Recently added

Personal AI-coding discipline harness — one developer's opinionated AI-CODING-SPEC v6.35, enforced via Claude Code hooks + shipped with the plugin

실무에서 막히는 순간에 꺼내 쓰는 업무 도구함. 조사·기획·보고·카피·이미지·데이터·자동화 7개 영역 52개 상황에 맞춰 문서·메시지·체크리스트를 만들어준다. 영역 스킬이 상황을 판별해 해당 지침으로 수행하며, 모르는 것은 추정하지 않고 확인 필요로 남긴다.

경영컨설팅 펌 수준의 대시보드·보고서를 만든다. 독자가 무엇을 모르는가에 따라 진단·선택·감시·추적 네 유형으로 형태를 나누고, 유형 확인 → 자료 → 스펙·배치 확인 → 렌더링 → 검수 5단계로 돈다. 전달 전에 소스 검사와 실제 렌더 검사 스크립트가 돌고, 만든 맥락이 없는 서브에이전트가 결과물을 다시 본다.

도서 제작 수량을 근거 있게 정한다. 신간은 경쟁서 시장에서 역산해 첫해 수요와 초판 부수를 잡고, 기간본은 자사 출고 추세와 재고에서 소진 시점·발주 마감일을 잡아 재제작 수량을 낸다. 개정·폐간 예정이 있으면 잔여 수명까지만 찍도록 상한을 건다. 직접 조정할 수 있는 HTML 보고서까지 만든다.

새로 알게 된 지식(용어·개념·판단)을 atomic 노트로 분해해 Obsidian vault에 쌓고 링크로 연결한다. 기존 노트와 alias를 대조해 중복을 막고, 아직 노트가 없는 링크를 다음에 정리할 목록으로 뽑아준다.

Willow sovereign agent platform — SQLite store, Postgres knowledge base, Kart task queue, plus the hooks and skills that keep them used correctly.

Maps repositories, creates specialist Navigators, and preserves verified code rationale between Claude Code sessions.

Portable spec-driven development for Claude Code, Codex, Hermes Agent, and OpenCode with human-readable contracts, durable operational state, traceability, bounded autonomous correction, and isolated fleets.

Integração com YouTrack Cloud via MCP oficial embutido (2025.3+) — issues CRUD, busca com query language, comentários, tags, artigos da knowledge base e log de trabalho. Fallback REST autenticado para o que o MCP não cobre: agile boards, sprints, relatórios de tempo, anexos e operações em lote. Setup guiado com token fora do repositório.

Stack-agnostic UI/UX engineering framework for Claude Code — 6 real subagents + inline orchestrator/theme personas, 5-phase workflow with human gates, Figma integration, WCAG 2.1 AA, deterministic SQLite audit via hooks. Supports shadcn-vue, shadcn/ui, PrimeVue, Untitled UI, Tailwind Plus, and custom stacks.

Configure and manage Claude Code status line — installs a rich, configurable bash status bar (single-jq-pass, dynamic colors, formatted tokens, truncated paths) showing model, git branch, context usage, rate limits, and token counts.

Produção de criativos para redes sociais com orquestração de APIs de geração no centro — Ideogram, Leonardo, Flux, Runway e Freepik/Magnific via wrappers com trava de gasto; triagem de custo, engenharia de prompt, consistência visual e curadoria de variações. Figma como camada opcional de composição. 19 skills, 4 subagentes, revisão de acessibilidade obrigatória.

Review, refactor and benchmark Agent Skills across Claude Code, Codex, Hermes Agent and OpenCode, with runtime and model discovery and objective headless A/B benchmarks.

Portable quality assurance workflows, specialist guidance, evidence handling, and verifiable HTML and PDF reporting for Claude Code, Codex, and Hermes Agent.

PRD creation framework for Claude Code — 12-step interview-driven Product Requirements Documents, run inline (the interviewer talks to you; zero subagents by design), technology-agnostic, Markdown + canonical JSON export, deterministic SQLite audit via hooks.

Disciplined, approval-gated development: product requirements, executable roadmap, brainstorm-gated plans, subagent-driven execution with a ledger and bounded fix loop, adversarial verification, and isolated cmux fleets.

Integração com PostgreSQL via servidor MCP próprio (@soarescbm/postgres-mcp, npx) — SELECT somente-leitura validado por AST, inspeção de schema (tabelas, índices, constraints) e mutações DML/DDL com dry-run obrigatório (preview antes de executar). Setup guiado com a connection string fora do repositório.

Integração com Obsidian via servidor MCP embutido no plugin comunitário Local REST API (HTTPS local, self-assinado) — leitura, escrita e edição estruturada de notas (heading/block/frontmatter), busca por JsonLogic e por texto livre, tags, arquivo ativo e comandos da paleta. Panorama só-leitura do vault. Setup guiado com API Key fora do repositório.

Integração com GLPI 10.x e 11.x pela API REST Legacy V1 via servidor MCP próprio (@soarescbm/mcp-glpi, npx).

Runtime-independent, spec-driven development with operational health, audit, maintenance, PWDEV Code migration, isolated autonomous fleets, and guarded external CLI delegation.

Simplified AI-assisted feature development — PWDEVIA 7-question action plans created inline (interviewing you, max 2 rounds), executed by a real executor subagent with fresh context and IMPLEMENT/REPORT modes, an advisor subagent (strong model) for hard mid-task decisions, read-only consumption of pwdev-code's curated project memory when present, deterministic SQLite audit via hooks. Fast, practical, no ceremony.

Visual planning with Excalidraw diagrams through an MCP server, portable across Claude Code and Codex.

Framework de DevOps com postura de execução segura — leitura livre, mutação sob confirmação por comando, destrutivo bloqueado. 24 skills cobrindo AWS, Kubernetes, Docker, Linux, Nginx, PostgreSQL, observabilidade, incidente, segurança, Proxmox, automação, performance, backup, Laravel, confiabilidade, FinOps, infraestrutura de IA, quality gates e documentação contínua. 4 subagentes e guard script como segunda barreira.

Framework de copy genérico e treinável — um arquivo de contexto define marca, ICP e voz, e 20 skills cobrem o ciclo completo: pesquisa VOC, brand voice, criação (landing, social, ganchos, reaproveitamento), revisão em 7 sweeps com anti-slop, e camada de análise que fecha o loop (perf-analyzer, perf-patterns, perf-optimize). Inclui 5 subagentes reais e revisão adversarial de conversão.

Spec-driven development framework — hybrid orchestration with 8 real subagents (executor, advisor, simplifier, code-reviewer, QA, adversarial verifier, researcher, roadmap), per-task model routing by complexity, curated project memory graph feeding every spawn, opt-in parallel waves with worktree isolation, /pwdev-code:fleet for running multiple phases end-to-end (plan→execute→review→verify) unattended in isolated worktree+docker+tmux sessions, external CLI delegation (codex, opencode, kimi, gemini, kiro + smart /delegate), optional external reviewer CLI, strict dual-verifier mode, 6 phases with correction loops, deterministic SQLite audit via hooks, and extensible skills that turn requirements into verified, traceable code.

Segundo cérebro persistente em Markdown — LLM Wiki no padrão Karpathy + Open Knowledge Format v0.2: ingestão com discussão e citação por afirmação, consulta com síntese citada e incorporação de respostas duráveis, lint de conformidade com fixes aprovados. Servidor MCP embutido somente-leitura (6 tools, Node puro, zero dependências).

Focused AI evaluation, retrieval, privacy, tool testing, and human review workflows.

Self-improving learning loop across coding-agent sessions: retrieval, capture, consolidation, and cross-project transfer

Salesforce delivery harness for Claude Code: parallel multi-agent workflow, documentation-grounded Salesforce and fflib skills, deterministic hooks, and local plus post-deploy verification gates.

Extremely complete reference toolkit for vibe coders and developers: frontend, backend, security, testing, architecture, devops, git/DX, and AI-integration guidance, with routing to specialized design/security skills when available.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

fixture is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.