Coding & Dev Tools

PaLI-3: Smaller, Faster, Stronger

VQAv2: Making the V in VQA Matter

DINOv2 for Dense Prediction Tasks

Towards Open-World Segmentation of Parts

SVIT: Scaling up Visual Instruction Tuning

OpenCLIP: An Open Source Implementation of CLIP

Training Compute-Optimal Large Language Models

Mantis: Interleaved Multi-Image Instruction Tuning

Gemini: A Family of Highly Capable Multimodal Models

LLaVA-NeXT: Improved Reasoning, OCR, and World Knowledge

Probing Multimodal LLMs as World Models for Driving

AutoAugment: Learning Augmentation Strategies from Data

DALL-E 3: Improving Image Generation with Better Captions

Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask in any language for code review, issue or PR triage, release gates, publishing follow-through, or project audits. Not for debugging root causes or prose review.

Performance-coaching mode for repeated failures, passive behavior, completion-quality issues, or explicit try-harder requests. Uses structured troubleshooting and evidence-first delivery habits.

Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.

Establish and manage SSH connections to remote machines, including key generation, configuration, and file transfers. Use when connecting to remote servers, executing remote commands, or transferring files via SCP.

飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件（支持大文件分片下载）、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。

Use when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, efficient frontiers, scenario generation, or NVIDIA cuOpt.

Preparation guideline for organizing a US trademark application with the USPTO

Preparation guideline for organizing a Canadian trademark application with CIPO

Founder onboarding interview that captures company context across 7 dimensions. Invoke with /cs:setup for initial interview or /cs:update for quarterly refresh. Generates ~/.claude/company-context.md used by all C-suite advisor skills.

Financial leadership for startups and scaling companies. Financial modeling, unit economics, fundraising strategy, cash management, and board financial packages. Use when building financial models, analyzing unit economics, planning fundraising, managing cash runway, preparing board materials, or when user mentions CFO, burn rate, runway, fundraising, unit economics, LTV, CAC, term sheets, or financial strategy.

Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Use when assessing technical debt, scaling engineering teams, evaluating technologies, making architecture decisions, establishing engineering metrics, or when user mentions CTO, tech debt, technical debt, team scaling, architecture decisions, technology evaluation, engineering metrics, DORA metrics, or technology strategy.

Runbook Generator

C-suite orchestration layer. Routes founder questions to the right advisor role(s), triggers multi-role board meetings for complex decisions, synthesizes outputs, and tracks decisions. Every C-suite interaction starts here. Loads company context automatically.

Changelog Generator

Extreme Programming for AI-human pair development. Use when: pair programming with your AI, building incrementally with tests, working with clear role division, or the user mentions XP/YAGNI/simple design/continuous refactoring.

Recover session state from git, plans, and open PRs, then continue from the last completed phase without repeating work

Local build-error triage. Detects common compile errors and suggests fixes

Meta-skill — defines when to apply other skills automatically without being asked

Onboard into an unfamiliar repository fast before making any changes

Decide the highest-value safe thing to do right now in the active repo or workspace.

SKILL.md is an open specification released by Anthropic in 2025 that standardizes how tools discover and auto-invoke procedural knowledge (skills, patterns, guides, rules). Instead of each tool (Claude, Cursor, VSCode, CLI) maintaining isolated skill registries, SKILL.md enables a single skill to be published once and auto-invoked across any tool that speaks the spec.

Sync files (skills, packages/core/patterns, agents, specs) from EN canonical repo to PT mirror, inserting "Tradução pendente" blockquote after YAML frontmatter, then open PR.

Composite skill — take a PR from "I think it's ready" to merged with full gate verification. Chains pr-merge-readiness (verdict) → ci-watch / gh-fix-ci (if blockers) → gh-address-comments (if review needed) → ship (when verdict is MERGE). Use as the one-call answer to "can I merge this?" instead of running 4 skills sequentially.