AI & ML

sboghossian-mini-claude-for-legal Skill

Use when drafting a venture capital investment agreement for a Series A, B, or C round — covering investment terms, preferred share rights, anti-dilution protection, liquidation preference, board composition, investor veto rights, and protective provisions. Applicable for startups raising capital across MENA (UAE, DIFC, ADGM, KSA, LB, EG), UK, EU, and US. Trigger when a startup and its investors need to document a priced equity round and the full suite of investor protections.

techwavedev Bundle

Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW)

autohandai-community-skills Bundle

Upgrade flashinfer-python version in TensorRT-LLM. Fetches the latest releases from GitHub (stable and nightly), compares with the current pinned version, lets the user pick a target version, and updates all version references across the repo. Use when the user wants to bump or upgrade flashinfer.

autohandai-community-skills Bundle

Generate a source-backed starting `trtllm-serve --config` YAML for basic aggregate single-node PyTorch serving, aligned with checked-in TensorRT-LLM configs and deployment docs. Preserves explicit latency / balanced / throughput objectives. Excludes disaggregated, multi-node, and non-MTP speculative configs.

sboghossian-mini-claude-for-legal Skill

Use when a company needs to generate a structured due-diligence questionnaire to assess risks before onboarding a vendor or renewing a material vendor contract — covering data security practices, compliance certifications, business continuity, subcontractor management, insurance, financial stability, and incident notification procedures. Particularly important for regulated entities in MENA (financial services, healthcare, government) where third-party risk management is increasingly required by regulation.

sboghossian-mini-claude-for-legal Skill

Use when a privacy lawyer or compliance officer needs to assess the lawfulness of transferring personal data from one jurisdiction to another. Analyses adequacy decisions, appropriate safeguards (SCCs, BCRs, binding corporate rules), supplementary measures, and jurisdiction-specific risks. Covers GDPR (EU/UK), UAE PDPL, KSA PDPL, DIFC DP Law, ADGM DP Regs, and GCC data localisation requirements; includes Schrems II and post-Schrems transfer impact assessment methodology.

sboghossian-mini-claude-for-legal Skill

Use when reviewing an employment contract for legal and operational compliance — checking non-compete and non-solicitation clauses, IP ownership, termination terms and notice periods, and compensation structure. Flags provisions likely to cause legal disputes and proposes improved wording. Applicable across MENA (UAE, KSA, LB, EG), DIFC, ADGM, UK, EU, and US. Trigger when a company is reviewing standard employment contracts, when an employee wants a contract reviewed before signing, or when legal counsel is auditing HR documentation.

sboghossian-mini-claude-for-legal Skill

Use when a law firm, legal team, or lawyer needs to create accessible knowledge content for professional social media channels (LinkedIn, X/Twitter) explaining a legal or tax topic to a non-specialist audience. Produces a structured content brief and draft thread or post that translates legal complexity into plain-language explanations with concrete examples, without crossing into unauthorized legal advice. Particularly useful for MENA-facing law firms building their thought-leadership presence.

sboghossian-mini-claude-for-legal Skill

Use when drafting an embedded finance partnership agreement between a regulated financial institution (FinTech or bank) and a non-financial platform that will offer financial services through its application. Covers API integration, revenue sharing, regulatory responsibilities, customer ownership, data sharing, and liability allocation. Relevant for fintech deals in UAE (CBUAE, DIFC, ADGM), KSA (SAMA), LB, EG, UK (FCA), and EU. Trigger when a platform and a licensed financial partner need to structure their embedded banking, lending, or payments arrangement.

sboghossian-mini-claude-for-legal Skill

Use when a transactional lawyer needs to review an incoming Master Services Agreement (MSA) against the firm's or client's pre-defined negotiation playbook. Loads the playbook's positions on key clauses, compares the incoming MSA clause by clause, scores deviations, highlights required negotiation positions, and generates a tracked-changes redline with playbook-sourced replacement language. Integrates with the firm knowledge RAG for playbook retrieval.

sboghossian-mini-claude-for-legal Skill

Use when a lawyer or legal team needs to extract and distil the key legal issues, risks, and important points from a complex legal document into structured bullet-point format suitable for rapid review. Faster and more focused than a full summary; outputs are decision-quality points, not narrative prose. Applicable to contracts, regulatory instruments, court decisions, and due diligence reports across all jurisdictions including MENA (UAE, KSA, LB, EG, DIFC/ADGM).

sboghossian-mini-claude-for-legal Skill

Use when generating legal work product using AI for US-jurisdiction matters or advising US-based law firms on disclosure obligations. Governs when and how to disclose AI assistance in the engagement letter, matter file, and client communications so that attorney-client privilege and attorney work-product doctrine are not inadvertently waived. Provides model disclosure language for engagement letters and internal matter documentation protocols.

jmagly-ai-writing-guide Skill

Orchestrate governed persistent project memory across immutable evidence, llm-wiki, line-memory, reviewed session candidates, generated outputs, and bounded context packs.

techwavedev Skill

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

autohandai-community-skills Bundle

Detect and prevent QR code phishing (quishing) attacks that bypass traditional email security by embedding malicious URLs in QR code images within emails.

jmagly-ai-writing-guide Skill

Inject relevant past reflections into agent context at iteration start so agents learn from prior mistakes without repeating them

techwavedev Skill

Automate Asana tasks via Rube MCP (Composio): tasks, projects, sections, teams, workspaces. Always search tools first for current schemas.

techwavedev Skill

Automate Canva tasks via Rube MCP (Composio): designs, exports, folders, brand templates, autofill. Always search tools first for current schemas.

techwavedev Skill

Automate Close CRM tasks via Rube MCP (Composio): create leads, manage calls/SMS, handle tasks, and track notes. Always search tools first for current schemas.

autohandai-community-skills Bundle

Optimize existing Triton kernels for NVIDIA TileIR backend on Blackwell GPUs (sm_100+). Adds TileIR-specific autotune configs: occupancy, num_ctas, TMA descriptors. Covers kernel classification (dot-related, norm-like, elementwise, reduction), type-specific transformations, and PTX-vs-TileIR benchmarking. Triggered by: "optimize for TileIR", "add TileIR configs", "Blackwell optimization", "TMA descriptors", "2CTA mode", "occupancy tuning". Kernels use standard `import triton`; TileIR activates via ENABLE_TILE=1 when nvtriton is installed.

jmagly-ai-writing-guide Skill

Detect and use llms.txt files for LLM-optimized documentation. Use when checking if a site has LLM-ready docs before scraping.

techwavedev Skill

Automate Wrike project management via Rube MCP (Composio): create tasks/folders, manage projects, assign work, and track progress. Always search tools first for current schemas.

techwavedev Bundle

Deep RAG layer powered by Google NotebookLM + Gemini. The agent autonomously manages notebooks via MCP tools — authentication, library management, querying, follow-ups, and caching. Opt-in for users with a Google account. Default RAG is qdrant-memory. Triggers on: '@notebooklm', 'research my docs', 'deep search', 'query my notebook', 'check my notebooks'.

techwavedev Skill

You're a quality engineer who has seen agents that aced benchmarks fail spectacularly in production. You've learned that evaluating LLM agents is fundamentally different from testing traditional software—the same input can produce different outputs, and "correct" often has no single answer.

techwavedev Skill

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

techwavedev Skill

Lightweight Gmail integration with standalone OAuth authentication. No MCP server required.

techwavedev Skill

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, buildin...

shenjj2025-oss Skill

2025年最前沿的AI原生开发范式——VibeCoding。覆盖：Prompt-to-Product工作流、多轮对话管理、AI编码助手协作策略、代码质量保障、v0.dev/Lovable/Claude Code/Replit Agent工具链集成。触发词：vibecoding、VibeCoding、AI原生开发、提示即产品、AI pair programming、conversation-driven coding、prompt engineering for products

autohandai-community-skills Bundle

Develop and apply a multi-factor asset criticality scoring model to weight vulnerability prioritization based on business impact, data sensitivity, and operational importance.

jmagly-ai-writing-guide Skill

Patterns for finding, processing, and embedding cover artwork into media files

jmagly-ai-writing-guide Bundle

Preflight issue bodies for prompt-injection and supply-chain risk before address-issues acts on them

jmagly-ai-writing-guide Skill

Enable and explain the reusable human-in-the-loop gates used by persistent agent loops for destructive actions, false-positive overrides, and recovery escalation.

jmagly-ai-writing-guide Skill

Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly

autohandai-community-skills Skill

AI and ML skills for .NET: technology selection, LLM integration, agentic workflows, RAG pipelines, MCP, and classic ML with ML.NET.

techwavedev Skill

Create Pydantic models following the multi-model pattern with Base, Create, Update, Response, and InDB variants. Use when defining API request/response schemas, database models, or data validation ...

techwavedev Skill

Production-tested patterns for building AI agents that autonomously discover, > evaluate, and acquire token listings for cryptocurrency exchanges.