Latest Agent Skills

Use this when reviewing a full system design, architecture plan, or cross-service implementation for operational risk, boundary clarity, security posture, deployability, and maintainability.

Use when an existing Antigravity skill has weak triggers, vague instructions, missing constraints, or poor structure and needs to be improved. Trigger on requests to rewrite, tighten, split, or review a skill for better routing and reuse.

Use this when reviewing code changes for correctness, maintainability, security-sensitive logic, boundary separation, and likely regressions across any supported runtime or framework.

Use when the team needs API routes, action contracts, request and response shapes, error handling, pagination, or webhook patterns for a backend or BFF. Trigger on requests to design APIs before implementation.

Use when investigating a bug, runtime error, unexpected behavior, test failure, or crash. For systematic root cause analysis, error message interpretation, stack trace reading, reproduction steps, and targeted fixes. Activate when the user says "it's broken", "this doesn't work", "I'm getting an error", or "help me debug".

Use when code is hard to read, has duplication, is too complex, has grown beyond 300 lines, or needs restructuring without changing behavior. For extracting functions, simplifying nested logic, removing dead code, improving naming, splitting large files, and applying clean code principles. Activate when user says "clean this up", "this is messy", "simplify", "extract", or "improve readability".

Use this skill when the user is designing any visual system, UI, graphic, layout, brand asset, or interface and needs structured, high-quality, communication-first design decisions across typography, layout, color, imagery, and UX.

接活分诊 + 新项目初始化。用户说「开始干活」「接个新项目」，或当前代码根没有 CONTEXT.md 时用。

阶段② 详细设计。根据 design.md 第一章补全第二章各模块设计 + 第四章 ADR。

阶段③ 任务划分。把 design.md 拆成 tasks/<模块>.md 和 tasks/progress.md。

夜间模式：无人值守连续推进，遇歧义不停下、用最稳妥假设继续并记录。只能由用户手动开启。

阶段⑤ Review。审查已实现的代码并修复问题。

每完成一个任务或模块后收尾：多余物检测 + 更新文档 + 写下一轮当前任务 + 提醒 git。

阶段④ 执行。主 agent 跟踪进度 + 并行派生子 agent 实现模块，含代码门禁与调试档位。

阶段① 需求确认。以提问方式逐步确认需求，产出 design.md 第一章。

Read-only EVM client: wallets, tokens, gas across 8 chains.

Current weather and forecasts with wttr.in via curl for locations, rain, temperature, travel planning.

Terminal Spotify playback/search via spogo (preferred) or spotify_player.

Local speech-to-text with the Whisper CLI (no API key).

Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.

Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

24/7 system health monitoring, auto-restart crashed services, and multi-channel alerting (Discord, Slack, email).

Design one-off HTML artifacts (landing, deck, prototype).

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Manage Trello boards, lists, and cards via the Trello REST API.

Search and analyze your own session logs (older/parent conversations) using jq.

Delegate coding work to Codex, Claude Code, OpenCode, or Pi as background workers; not simple edits or read-only code lookup.

Generate charts and visualizations from structured data using D3.js and Chart.js.

Search meme templates, suggest formats, and generate local or hosted image memes.

Send third-party WhatsApp messages or sync/search WhatsApp history via wacli, not normal active chats.

Slack tool actions: send/read/edit/delete messages, react, pin/unpin, list pins/reactions/emoji, member info.

Scan codebases for known vulnerabilities using OSV, CVE, and GHSA databases.

Monitor RSS feeds, arXiv, HackerNews, GitHub trending for topics of interest on cron schedule.

Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).

Airtable REST API via curl. Records CRUD, filters, upserts.

Benchmark LLM performance across tasks — latency, quality, cost comparison.

HuggingFace hf CLI: search/download/upload models, datasets.

YouTube transcripts to summaries, threads, blogs.

Play Pokemon via headless emulator + RAM reads.

Pre-built cron job templates for common automation patterns.

Apple Reminders via remindctl: add, list, complete.

Search personal knowledge bases, notes, docs, and meeting transcripts locally using qmd — a hybrid retrieval engine with BM25, vector search, and LLM reranking. Supports CLI and MCP integration.

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.

Read, search, create, and edit notes in the Obsidian vault.

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Automatically collects dialectic memory to fine-tune local models.

Create, triage, label, assign GitHub issues via gh or REST.

Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.

Generate and manage Terraform/Pulumi infrastructure configurations.

Manim CE animations: 3Blue1Brown math/algo videos.

Knowledge comics (知识漫画): educational, biography, tutorial.

ASCII video: convert video/audio to colored ASCII MP4/GIF.

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.