AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
techwavedev Skill X Twitter ScraperX (Twitter) data platform skill — tweet search, user lookup, follower extraction, engagement metrics, giveaway draws, monitoring, webhooks, 19 extraction tools, MCP server.
-
sboghossian-mini-claude-for-legal Skill Import Legal Risk Assessment Zacharie LaikUse when migrating the Zacharie Laik legal risk-assessment methodology into the mini-claude-for-legal format. This import adapter preserves the Laik practitioner framework — structured risk identification, qualitative scoring, and mitigation sequencing — mapping it into the standard skill model with MENA and civil-law jurisdictional context. Triggers when importing a risk-assessment skill attributed to or modelled on the Laik approach.
-
sboghossian-mini-claude-for-legal Skill Onboarding Persona Detection QuestionsUse when a new user must be guided through a brief onboarding quiz to determine their persona for a legal AI assistant. Defines the exact 3–4 quiz questions, the valid answer options, the mapping from answers to personas, and the anti-patterns that cause quiz abandonment. The quiz output feeds the B2C vs B2B fork, the starter prompt selection, and the persona setting in the user profile. Never ask more than 4 questions; always offer a skip path.
-
sboghossian-mini-claude-for-legal Skill Prompt Pack Board Resolution TemplateUse when generating a reusable board resolution template for any approval, appointment, or policy change, with fill-in fields for company name, action, authorized signatories, and jurisdiction-specific signature blocks. Corporate governance practice area; this is the blank-template companion to the substantive board-resolution skill — useful when the user needs a clean structural template to adapt for a recurring use case.
-
sboghossian-mini-claude-for-legal Skill Prompt Pack Content License AgreementUse when a licensor needs to grant rights to use content (images, video, articles, music, software, brand assets) to a licensee for defined purposes. Produces a structured Content License Agreement covering scope, exclusivity, permitted uses, restrictions, attribution, fees, and takedown obligations. Relevant across MENA (UAE, KSA, LB, EG), DIFC/ADGM, EU (GDPR and DSA), and UK; addresses how copyright treatment differs between civil-law MENA systems and common-law DIFC/ADGM/UK frameworks.
-
sboghossian-mini-claude-for-legal Skill Prompt Pack Expert Report ArbitrationUse when preparing the outline and structure of an expert report for international arbitration proceedings — covering the expert's qualifications, scope of instructions, methodology, data reviewed, opinions, and compliance with institutional requirements such as IBA Rules on Taking of Evidence. Applicable for financial damages, technical, industry practice, and valuation experts in arbitrations before ICC, LCIA, DIAC, ADCCAC, SIAC, and other institutions. Trigger when party-appointed expert counsel needs to structure a formal arbitration expert report.
-
sboghossian-mini-claude-for-legal Skill Prompt Pack Full Contract Risk ReviewUse when reviewing a commercial contract to identify legal risks, unclear clauses, missing protections, and terms that expose a named company to financial or legal liability. Produces a structured report with sections for high-risk clauses, ambiguous language, missing protections, one-sided provisions, and suggested revisions. Applicable to any commercial contract type across all jurisdictions. Trigger when a company or its counsel needs a systematic risk review before signing any significant agreement.
-
sboghossian-mini-claude-for-legal Skill Prompt Pack Master Services AgreementUse when drafting a master services agreement (MSA) establishing a framework under which a service provider will deliver ongoing services to a client under individual statements of work. Covers service scope, change orders, SLA terms, liability caps, insurance, IP ownership, data protection, and audit rights. Applicable across MENA, GCC, EU, UK, and US jurisdictions with civil-law and common-law adaptations.
-
techwavedev Skill LLM EvaluationImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or ...
-
techwavedev Skill Prompt CachingCaching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augm...
-
techwavedev Skill Prompt LibraryCurated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-...
-
autohandai-community-skills Bundle Nvidia Megatron Bridge Nemo Rl E2e TestingExternal NeMo-RL end-to-end validation workflow for Megatron-Bridge model/provider changes, including downstream compatibility checks, external RL lifecycle behavior, Megatron policy setup, HF import/export, checkpoint/resume, non-colocated vLLM refit, delta weight transfer, optional LoRA/generation variants, and questions such as "does this model work in NeMo-RL", "run NeMo-RL e2e", or "external RL loop validation". Covers running NeMo-RL Megatron policy jobs from a Bridge checkout, choosing GRPO/SFT/checkpoint/non-colocated refit variants, setting PYTHONPATH so NeMo-RL imports the local Bridge tree, and reporting pass/fail evidence.
-
autohandai-community-skills Bundle Nvidia Model Optimizer Release Cherry PickCherry-pick merged PRs labeled for a release branch into that branch, then open a PR and apply the cherry-pick-done label. Use when asked to "cherry-pick PRs for release/X.Y.Z", "pick PRs to release branch", or "cherry-pick labeled PRs".
-
autohandai-community-skills Bundle Nvidia Tensorrt LLM Perf Host OptimizationProfiles and optimizes TensorRT-LLM host/CPU overhead using line_profiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.
-
autohandai-community-skills Bundle Nvidia Tensorrt LLM Perf Torch Cuda GraphsApply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch make_graphed_callables, TE make_graphed_callables, MCore CudaGraphManager, FullCudaGraphWrapper, manual torch.cuda.graph), code compatibility, capture workflows, dynamic pattern handling, and troubleshooting. Triggers: CUDA graph, torch.cuda.graph, make_graphed_callables, reduce-overhead, graph capture, graph replay, kernel launch overhead, CudaGraphManager, FullCudaGraphWrapper, full-iteration graph, stream capture.
-
jmagly-ai-writing-guide Bundle Mission ControlOrchestrate multi-loop background operations via the Mission Control dashboard — start sessions, dispatch missions, monitor, and stop
-
sboghossian-mini-claude-for-legal Skill Efirm Finance Partner Comp AllocatorUse when a law-firm administrator or managing partner needs to model, allocate, or review partner compensation for a period. Covers the full input set (billable hours, origination credit, working credit, supervision credit, firm contributions), all major allocation models (lockstep, eat-what-you-kill, hybrid), and outputs a structured recommendation with sensitivity analysis and benchmarks. Designed for multi-jurisdiction law firms including MENA practices.
-
sboghossian-mini-claude-for-legal Skill Import Requete Cph Licenciement Faute GraveUse when migrating a French Conseil de Prud'hommes (CPH) pleading skill for gross-misconduct dismissal (licenciement pour faute grave) into the mini-claude-for-legal format. The adapter maps legacy CPH claim-drafting logic — requête, articulation des faits, qualification juridique, and demande indemnitaire — into the standard skill model under French employment law. Primary jurisdiction France; Barème Macron indemnity rules and procedural requirements of the CPH apply.
-
sboghossian-mini-claude-for-legal Skill Prompt Pack Complex Law Simple SummaryUse when a lawyer needs to summarise a complex legal or tax provision in plain language suitable for a non-lawyer client or business team. The output captures key compliance requirements, practical implications, and any action items — stripping technical jargon while preserving all substantive meaning. Applicable to any jurisdiction; MENA-aware for UAE, KSA, LB, EG, and GCC regulatory instruments.
-
sboghossian-mini-claude-for-legal Skill Prompt Pack Convert Law Into ChecklistUse when a lawyer or compliance professional needs to convert a legal provision, regulation, or statute into a practical, actionable compliance checklist for business use. The output enables non-lawyers to self-assess compliance without re-reading the underlying law. Applicable to any legal instrument and any jurisdiction; particularly useful for MENA regulations (UAE, KSA, LB, EG, DIFC/ADGM) that are frequently updated and not always available in accessible English-language summaries.
-
sboghossian-mini-claude-for-legal Skill Prompt Pack Due Diligence Request ListUse when preparing a comprehensive due diligence request list (DDRL) for an M&A acquisition — covering corporate documents, financials, material contracts, IP, real property, employment, litigation, regulatory compliance, and IT/data. Tailored to the target company's industry and jurisdiction. Relevant for transactions in MENA (UAE, KSA, DIFC, ADGM, LB, EG) and internationally. Trigger when buy-side counsel needs to send an initial or supplemental document request to the seller or its counsel.
-
sboghossian-mini-claude-for-legal Skill Prompt Pack Ip Due Diligence ChecklistUse when conducting IP due diligence in connection with an M&A transaction, investment, or licensing deal. Generates a comprehensive checklist covering patents, trade marks, copyrights, trade secrets, licences, assignments, encumbrances, and ongoing/threatened IP litigation. Relevant for target-company evaluation across MENA, EU, UK, and US IP registries.
-
sboghossian-mini-claude-for-legal Skill Prompt Pack Outside Counsel GuidelinesUse when drafting outside counsel guidelines (OCGs) for a company's legal department governing how external law firms bill, staff, manage, and report on legal matters. Covers billing requirements, approved rate structures, staffing and supervision standards, invoice submission, e-billing, diversity requirements, and performance metrics. Applicable to any in-house legal department managing external counsel spend.
-
sboghossian-mini-claude-for-legal Skill Prompt Pack Software License AgreementUse when a software licensor needs to draft a license agreement granting a licensee rights to use specific software. Covers license scope, permitted users, use restrictions, fees and maintenance, IP ownership, warranties, limitation of liability, and termination. MENA-specific guidance addresses UAE copyright law treatment of software, enforceability of seat-of-use restrictions across MENA free zones and onshore entities, and the distinction between software license and SaaS agreements in Arab civil-law jurisdictions.
-
techwavedev Skill Vercel AutomationAutomate Vercel tasks via Rube MCP (Composio): manage deployments, domains, DNS, env vars, projects, and teams. Always search tools first for current schemas.
-
techwavedev Bundle Audio TranscriberTransform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration
-
techwavedev Bundle Agent OrchestratorMeta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
-
jmagly-ai-writing-guide Skill Generate RealizationGenerate behavioral specifications (Layer 3) from use cases and architecture documents using multi-agent orchestration
-
jmagly-ai-writing-guide Skill Aiwg Utils QuickrefAUTO-INVOKE for ANY AIWG capability question, framework/addon/extension query, steward routing, MCP profile, or when unsure where to start. ALWAYS consult before filesystem search on .claude/.factory/.codex/.warp/etc. AIWG core utilities quick reference — always-on framing, steward, index, meta operations.
-
jmagly-ai-writing-guide Skill Execute FeedbackExecute tests on generated code and iterate until passing
-
autohandai-community-skills Bundle Implementing Cisa Zero Trust Maturity ModelImplement the CISA Zero Trust Maturity Model v2.0 across the five pillars of identity, devices, networks, applications, and data to achieve progressive organizational zero trust maturity.
-
autohandai-community-skills Bundle Nvidia Megatron Bridge Adding Model SupportGuide for adding support for new LLM or VLM models in Megatron-Bridge. Covers bridge, provider, recipe, tests, docs, and examples.
-
sboghossian-mini-claude-for-legal Skill Heuristic Refuse If No Jurisdiction GivenUse when a user submits a drafting, review, or legal advice request without specifying the applicable jurisdiction. Defines the decision rule — when to ask (hard ask for drafting and specific advice) versus when to assume and flag (general knowledge questions) — and provides the standard prompt for eliciting jurisdiction from the user. This is a P0 quality gate that prevents defective legal outputs grounded in the wrong governing law.
-
sboghossian-mini-claude-for-legal Skill Import Mediation Dispute Analysis Jinzhe TanUse when migrating the Jinzhe Tan mediation and dispute-analysis methodology into the mini-claude-for-legal format. This adapter preserves structured mediation-readiness analysis — party interests vs positions mapping, BATNA/WATNA scoring, settlement zone identification, and mediator-style reframing — and maps it into the standard skill model. Particularly valuable for cross-border commercial disputes in MENA, DIFC, ADGM, and Greater China corridors.
-
sboghossian-mini-claude-for-legal Skill Prompt Pack Arbitration Cost SubmissionUse when drafting a costs submission in an international arbitration proceeding seeking recovery of a party's legal fees, expert fees, arbitration institution costs, and other recoverable expenses. Arbitration practice area; covers DIAC, ICC, LCIA, SIAC, and CRCICA cost recovery principles with MENA-specific notes on cost allocation practices and tribunal discretion.
-
sboghossian-mini-claude-for-legal Skill Prompt Pack Corporate Governance PolicyUse when a company needs to draft or update a Corporate Governance Policy covering board structure, director qualifications and independence, board evaluations, succession planning, shareholder engagement, and compliance with applicable governance codes. Relevant across MENA (UAE, KSA, LB, EG) and for entities subject to DIFC/ADGM, DFM, ADX, Tadawul, or international listing requirements. Addresses civil-law and common-law governance frameworks and the intersection with Sharia-compliant governance in GCC markets.
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include nvidia-megatron-bridge-nemo-rl-e2e-testing, nvidia-model-optimizer-release-cherry-pick, nvidia-tensorrt-llm-perf-host-optimization. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.