skill-contract

Shared vocabulary and discipline for designing deep modules and sharpening domain models. Use when designing or improving module interfaces, finding deepening opportunities, deciding seam placement, making code more testable or AI-navigable, refining ubiquitous language, writing or editing CONTEXT.md, or recording an ADR.

1 skill

Review a branch, PR, worktree, or implementation handoff against both repository standards and feature intent. Use for implementer self-review or independent review when the target repo may contain Spec Kit artifacts and repo-kit files; preserves separate Standards and Spec axes, fans Standards review out by changed layer, checks cross-layer dependency direction, and reports cited findings without editing code.

1 skill

对任意主题做深度、多来源、经交叉核查的调研,产出带引用、按置信度分级的报告。五阶段流水线:把问题分解成 4-8 个子问题 → 跨渠道(web/github/news/academic)并行 fan-out 调研 → 对每个发现做对抗式核查(证伪而非确认,发现者≠核查者)→ 交叉验证+圆桌综合、标注分歧 → 输出 HIGH/MEDIUM/LOW/CONTESTED 分级的引用报告。Provider-agnostic:同一份 skill 在 Claude Code、Kimi(kimi -p)、Codex(codex exec)三端都成立;fan-out 与核查阶段可跨模型互查(claude 的发现让 codex/kimi 证伪,反之亦然),对方模型作独立第二视角。当用户想「深度调研 / deep research / 全面调研 / 多角度调研 / research roundtable / 帮我把某主题查透并给带引用的报告」时使用。调用前:若问题欠具体(如「买什么车」却无预算/用途/地区),先问 2-3 个澄清问题收窄范围,再把澄清结果织进 args。

1 skill

Entry A of the Dual-Entry Design Flow: ingest, classify, and stockpile design inspirations, measured palettes, interaction/motion patterns, and video assets.

1 skill

howto skill

1 skill

面向日常学习、知识获取与好内容拆解沉淀的通用技能：支持「通道 A 主动求知（问题/概念 -> 快速多维检索四要素）」与「通道 B 素材拆解（视频总结/脚本/文章/URL -> 知识卡 + 制作技巧）」双通道输入，统一以「极简 TL;DR + 核心痛点问答（3–5 问）+ 立即可用清单 + 可选脚本/表达技巧拆解」直击痛点，并分类沉淀到 ~/Development/Personal/knowledge-vault/。

1 skill

Connect Claude Code to 325+ business data sources via Windsor.ai. Query marketing, sales, CRM, ecommerce, finance, and analytics data from Google Ads, Meta, HubSpot, Salesforce, Shopify, Stripe, and hundreds more — directly from your terminal.

Technical SEO optimization including meta tags, keywords, structure, and featured snippets

4 agents

Cross-platform ad management for Google Ads, Meta Ads, TikTok Ads, and LinkedIn Ads. 91 tools for keyword research, campaign creation, performance analysis, and budget optimization.

15 skills · 5 commands · 1 agent · 1 MCP server

Founder-mode executive team plugin: 13 cs-* C-suite agents (CFO, CMO, CRO, CPO, COO, CHRO, CISO, Chief of Staff, General Counsel, Chief Data Officer, Chief AI Officer, Chief Customer Officer, VP of Engineering) with distinct cognitive voices, plus 21 /c-level-agents:* slash commands — forcing-question office hours (CFO/CMO/CPO/CRO/CTO/CISO/GC/CDO/CAIO/CCO/VPE reviews), strategic sprint pipeline (brief → boardroom → decide → execute → post-mortem), and meta routing (/c-level-agents:founder-mode auto-router, /cs-onboard, /c-level-agents:cross-eval multi-model consensus, /c-level-agents:freeze cooldown lock). Wraps the 33 c-level skills with cognitive gearing, persona voice, and artifact-driven handoffs. The business-domain answer to YC Garry Tan's gstack.

22 skills · 13 agents

Agent coordination and meta-programming - multi-agent orchestration, workflow automation, and safe refactor governance. Works best with other voltagent plugins installed.

Comprehensive context engineering and harness engineering skills for production-grade AI agent systems: fundamentals, degradation patterns, compression, optimization, self-managed context (model-controlled live context editing), multi-agent coordination, long-horizon prompting (pseudo-formal task briefs for long-running and parallel agents), memory systems, tool design, filesystem context, hosted agents, evaluation, autonomous harnesses, self-improvement loops (RSI, meta-harnesses, evolutionary scaffold search), latent briefing (KV cache sharing between agents), project development, and cognitive architecture. Ships with a researcher operating system (rubrics, mechanism registry, claim provenance, run state machine, adversarial benchmarks, continuous loop).

19 skills