Productivity plugins

VitaeContext gives AI agents a private, reusable source of truth about a person's career, then provides focused skills for turning that context into grounded professional work.

4 skills

Audio notifications + AI-controlled config for Claude Code, Cursor IDE, and Codex CLI events. Auto-bridges to Cursor 3.2.16+; native install for Cursor via 'audio-hooks install --cursor' and for Codex via 'audio-hooks install --codex'.

1 skill · hooks

AI code review catches structural issues — null derefs, leaks, races — about 65% of real defects. The other 35% are intent violations: bugs only catchable when you know what the code is supposed to do. Quality Playbook derives behavioral requirements from your codebase AND your docs (specs, issues, chat history), then drives a six-phase review against them. Finds the bugs that look right but aren't.

1 skill

Orchestrate Quality Playbook runs across multiple repos from one Claude Code session. The harness skill drives a disk-backed state machine via in-session ScheduleWakeup polling: each tick dispatches QPB worker subagents (Task tool), tails their heartbeats, advances the state machine, prints a status table, and reschedules — until every run reaches a terminal state or you write a STOP file. No external scheduler, no long-running daemon; the same ScheduleWakeup primitive the v1.5.7 watcher has run reliably for weeks.

1 skill

Deterministic decision capture + pre-task veto warnings from your self-hosted RoBrain stack or RoBrain cloud

hooks

從不同角度看問題，找出容易漏掉的選項與會改變判斷的資訊。

1 skill

Delegation system with workflow orchestration, specialized agents, and parallel execution for Claude Code

2 commands · 8 agents

Método jurídico aberto e executável por agentes de IA: base curada de STF/STJ, legislação, súmulas, temas e teses; 10 protocolos e motores locais. Fontes verificáveis, casos privados. Direito brasileiro, PT-BR.

10 skills

MCP server that orchestrates multiple Claude CLI instances as parallel workers with a real-time dashboard

1 skill · 1 MCP server

Investigate ambiguous, non-emergency health symptoms with lightweight intake, tracking, testing, analysis, and careful experiment planning.

1 skill

Personal IT guy for non-technical macOS users — 12 plain-language commands, 4 agents, observation-first onboarding, a machine profile that retires its own stale beliefs by retesting them, a locked and transactional state writer, a PreToolUse guard that blocks destructive shell commands, a toolbox that turns repeated chores into reusable micro-tools and offers automations you did not know to ask for, learning maps built from your own measurements, and answers in your chosen language while everything on disk stays English. Ships a Codex layout with the same hooks. macOS only. 129 assertions.

8 skills · 12 commands · 4 agents · hooks

Work with your SoftSync CRM from any AI assistant: find and update companies, contacts and deals, read emails and meeting summaries, check your calendar and book meetings, write notes, set reminders, manage forms and email templates, and run your automations.

18 skills · 1 MCP server

18 universal AI skills for Claude Code — planning, orchestration, product strategy, career workflows, research, content processing, UI/UX design, Obsidian knowledge management, document conversion, and Avanade-branded web generation

18 skills

A focused kit of feedback-first writing review skills for stress-testing drafts, arguments, pacing, clarity, and line-level prose.

13 skills

Audit and opt-in-fix classic SEO and AI-search visibility across a website or web codebase.

34 skills · 5 agents · hooks

Publication-quality plotting and schematics (Matplotlib, Seaborn, Plotly) (9 skills)

9 skills

Writes findings up in your own voice, with an AI-pattern review gate and a learning loop.

3 skills · 5 agents

Faculty research-lifecycle and academic administration (syllabus AI-policy, IRB/consent, post-award grant admin, recommendation letters, accreditation AoL) (6 skills)

6 skills

Matrix remote computer tools and coding workflows

4 skills · 1 MCP server

Agent skills for 37signals products, each driving its product's CLI. Bundles the Basecamp skills today; HEY and Fizzy join as their CLIs publish here (see the README).

4 skills

Document and Markdown conversion (MarkItDown, Open Notebook) (3 skills)

3 skills

Read and update your team's Folio wiki from Claude Code: the Folio MCP server and a skill that tells the agent how to work with pages, tables and boards.

2 skills · 1 MCP server

Architect/executor workflow over MCP — Claude Code or Google Antigravity drives a local LLM executor through structured phases, review gates, and telemetry.

5 skills · 1 MCP server

The vocabulary layer for Web and mobile H5 — turns a description the user can't quite phrase into one accurate sentence they can hand straight to an Agent, and names the term they just described but couldn't call. Applies in any turn rather than one stage: whenever someone says 「鼠标放上去变个色」「底下那条黑杠挡住按钮了」「弹窗底下还能滑」「看着有点土」, it finishes the actual work first and then drops the term, one plain-language explanation, and the trap that term most often falls into. 142 local entries across five books — web · h5 · motion · mini-program · fundamentals, zero network calls, searched by how a user would describe the symptom rather than by what the thing is called — because not knowing the name is the whole problem. Enforces three gates: every term must point at the exact words in the user's own sentence that triggered it, H5 terms ship in pairs because those traps are paired (吸底 ↔ 安全区, 弹层 ↔ 滚动锁, 输入框 ↔ 键盘顶起), and the work always ships before the vocabulary.

1 skill

Your own local Claude Tag, in the Claude app, Discord, Telegram, or a custom Claude Code channel.

36 skills · 7 agents · hooks

Security-first specification pipeline. prd-generator writes a full PRD with a threat model from a plain-language feature description. The 12 phoenix-* roles run the same pipeline stage by stage: context curation, scope, constraints, RFC 2119 requirements, ambiguity hunting, threat model, API contracts, verification matrix, delivery batches and a final ship gate.

13 skills

Scheduled briefs for Hermit from sources you choose, with story tracking, weekly summaries, and source-quality checks.

8 skills · 1 agent · hooks

Persistent memory for Claude across conversations.

1 skill · 4 commands · 1 agent · 1 MCP server

Automatic local memory across sessions and agents (Claude Code, Codex). No model calls to save.

1 MCP server · hooks

研发流程与导航工具集：Delivery Secretary、BRD、UC、PRD、UI Design、Prototype、API、分层及有限变更 HLD/LLD Review、Code Writer、授权溯源 Code Review、Test、Runbook。命令：/testany-eng:guide, /testany-eng:delivery-secretary, /testany-eng:brd-interviewer, /testany-eng:uc-interviewer, /testany-eng:prd-writer, /testany-eng:prd-reviewer, /testany-eng:ui-designer, /testany-eng:prototype-designer, /testany-eng:prototype-reviewer, /testany-eng:api-writer, /testany-eng:api-reviewer, /testany-eng:guardrails-writer, /testany-eng:guardrails-reviewer, /testany-eng:hld-writer, /testany-eng:hld-reviewer, /testany-eng:test-strategy-writer, /testany-eng:test-strategy-reviewer, /testany-eng:lld-writer, /testany-eng:lld-reviewer, /testany-eng:code-writer, /testany-eng:code-reviewer, /testany-eng:test-spec-writer, /testany-eng:test-reviewer, /testany-eng:runbook-writer

24 skills · 24 commands