Latest Agent Skills

PUA Shot — compact all-in-one PUA reference for explicit injection into sub-agents or short sessions. Strong flavor, same evidence-first behavior.

妈妈唠叨模式 — 中国式妈妈提醒风格的生产力 coaching。底层行为仍是结构化排障、证据优先、完成质量检查。

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".

Oracle Database guidance for SQL, PL/SQL, SQLcl, ORDS, administration, app development, performance, security, migrations, and agent-safe database workflows. Use when the user asks to write, edit, rewrite, review, format, debug, tune, or explain SQL; create or refactor PL/SQL; use SQLcl, Liquibase, ORDS, JDBC, node-oracledb, Python, Java, .NET, or database frameworks; troubleshoot queries, sessions, locks, waits, indexes, optimizer plans, AWR, ASH, migrations, schemas, users, roles, privileges, backup, recovery, Data Guard, RAC, multitenant, containers, monitoring, auditing, encryption, VPD, or safe agent database operations.

Mem0 Platform SDK for adding persistent memory to AI applications. TRIGGER when: user mentions "mem0", "MemoryClient", "memory layer", "remember user preferences", "persistent context", "personalization", or needs to add long-term memory to chatbots, agents, or AI apps. Covers Python SDK (mem0ai), TypeScript SDK (mem0ai), and framework integrations (LangChain, CrewAI, OpenAI Agents SDK, Pipecat, LlamaIndex, AutoGen, LangGraph). Also covers the open-source self-hosted Memory class. This is the DEFAULT mem0 skill for ambiguous queries. DO NOT TRIGGER when: user asks about CLI commands, terminal usage, or shell scripts (use mem0-cli), or Vercel AI SDK / @mem0/vercel-ai-provider / createMem0 (use mem0-vercel-ai-sdk).

Weed the Allium garden. Find where Allium specifications and implementation code have diverged, and help resolve the divergences. Use when the user wants to check spec-code alignment, compare specs against implementation, audit for spec drift or violations, sync specs with code or code with specs, or verify whether the implementation matches what the spec says.

Tend the Allium garden. Use when the user wants to write, edit, update, add to, improve, clarify, refine, restructure, fix or migrate Allium specs. Covers adding entities, rules, triggers, surfaces and contracts, fixing syntax or validation errors, renaming or refactoring within specs, migrating specs to a new language version, and translating requirements into well-formed specifications. Pushes back on vague requirements.

Run vet immediately after ANY logical unit of code changes. Do not batch your changes, do not wait to be asked to run vet, make sure you are proactive.

Vue 3 Composition API, script setup macros, reactivity system, and built-in components. Use when writing Vue SFCs, defineProps/defineEmits/defineModel, watchers, or using Transition/Teleport/Suspense/KeepAlive.

Audit, plan, and implement SEO improvements across technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy. Use when the user wants better search visibility, SEO remediation, schema markup, sitemap/robots work, or keyword mapping.

Rewrites and polishes prose in Chinese or English, removes AI-like wording, and reviews product localization copy while preserving intent for drafts, docs, release notes, launch copy, and social posts. Use when users ask in any language to draft, rewrite, proofread, localize, polish release notes, remove AI-like wording, or prepare launch and social copy. Not for code comments, commit messages, or inline docs.

Turns rough ideas into approved, decision-complete plans with validated structure before coding. Use when users ask in any language for planning, architecture, design direction, feasibility, value judgment, or whether a feature is worth doing before implementation. Not for bug fixes or small edits.

Runs a six-phase research workflow that turns unfamiliar domains, source bundles, or collected material into publish-ready output. Use when users ask in any language to research, study, deep-dive, compile sources, synthesize unfamiliar material, or turn a source bundle into a coherent reference. Not for quick lookups or single-file reads.

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.

SB Leader 夸夸模式 — ENFP 型领导，懂情绪有节奏。底层行为不变（三条红线、方法论），旁白从施压变成共情+鼓励+偶尔戏谑吐槽。Triggers on: '/pua:yes', '夸夸模式', '唠嗑模式', '情绪价值', 'yes', '夸我', '鼓励模式'.

Use for PUA/try-harder productivity coaching when the user expresses frustration, repeated failure, quality complaint, passive behavior, says retry/change approach/don't give up, asks for evidence/completion check/test before done, or wants Ding-style workplace reminders. Triggers include: try harder, stop giving up, figure it out, again??, why still failing, change approach, no evidence, run tests, done without proof, 换个方法, 再试试, 别摆烂, 别偷懒, 为什么还不行, 又错了, 证据呢, 没跑测试别说完成, 验收, 闭环, 自嗨, 置身钉外, 无招, 老板体感. Do not use for calm first-attempt requests.

PUA Pro extensions: self-evolution notes, compaction state continuity, KPI-style summaries, flavor switching, and feedback tools.

P10 CTO mode — define strategic direction, design org topology, manage P9 teams. Use when user says 'CTO模式', 'P10', '战略规划', '架构委员会', or when facing cross-team architectural decisions. Produces: strategic input templates + org design.

Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.

Build durable backend AI agents with the eve framework. Use when creating, editing, or debugging an eve project — agent instructions, skills, tools, connections, channels, sandboxes, subagents, schedules, or evals.

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.

Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report in any language errors, crashes, broken behavior, regressions, failing tests, screenshot evidence, or something that used to work and now fails. Not for code review or new features.

P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents. Produces: Task Prompts (六要素) + P8 team delivery.

P7 Senior Engineer mode — solution-driven execution under P8 supervision. Use when user says 'P7模式', '方案驱动', or when spawned as sub-task executor by P8. Produces: implementation plan + code + 3-question self-review, delivered via [P7-COMPLETION].

Produces distinctive, production-grade UI for pages, components, visual interfaces, typography, and screenshot-driven polish. Use when users ask in any language for UI, page, component, frontend, typography, screenshot-grounded visual polish, or complaints that a screen looks unclear, ugly, inconsistent, or visually wrong. Not for backend logic or data pipelines.

Search local markdown knowledge bases, notes, docs, and wikis with QMD. Use when users ask to find notes, retrieve documents, inspect a wiki, answer from indexed markdown, or set up QMD access.

NLVR2: A Visual Reasoning Benchmark for Natural Language

Multimodal Few-Shot Learning with Frozen Language Models

DALL-E 3: Improving Image Generation with Better Captions

Alpaca: A Strong, Replicable Instruction-Following Model

3D-LLM: Injecting the 3D World into Large Language Models

Emu2: Generative Multimodal Models are In-Context Learners

No Robots: A Dataset of Personally Written Instructions

MMBench: Is Your Multi-modal Model an All-around Player?

ImageNet: A Large-Scale Hierarchical Image Database

Flamingo: A Visual Language Model for Few-Shot Learning

DreamLIP: Language-Image Pre-training with Long Captions

Deduplicating Training Data Makes Language Models Better

AutoAugment: Learning Augmentation Strategies from Data

Label Noise SGD Provably Prefers Flat Global Minimizers

EVA-CLIP: Improved Training Techniques for CLIP at Scale

nuScenes: A Multimodal Dataset for Autonomous Driving

LaCLIP: Improving CLIP Training with Language Rewrites

Probing Multimodal LLMs as World Models for Driving

LISA: Reasoning Segmentation via Large Language Model

DriveLM: Driving with Graph Visual Question Answering

Donut: Document Understanding Transformer without OCR

RefinedWeb: A Falcon's Recipe for High-Quality Web Data

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

LLaVA-Critic: Learning to Evaluate Multimodal Models

Scaling Vision Transformers to 22 Billion Parameters

LongVA: Long Context Transfer from Language to Vision

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Gemini: A Family of Highly Capable Multimodal Models

DataPerf: Benchmarks for Data-Centric AI Development

CogVLM: Visual Expert for Pretrained Language Models

Kinetics-400: A Large Video Understanding Dataset

Mosaic Augmentation for Detection and Segmentation

Mantis: Interleaved Multi-Image Instruction Tuning

Copy-Paste Augmentation for Instance Segmentation