Recently added agent tools.

## 📋 Metadata | Atributo | Valor | |----------|-------| | **ID** | `flutter-firebase` | | **Nivel** | 🟡 Intermedio | | **Versión** | 2.0.0 | | **Keywords** | `firebase`, `firestore`, `auth`, `cloud-messaging`, `analytics`, `storage`, `remote-config`, `crashlytics`, `provider` | | **Referencia** | [FlutterFire](https://firebase.flutter.dev/) | ## 🔑 Keywords para Invocación - `firebase` - `firestore` - `firebase-auth` - `cloud-messaging` - `firebase-analytics` - `firebase-storage` - `firebase-r

Use when behavior, setup, validation, public wording, data provenance, or workflow commands change and repository documentation may need to be updated.

Use when behavior, setup, validation, public wording, data provenance, or workflow commands change and repository documentation may need to be updated.

Use when behavior, setup, validation, public wording, data provenance, or workflow commands change and repository documentation may need to be updated.

Use when behavior, setup, validation, public wording, data provenance, or workflow commands change and repository documentation may need to be updated.

Generate varied practice problems, exercises, and drills with progressive difficulty and interleaving for skill mastery. Use for deliberate practice. Activates on "practice problems", "exercises", "drills", or "skill practice".

> **作者**: 邹英龙 > **更新日期**: 2026-04-29（最终版，所有修复已验证） > > 本文档记录Task6开发过程中踩过的所有坑、经验、原则和上下文。仅供开发参考，不属于最终交付内容。 > **适用范围**: Task6 多模态整网变异和验证（单机 + 多机） --- ## 核心原则（不可违背） ### 原则0：CogVideoX / InternVL3 跑通后作为基准 **CogVideoX 和 InternVL3 已成功跑通（单机 + 多机），证明Task6框架、环境配置、日志捕获逻辑、多机部署均正确。** **在调试其他模型时，以下部分禁止修改：** 1. **Task6核心框架**（`utils/task/task6.py`）： - 环境变量读取逻辑（`_init_config`） - PTA/MSA执行流程（`_run_pta_verify`、`_run_msa_verify`） - 多机并发启动逻辑（`ThreadPoolExecutor` + SSH/rsync） - 日志解析正则表达式 - 成功/失败判定逻辑 - 精度/显存/性能判定标准 2. *

Perform a structured audit of a codebase covering security, code quality, performance, dependencies, architecture, and testing hygiene, then produce a prioritized findings report. Use this skill whenever the user asks for a code review, code audit, security review, codebase assessment, "look over this repo", "what's wrong with this codebase", legacy-code triage, pre-acquisition technical due diligence, or any request to systematically evaluate the health of a project. Trigger even when the user

Browser automation via webctl CLI in Claude.ai containers with authenticated proxy support. Use when users mention webctl, browser automation, Playwright browsing, web scraping, or headless Chrome in container environments.

>

Imported skill one_on_one_template from openai

Second of two skills declaring the same name to trigger the duplicate-name violation.

将 Anthropic 官方品牌颜色与排版应用于任何可能受益于 Anthropic 外观与感觉的工件。当品牌颜色或样式指南、视觉格式或公司设计标准适用时使用。

This skill guides the agent in managing complex, long-term penetration testing campaigns. ## 1. Multi-Stage Planning A full pentest is not a single tool call. It is a sequence of dependent operations: - **Stage 1: Recon**: Broad discovery of assets (Shodan, CT Logs, Google). - **Stage 2: Scan**: Deep analysis of identified assets (FBH, MobSF). - **Stage 3: Research**: Intelligent mapping of findings to 0-day disclosures. - **Stage 4: Exploit**: Generation and execution of Proof of Concepts. - **

Integrate Honcho memory and social cognition into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, implementing the dialectic chat endpoint for AI agents, or wiring Honcho into bot frameworks (nanobot, openclaw, picoclaw, etc).

Reference system prompt and tool schemas for Lovable. Use when imitating, comparing, or analyzing Lovable's prompting style; designing prompts inspired by Lovable; or answering questions about how Lovable is prompted.

当有一个已验证的高潜力核心观点（如一个爆款社交媒体帖子），需要将其扩展为结构化的深度内容（如文章、新闻简报）时

Svelte 5 runes, component patterns, stores, transitions, and SvelteKit routing. Use when writing or reviewing Svelte code.

Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off. This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation. Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility

Drug-Drug Interaction Checker - Check interactions between multiple drugs using FDA interaction data, PubChem compound info, and ChEMBL target overlap analysis. Use this skill for clinical pharmacology tasks involving get drug interactions by drug name get compound by name get target by name. Combines 3 tools from 3 SCP server(s).

Viral Content Formula — Skill especializada para viral content formula

Busque documentação atualizada do Railway para responder perguntas com precisão. Use quando o usuário perguntar sobre recursos do Railway, como o Railway funciona, ou compartilhar uma URL docs.railway.com.

Install and initialize Pappardelle in a repository. Installs Pappardelle, checks prerequisites, asks about your VCS host, issue tracker, and project profiles, then generates a .pappardelle.yml config file.

Svelte 5 runes + SvelteKit adapter-static (SSG/SSR) patterns for hydration-safe state, store bridges, and reactivity that survives prerendering

>-

Analyzes iron condor credit spreads with OTM put and call spreads for range-bound trading. Requires numpy>=1.24.0, pandas>=2.0.0, matplotlib>=3.7.0, scipy>=1.10.0. Use when expecting sideways price action, want to collect premium in high IV, analyzing range-bound opportunities, or implementing neutral income strategies on stocks with defined trading ranges.

>

>

>

Analyze errors, stack traces, and logs to diagnose root causes and suggest fixes. Use when debugging Python, Node.js, Go, or Bash errors, interpreting Kubernetes events, diagnosing Docker issues, or resolving database connection errors.

Analyze aired series, including information retrieval, scene-by-scene analysis, five elements analysis, and web search. Suitable for deep analysis of series creation techniques, learning plot design

Diseño que funciona para todos sin necesidad de adaptación. Use cuando diseñe

>

Use when designing or auditing ESEC/FSE empirical evaluations, covering real subject systems, fair baselines, SE-standard statistics and effect sizes, qualitative and mixed-methods rigor, contamination-aware LLM ablations, provenance for mining studies, and matching evidence to the shape of each software-engineering claim.

Functional annotation and taxonomy inference from sequence homology.

Master modern web development. Learn HTML/CSS/JavaScript fundamentals, React/Vue/Angular frameworks, Node.js backend, databases, APIs, and full-stack architectures. Use when building web applications, learning web technologies, or choosing tech stacks.

Wenn es um Mandantenkorrespondenz — Form und Zugang: Templates in Schriftform und Textform im BGB geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.

Wenn es um Einstweiliger Rechtsschutz in Handelsvertreterstreitigkeiten nach Paragrafen 916 ff. ZPO in Handelsvertreterrecht und Vertriebsverträge geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und nächsten Schritt; liefert ein direkt nutzbares Arbeitsprodukt mit Prüfpunkten, Risiken und nächstem Schritt.

Master Rust 1.75+ with modern async patterns, advanced type system

Master modern business analysis with AI-powered analytics,

|

Track engagement metrics, measure campaign ROI, and analyze content performance across Instagram, Facebook, YouTube, and TikTok.

Azure Event Hubs SDK for Rust. Use for sending and receiving events, streaming data ingestion.

Structure a hard business decision — frame the choice, score options against weighted criteria, run a pre-mortem and stress-test, and produce a recommendation + decision record for any active brand

Create and manage Zoom meetings and access cloud recordings via the Zoom API. Use for queries like "create a Zoom meeting", "list my Zoom meetings", "show my Zoom recordings", or "schedule a meeting for tomorrow".

Transform comprehensive written content into purposeful spoken guidance. Use when adapting for speech, converting to spoken format, optimizing for listening, or creating audio content from written material. Keywords: speech, audio, spoken, listening, adaptation, podcast.

Synchronize reciprocity mandates across agent boundaries.

Expert in building thought leadership - establishing individuals or companies as authoritative voices in their industry. Covers positioning, content strategy, speaking, writing, and building genuine expertise into visible influence. Knows the difference between thought leadership and self-promotion, and how to build lasting authority. Use when "thought leadership, industry authority, executive visibility, speaking engagements, opinion content, industry voice, build authority, " mentioned.

This skill should be used when the user asks to "write an article", "help me write a blog post", "draft a technical article", "review my article", "check my writing", "improve this draft", "give me writing feedback", "find a topic", "what should I write about", or mentions "writing coach". Provides comprehensive guidance including topic selection, 17 writing skills, and reviewer collaboration from "Writing for Developers" by Piotr Sarna & Cynthia Dunlop.

コードやPRをレビューする際に使用。品質、保守性、よくある問題をカバー。