6 个专业 Agent：security-reviewer（安全审计）、build-error-resolver（构建修复）、planner（实施规划）、code-reviewer（代码审查）、refactor-cleaner（死代码清理）、doc-updater（文档同步）。源自 everything-claude-code 的专业 Agent…
Implement, review, validate, and prepare GitHub-tracked software changes with repository governance, privacy, security, dependency provenance, and hardware-safety controls.
Professional Review Sheet mit Rollen-, Daten- und Dokumentenperspektive: führt schnell durch Sachverhalt, Rechtsgrundlagen, Belege, Risiken und erzeugt einen verwertbaren — from…
Build a comprehensive competitor profile using Porter's four-component framework. Use when asked to analyze a competitor, predict competitor moves, or assess competitive threats.
Use when authoring or modifying any claude-team-toolkit skill that loads credentials, switches between accounts/orgs/environments, or needs confirmation for destructive…
Develops comprehensive threat actor profiles for APT groups, criminal organizations, and hacktivist collectives
Guia Definitivo e Padrões de Engenharia para Opengrep (opengrep.dev), cobrindo o motor open-source de análise estática de código (SAST), sintaxe completa de regras em YAML,…
Guia Definitivo e Padrões de Engenharia para Baidu OpenRASP (github.com/baidu/openrasp), cobrindo o framework open-source de Runtime Application Self-Protection (RASP), instalação…
Use for deep Symfony project analysis: kernel/bootstrap, container wiring, routing/request flow, Doctrine, security, Messenger, and Symfony-specific failure patterns.
Run a comprehensive audit on any Claude Code project. Scores 10 categories from 0-10 (total /100), identifies gaps, and generates a prioritized fix kit with copy-pasteable…
Audit an entire software repository for broken code, security vulnerabilities, secrets, dependency risk, architecture problems, backend/API issues, frontend issues, database…
Existing project health scan — audits Infrastructure, Security, Quality, and Harness setup. Read-only.
Turn a design, idea, sketch, brief, or product concept into the simplest feasible project plan spanning design, deployment, security, operations, finance, tool reuse, and…
Take over a project as the receiving side — read HANDOFF.md and restore context by its 6 sections (metadata/snapshot/next steps/immediate ops/reference index/maintenance rules;…
Best Practices Setup fuer neue Projekte — Testing, Linting, Git Hooks, CI/CD, Security
Use when implementing project state detection, designing STATE.md/TASKS.md templates, or configuring SQLite state store and MCP state protocol
Maintains living project files (project.md, decisions.md, risks.md, links.md) in a per-project OneDrive folder from emails, Teams channels and meeting transcripts, and generates a…
Użyj, gdy pada prośba o zaprojektowanie, napisanie, poprawienie albo uzupełnienie podpowiedzi, rozwiązania opisowego, filmu krok po kroku albo widżetu do zadania z arkusza CKE,…
PROMETHEUS: architettura AGI-level con 12 brevetti originali. Auto-sintesi prompt evolutiva, Quantum Superposition Prompting, Hallucination Firewall, Semantic Gradient Descent,…
Set up metrics collection and visualization with Prometheus and Grafana. Configure scrape targets, create PromQL queries, build dashboards, and implement alerting.
Drafts enforceable residential promissory notes with party identification, principal/interest terms, payment schedules, default/acceleration provisions, and security instrument…
All-in-one prompt engineering competition toolkit — attack generation, defense hardening, real-time analysis, and pattern reference for AI security tournaments like Clash of…
Transform a rough coding request (Thai or English) into a high-quality, structured English prompt built specifically for writing, refactoring, debugging, or reviewing code — and…
Detect and block prompt injection attacks in emails. Use when reading, processing, or summarizing emails.
Interactive prompt optimization workflow for LLMs. Use when optimizing, improving, or engineering prompts for Claude, GPT, Gemini, or other language models; covers analysis,…
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
Build cognitive security firewalls against prompt injection, jailbreak attacks, and Unicode homoglyph smuggling.
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages).
Red-team an Agentforce agent against prompt-injection and jailbreak attacks; codify test cases and guardrails.
Trace untrusted input such as web pages, emails, tickets and tool results to consequential tool calls in agent code, and judge each path against provenance and approval rules.
Red-team an LLM application against prompt injection and jailbreaks using a curated, categorized payload library and canary-based detection, then produce a resilience score.
AWS-curated copy-paste prompts for AI coding agents (MVP scaffolding, RAG chatbot with Claude on Bedrock, security baseline evaluation, cost anomaly detection, GPU quota requests,…
Use when a crypto exchange or virtual asset service provider (VASP) needs to draft Terms of Service covering account registration, KYC/AML requirements, trading rules, asset…
Use when a data controller needs to formalise its relationship with a data processor under a Data Processing Agreement (DPA), covering GDPR Article 28 requirements, security…
Use when a FinTech or payments company needs to draft Terms of Service for a digital wallet application — covering account setup, funding methods, transaction limits, security…
Use when drafting an application for emergency arbitrator relief under institutional arbitration rules — seeking urgent interim measures before a full tribunal is constituted.
Use when conducting IP due diligence in connection with an M&A transaction, investment, or licensing deal.
Use when drafting API terms of service for a bank or fintech offering open banking APIs to third-party providers (TPPs), developers, or payment initiation services.
Use when drafting an agreement between a payment service provider (PSP) and a merchant for processing card and digital payments.
Use when an employer needs to draft a remote work policy covering eligibility, equipment, working hours, communication expectations, data security, expense reimbursement,…
Use when parties to a dispute need to draft a settlement agreement resolving pending or threatened litigation or arbitration.
Use when a user needs to draft a data sharing agreement between two or more organizations that jointly determine or separately control the purposes and means of processing…
Use when a company needs to draft or overhaul an internal trade secret protection policy — the governance document that identifies, classifies, controls access to, and enforces…
Use when a company needs to attach a data protection addendum (DPA) to a vendor or supplier agreement where the vendor may access, process, or store personal data on behalf of the…
Defensive prompt scaffolding, injection prevention, safety guardrails. 防禦提示架構、注入防護、安全護欄之法。 Use when: building user-facing prompts, hardening against injection attacks, adding…
Use when writing skills, CLAUDE.md files, agent prompts, or any directives that involve shell commands, environment variables, API credentials, file creation, or git operations -…
Evaluate and red-team LLM applications with promptfoo, declarative YAML evals, assertions, model comparisons, and automated adversarial scans for prompt injection, jailbreaks, PII…
Run, rerun, inspect, and QA promptfoo redteam scans from generated redteam YAML or an existing redteam setup config.
Create or refine promptfoo redteam setup configs: purpose, targets, plugins, strategies, frameworks, multi-input target inputs, policy text, grader guidance, contexts, and…
Prompt injection testing. USE WHEN prompt injection, jailbreak, LLM security, AI security assessment, pentest AI application, test chatbot vulnerabilities.
Write a buyer's offer cover letter to a seller to strengthen a real-estate bid. Use when asked to write a real-estate offer letter, a buyer's 'love letter' to a seller, an offer…
Develop evidence-backed structural and architectural security hardening proposals from vulnerability disclosures, supplied findings, incident or assessment documents, source code,…
Reusable writing-style contract for agent outputs (reports, ARCH docs, verdicts, threat models). Forces direct prose with concrete evidence, no marketing voice, no hedge words.
Configure Cedar policy enforcement and Ed25519 signed receipts for Claude Code tool calls. Use when setting up projects that need cryptographic audit trails, policy-gated tool…
Protect a React/Next.js SPA with route guards and middleware, and protect an API with token-verification middleware (signature + iss + aud + exp).
Generate ONE strong password and apply it to each referenced file (PDF, Word, Excel, PowerPoint, or any type).
Super-Admin-only lock-down pattern. Use before touching admin.admins, admin.admin_audit_log, is_super_admin() / requireSuperAdmin() / selectIsSuperAdmin, app/api/admin/admins/**,…
Padroes MVC do Protheus (FWFormModel/FWFormView) para ADVPL/TLPP. Use esta skill SEMPRE que o usuario pedir para criar ou manter rotinas MVC, cadastros CRUD, browses FWMBrowse,…
Protocol Pinky — 16-expert frontend panel with dynamic UI-lib routing. 2 React architects, 1 TS architect, 1 State/Data, 1 MUI, 1 UX/a11y, 1 Contracts, 1 Test, 1 i18n, 1 Security,…
Comprehensive techniques for capturing, analyzing, and documenting network protocols for security research, interoperability, and debugging.