Productivity plugins

Twelve behavioral skills (a shared anti-sycophancy core plus eleven work-mode personas) that make Claude more direct, verification-driven, and efficient.

12 skills · 12 agents

Puts the right rules in context on every prompt, automatically — built for full-stack developers moving across frontend, backend, and SQL in one session, researchers working in bare or LaTeX-only directories, and teams who want adversarial review (security red/blue team, code critic) before merge. 222 rules across 30 domains, retrieved by relevance rather than dumped into CLAUDE.md, plus a plan-approval gate, session security hardening, and per-codebase lessons memory. Requires Python 3.10+ on PATH.

15 skills · 7 agents · hooks

18 intelligent skill routers + 1 external companion (x-skill-review) with optional multi-model orchestration via OpenCode and direct Gemini CLI. Plugin skills: x-do, x-research, x-review, x-verify, x-bugfix, x-mindful, x-design, x-api-pentest, x-qa, x-team, x-worktree (auto-applies docker-compose isolation when profile present), x-worktree-isolate, x-upstream, x-omo, x-gemini, x-guide, x-backlog, x-skill-improve.

18 skills · 1 command · hooks

Use for planning, TDD, verification loops, constraints, gardening, review, PRs, debugging, and ticket pipelines. Lean MIT skill stack for coding agents.

20 skills

Memory-augmented development workflows - 8 commands for planning, implementation, debugging, and research with persistent memory across sessions

2 skills · 9 commands · 8 agents · hooks

Agent skills for managing social media with Marky: authenticate and connect the API/MCP, create and schedule posts, plan a week of on-brand content, manage topics and your library, review performance, and repurpose what works.

16 skills · 2 commands · 1 MCP server · hooks

요구사항·계획 승인부터 구현·검증·재개까지

18 skills · 1 agent · hooks

Public workflow skills backed by the 101 MCP server.

16 skills · 1 MCP server · app connector

화면 설계 산출물 키트: 원본 → 문서 → 플로우 맵 → 화면설계서 → 디자인 캔버스 → 검수

11 skills · 6 commands

Cost-aware routing for Claude Code: a routing skill and session-start summary that tell the main session which tier handles which task, worker subagents pinned to Sonnet or Haiku with explicit tool lists, hooks that warn when a generic subagent is dispatched without a model, log each dispatch and permission request, and count advisor calls, plus opt-in alerts when Claude Code waits on a permission prompt, an opt-in live HTML board of a session's agents and tool calls, and a command that runs one task as a headless claude -p billed to an Anthropic API key instead of the subscription. Core-risk work and reviews stay at Opus or above; contained risk may run on Sonnet or grok and then gets the Opus review. Warns, never blocks. Requires jq. In Codex, the routing skill and seven worker procedures install without the hooks, alerts, or board.

2 skills · 6 commands · 7 agents · hooks

Strict Rust engineering workflows covering Axum, GraphQL, gRPC, TUI design, project baselines, review, refactoring, and remediation.

16 skills

Native macOS Swift and SwiftUI workflows for Liquid Glass design, project setup, Rust-core integration, visual QA, and regression control.

15 skills

Simple, lightweight local Kanban board for AI-human collaborative issue tracking

7 skills · 7 commands

Stashes findings, decisions and long outputs into .attic/ and keeps only a one-line index in context.

13 skills · hooks

Codex workflows and architecture, testing, debugging, Python, JAX, Polars, and Rust guidance.

14 skills

Evidence-driven code audits, root-cause diagnosis, simplification, remediation, improvement plans, and repository instruction policy.

14 skills

Orchestration & autonomy skills from broomva/skills: arc, autonomous, ctx-core, eve-forge, fleet, fleet-reconcile, governed-autonomy-loop, handback, handoff, p9, persist, provider-manager, resume, role-x.

14 skills

Video & multimedia skills from broomva/skills: brainrot-for-good, content-engine, creative-review, launch-video, ltx-video, motion-lab, video-cut.

13 skills

Apply while you sleep. Find jobs, tailor a resume from your master, fill applications in your own Chrome, and track them.

10 skills · 2 commands · 1 MCP server

Compact conversation-steering skills for changing direction, explaining decisions, asking for clarity, answering questions without implied action, finishing punted work, delegating research to a subagent, tightening prose, executing decisively, rethinking code architecture, and raising frontend quality.

12 skills

Extensible research workflows coordinated across local files, pluggable executors, and deterministic validation.

10 skills · 1 MCP server · app connector

Domain research skills.

11 skills · hooks

Search and analyze a Calibre library or Goodreads export

11 skills

Persistent vector+graph long-term memory for Claude Code, backed by Postgres+pgvector.

9 commands · 1 MCP server · hooks

Upstream presentation, document, PDF, image, Bilibili, PowerShell, frontend design, and Codex skill-development utilities.

11 skills

Session and personal productivity: collaborative brainstorming, plan stress-testing, session handoffs, meeting notes, a decision log, learning plans, a /prime command that loads project context, and a /weekly-review that assembles the week from evidence.

8 skills · 3 commands

Eat a foreign repository, digest it, and extract everything useful for your own repo without violating licenses.

5 skills · 2 commands · 3 agents · hooks

Governance & control skills from broomva/skills: agentic-control-kernel, architecture-design-principles, autoreview, bstack, cross-review, dogfood, harness-engineering-playbook, keel, legal-readiness, spec-contract, unhobble.

11 skills

Staff-engineer-level code review evaluating architectural alignment, failure modes, observability, security, and cross-team impact.

1 skill · 9 agents

A disciplined control loop for multi-window agent work across a tmux-resident fleet of Claude Code sessions: a Controller window claims requirement packages, plans task packages, prepares deliveries, imports immutable target results, obtains independent Test validation and reviews the evidence before completing and archiving a Demand. Explicit on-disk state roots keep every step auditable; Agents perform the host actions, Wakeflow owns the content and the verification. Supports macOS only (local file system); Linux and Windows are not supported.

4 skills · 4 commands · 1 MCP server · hooks