routed by hypothesis difficulty), a live experiment board via weed-harness loop-report, unlazy-backed termination gates, and kept changes collected as one squash commit each on a worktree branch that ends in a PR.

by weedmo

Autonomous code improvement loop, Claude Code edition - autocode: hypothesis-driven parallel experiments with in-session experimenters routed by the plugin agents, a live experiment board published as an Artifact, unlazy-backed termination gates, and kept changes collected as one squash commit each on a worktree branch that ends in a PR.

by weedmo

Autonomous improvement loops - autocode (code improvement loop with PGE team mode) and auto_research (ML research loop with optional 23-stage pipeline).

by Tong Wang

Build a trained, deployable RL policy from a verbal description of a dynamic decision-making problem: formalize it into an MDP-IR, generate a spec-conformant simulator domain, baselines, PPO training and tuning, and a policy-structure readback, with executable gates between stages.

by office-skills

Auto Office v3 adaptive orchestration runtime: durable role packets, harness/model/effort routing, adapter trust, quota-aware cost policy, verification, private telemetry, replay, maturity, and isolated self-improvement. Human merge-to-main remains mandatory.

by dzungtr

Auto-review hook for Codex PermissionRequest events. A static deny-bucket blocks universally destructive commands instantly; everything else is decided by a bounded-turn LLM agent loop using the official Z.ai Python SDK (`from zai import ZaiClient`) and native function tools (a single `review` tool with an `action` enum: allow / deny / probe).

by 万联易达

研发规范与 AI Agent 技能库：DDL/SQL 审查、API 审查，包含测试、数据库、API、Git 四大规范