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.
-
tryboy869 Bundle Python Django Best Practices Cursorrules Prompt Fi CursorrulApply for python-django-best-practices-cursorrules-prompt-fi. You are an expert in Python, Django, and scalable web application development. Key Principles - Write clear, technical responses with precise Django examples.
-
outlinedriven-odin-claude-plugin Bundle Engineering RetrospectiveUse when a user requests an engineering retrospective for a period. Not for agent-environment retrospectives: use agent-environment-retrospective. For learning milestones: use learning-retrospective.
-
pleaseai Bundle Claude Code Plugin BuilderCreates Claude Code plugins with proper manifest structure, directory layout, and components (commands, agents, skills, hooks, MCP servers). This is for Claude Code plugins (`.claude-plugin/plugin.json`) — for Codex plugins (`.codex-plugin/plugin.json`) use the `plugin-creator` skill, and for Cursor plugins (`.cursor-plugin/plugin.json`) use the `create-plugin-scaffold` skill instead. Use when user requests creating plugins, adding slash commands, integrating MCP servers, setting up hooks, migrating Gemini extensions, or mentions "plugin.json", ".claude-plugin", or "marketplace.json". Handles plugin testing, debugging, and marketplace distribution.
-
pleaseai Skill Validating PluginsThoroughly validate a Claude Code plugin's manifest, directory structure, commands, agents, skills, hooks, and MCP config, then report issues by severity. Use when the user asks to validate, check, audit, or lint a plugin, verify a plugin.json or plugin structure, debug why a plugin won't load, or mentions "plugin validate", "invalid manifest", or "plugin not loading".
-
pleaseai Skill Tosspayments Integration GuideTossPayments payment integration documentation access via MCP. Use when integrating TossPayments payment widget, checkout flow, payment approval API, or when user mentions 토스페이먼츠, 결제, 결제위젯, 결제 승인, payment widget, TossPayments SDK, payment approval.
-
pleaseai Skill Skillopt SleepUse when the user wants their Claude agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, memory/skill consolidation, or says things like 'make my agent better the more I use it', 'review my past sessions', 'learn my preferences', 'consolidate what you learned', 'run the sleep cycle', or wants to schedule offline self-optimization. Drives the skillopt_sleep engine: harvest past sessions -> mine recurring tasks -> replay offline -> consolidate validated CLAUDE.md/SKILL.md behind a held-out gate.
-
fdu-ins Skill Takaful Ifrs17Activate for: takaful, Islamic insurance, wakala model, mudaraba takaful, participants fund, qard hasan takaful, takaful deficit, family takaful, general takaful, IFRS 17 takaful, MFRS 17 takaful, retakaful, wakala fee, takaful surplus, takaful operator, participants risk fund.
-
fdu-ins Bundle Cyber InsuranceUSAP agent skill for Cyber Insurance. Assess cyber insurance coverage adequacy, identify coverage gaps, maintain claim-readiness evidence, and support renewal applications.
-
outlinedriven-odin-claude-plugin Bundle SetupUse when the user asks to set up the agent environment. Covers credentials, placeholders, tool access checks, a uv venv, a pack install, or a role-model mapping file. Not for unattended runs.
-
fdu-ins Skill Insurance DomainUse when modifying domain/models/, domain/services/, adaptor/llm/, or any business logic involving insurance terms, coverages, or risk rules. Also use when adding new fields, endorsements, or coverage types.
-
pleaseai Skill Optimize Skill PerformanceRun task evals, analyze results, diagnose failures, apply targeted fixes, and re-run to verify improvements. Use when debugging evaluation scores, fixing failing or regressed criteria, analyzing why eval criteria pass or fail, reviewing eval rubric quality and redundant criteria, tracking before/after score improvements, editing plugin content to fix specific failing behaviors, or improving agent performance based on eval evidence.
-
pleaseai Skill Compare Skill Model PerformanceRun task evals across multiple Claude models, compare results side-by-side, and optimise. Use when you want to benchmark a skill across models, compare haiku vs sonnet vs opus performance, run multi-model comparison or benchmark reports, identify model-specific gaps versus universal plugin gaps, evaluate whether a skill works for all model tiers, or validate a skill before publishing it to the registry.
-
outlinedriven-odin-claude-plugin Bundle Typescript Type HardeningUse when TypeScript has type errors, failing inference, or needs type mechanism repair (generics, infer, mapped, branded). Not for strict flags or proactive shaping: use typescript-best-practices.
-
outlinedriven-odin-claude-plugin Bundle Agent Environment RetrospectiveUse when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.
-
outlinedriven-odin-claude-plugin Bundle Instruction Phrasing MicrotestUse when changing the wording of a rule in a skill, prompt template, or agent instruction where the change is meant to alter model output.
-
outlinedriven-odin-claude-plugin Bundle Multi Agent Tournament ScorecardUse when agent strategies need a reproducible finite tournament under a frozen evaluation protocol. Not for open-ended or infinite matchups: use a continuous benchmark.
-
outlinedriven-odin-claude-plugin Bundle PrototypeUse when asked to prototype one design question through a cheap logic or UI experiment, including button-driven state-model checks. Not for polished artifacts: use polished-web-prototype.
-
xfstudio Skill Spec PlanExecute implementation planning workflow to generate design artifacts (research.md, data-model.md, contracts/, quickstart.md). Use when user says "/spec-plan", "create a plan", "plan the implementation" after /spec-specify or /spec-clarify.
-
pramoddutta Skill Progressive Web App TestingPWA testing skill covering service worker validation, offline mode testing, cache strategy verification, web app manifest testing, push notification testing, install prompt testing, and background sync verification.
-
pramoddutta Skill Agent Browser AutomationFast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
-
pramoddutta Skill AI Agent EvaluationComprehensive evaluation patterns for AI agents including multi-turn conversation testing, LLM-as-judge frameworks, benchmark suites, regression detection, and systematic eval pipelines for measuring agent quality and safety.
-
outlinedriven-odin-claude-plugin Bundle HandoffUse when work reaches a session boundary or the user asks to hand off, delegate, or get a clipboard-ready prompt. Mode brief packages continuity; mode prompt builds the delegation prompt.
-
pramoddutta Skill Flask Testing PatternsFlask application testing with test client, fixture patterns, SQLAlchemy model testing, blueprint testing, and Flask-specific extension testing.
-
pramoddutta Skill Nunit TestingNUnit 3 constraint-based testing for C# covering Assert.That patterns, parameterized tests, setup/teardown, Moq mocking, test categories, and the fluent assertion model.
-
pramoddutta Skill Ruby On Rails TestingRails application testing with RSpec, FactoryBot, Capybara, system tests, request specs, model specs, and Rails-specific testing conventions.
-
nordeim-openclaw-curated-skills Bundle IbtIntention→Behavior Transformer (IBT) — deterministic execution discipline for reliable agent behavior without flattening personality.
-
nordeim-openclaw-curated-skills Bundle ClawpmMulti-project task and research management (JSON-first CLI)
-
nordeim-openclaw-curated-skills Bundle KalibrAutonomous execution path routing for OpenClaw agents. Reads real-time telemetry and routes to the optimal model + tool + parameter combination — so your agent navigates around failures, degradations, and cost spikes autonomously.
-
outlinedriven-odin-claude-plugin Bundle ResearchUse when researching a named library, framework, SDK, API, or service, or finding a migration guide. Not for codebase-internal research. Dispatch a scout agent.
-
outlinedriven-odin-claude-plugin Bundle Skill DoctorUse when a user wants agent setup graded from conversation history. Not for skill fixing: use agent-surface-forge. Not for security scanning: use skill-scanner.
-
pramoddutta Skill Django Testing PatternsDjango application testing with TestCase, fixtures, factory_boy, model testing, view testing, middleware testing, and Django REST framework testing.
-
pramoddutta Skill Nemo JS TestingComprehensive Nemo.js test automation skill for PayPal's Selenium-based Node.js testing framework featuring view-driven locators, flexible configuration, Mocha integration, and scalable browser automation patterns.
-
pramoddutta Skill Prompt TestingComprehensive prompt testing and LLM output evaluation skill covering hallucination detection, response quality scoring, regression testing for prompts, A/B testing, and building evaluation pipelines for AI-powered applications.
-
nordeim-openclaw-curated-skills Bundle KlawdinNetwork on behalf of your owner on KlawdIn. Register your agent, publish a profile, browse other agent profiles, start private conversations, post to the public feed, and record introductions — all via authenticated HTTP calls to klawdin.com.
-
nordeim-openclaw-curated-skills Bundle InterclawSecure, sequenced, PGP-signed email mesh for agent-to-agent coordination via plain email
-
nordeim-openclaw-curated-skills Bundle Moltbook CLIA CLI client for Moltbook, the social network for AI agents. Use this skill to post content, engage with communities (submolts), search information, and manage agent identity.
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 takaful-ifrs17, cyber-insurance, insurance-domain. 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.