Claude Code and Codex plugins their authors filed under "productivity". All categories.
O problema não é falta de ideia, é o que recebe luz agora — planeja antes de implementar, responde em número, avisa no desvio e não chama de pronto sem a saída que prova
21 skills · 14 commands · 9 agents · hooks
sage-stack: a multi-agent development stack for Claude Code and Codex. Your session becomes a chief of staff, and a team of agents designs, builds, reviews and tests each change, with the rules held in code.
33 skills · 12 agents
The complete pstack 0.14 workflow port for Codex, with 44 skills, engineering principles, playbooks, and verification tools.
44 skills
44 production Claude Code skills across content, reels, SEO/AEO, client delivery, code quality, planning, and token efficiency.
41 skills
Lightweight SDLC workflow: capture backlog items, capabilities, decisions, drivers, milestones, principles, products, references, standards, tasks, and terms as markdown files with validated frontmatter. Ships task-level skills (task-work, task-review, task-ensure-ready, task-define) plus a JSON-schema-driven frontmatter validator every entity type plugs into.
39 skills
在 Claude Code 中使用 Clay：设置并登录 clay CLI，查询和分析 Clay 表格，在 Clay 的 GTM 数据库中搜索人员和公司，管理受众、信号、例程和工作流，并起草和审阅 Sequencer 营销活动。包含自动批准该插件自身 clay CLI 调用和 Clay skills 的 hooks；需要 Clay 账户。
38 skills · hooks
Plan creation, review, follow-through, and maintenance. Author an interactive HTML plan (implementation-plan), implement it through the acceptance and completion gates (build), review it (review-plan, finalize-plan), and ship a backlog in parallel (build-fleet). Also ships build-proposal, build-feature, deep-grill, prompt, prototype, design, publish-hub, documenting-plans, markdown-to-html, plan-status, plans-library, plans-open, and setup-sites. Full detail in the plugin README.
17 skills · 9 commands · 12 agents
Shipd commands and skills, namespaced under /s:
32 skills · 3 agents · hooks
Portable, file-based personal AI assistant (for development).
34 skills · 1 MCP server
Bloomberg-style financial terminal — 30 tools: quotes, charts, crypto, forex, portfolio risk analytics, SEC filings, FRED economics, technical analysis, stock screening, and Brave web search
6 skills · 27 commands · 1 MCP server · hooks
Project control, planning, implementation, code review, debugging, and code taste.
35 skills
33 productivity workflows + 1 agent — Google-style tech writing, ParentSquare district data CLI, Atrium publishing (AI Studio docs + HTML artifacts), beautiful HTML artifact generation (incl. self-contained data dashboards & charts), board policy formatting, PDF Builder, Documenso document signing, n8n workflow automation, document generation, research, TTS, enrollment automation, browser control, Google Workspace, and district operations
33 skills · 1 agent · 1 MCP server
AI-augmented research environment. Interview-first onboarding, Obsidian vault setup, document conversion, scheduled automation, and ongoing research tools for academics.
14 skills · 16 commands · 2 agents · hooks
Skill-first SDLC orchestrator: requirements -> spec -> plan -> TDD -> QA gates -> MR, with HITL/autonomous decision routing.
27 skills · 5 agents · hooks
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and MCP + hooks.
32 skills
AI Pilot workflow agents: sniper (code quality), research-expert, explore-codebase, websearch
19 skills · 12 commands · hooks
AI Pilot workflow agents: sniper (code quality), research-expert, explore-codebase, websearch
18 skills · 12 commands · hooks
Unified dev-workflow plugin — interview, spec, plan, tasks, implement, review — with docsmith docs governance and roadmap/issue tracking.
29 skills · 1 agent · hooks
Plans every prompt into a spec + Graph of Thought with HITL clarifications on a pluggable engine (Claude default, Grok optional), tracks it in Linear/Notion, and ships finished work through a Greptile-gated PR.
24 skills · 6 commands · hooks
Lossless output compression, a local code graph, a loop guard and lazy-senior-dev rules, in one plugin.
24 skills · 6 agents · hooks
Carta Investors 插件 —— 通过 Carta MCP Server 查询投资者数据、业绩基准、合规报告、AGM 演示文稿生成、品牌提取等的 skills。
29 skills · hooks
Core: 12 agents and 17 skills to plan, build, verify and publish safely, plus a hook that blocks leaking secrets and asks before destructive commands.
17 skills · 12 agents · hooks
Engineering philosophy ruleset — simple, efficient, deliberate. Enforces Intent Discovery thinking, stack audits, mid-task efficiency checks, snarky post-task suggestions, and cleanup protocols.
8 skills · 11 commands · 9 agents · hooks
Video editing skills — DaVinci Resolve vlog edits: speech-free travel vlogs (cut/stabilize, exposure/white balance, face mosaic, Gmarket Sans subtitles) and faceless talking developer vlogs (subtitles, project style guide, shot sketches)
29 skills
Skills and agents for Claude Code — TDD workflow, LLM wiki, skill packager, iterative review, and more.
27 skills · 1 agent · hooks
Skills and agents for Claude Code — TDD workflow, LLM wiki, skill packager, iterative review, and more.
27 skills · 1 agent · hooks
以对话方式管理 Carta CRM —— 通过 Carta CRM MCP Server 搜索、添加、更新和补全投资者、公司、联系人、交易、笔记和融资记录。
28 skills · hooks
Portable engineering harness (plan → work → verify → feedback) + an introspect skill that tailors .claude/ to a repo's stack.
18 skills · 9 agents · hooks
Per-project .brain/ knowledge engine: budgeted session context injection, an enforced knowledge SDLC (ingest / query / lint), a gated develop lifecycle (research → plan → build → review, wrapped per session), token discipline with receipts, and compounding domain expertise packs. Ships with five capability plugins from the official marketplace.
24 skills · 2 agents · 1 MCP server · hooks
Read-only advisor agents (architect, designer, reviewer, perf, principles, docs), profile-driven /pr and /ticket skills, enforcement hooks, and /harness-init.
9 skills · 17 agents · hooks