В каталоге 183 730 навыков в 14 категориях.
Change or extend software or a device the user owns but whose source they don't control (a desktop app, a website, a gam...
Für Mod Erklärung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Execute código Python na nuvem com contêineres serverless, GPUs e autoscaling. Use ao fazer deploy de modelos de ML, exe...
Serverless GPU cloud for Python with per-second billing on A100/H100/L40S. Use for burst ML training (>13B parameter mod...
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running ba...
Use when running Python or GPU workloads serverlessly on Modal — modal.App, inline container Images, gpu= on @app.functi...
Cloud computing platform for running Python on GPUs and serverless infrastructure. Use when deploying AI/ML models, runn...
Serverless GPU cloud for ML jobs and model APIs.
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or servi...
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure ma...
Use Modal for GPU/CPU remote compute beyond what the modal_run tool covers — Volumes, Secrets, Queues, deployed apps/end...
研究 codex 使用 skill 生成 survey 這件事
Serverless cloud compute for running scientific workloads at scale
Guides modAL-python active-learning workflows, query strategies, committees, Bayesian optimization, and optional deep in...
Use when you must run a modal analysis of a two degree of freedom mass-spring structural model: compute the natural freq...
Overlays — modals, drawers, bottom sheets, popovers — interrupt or augment the main flow. Each type has a different scop...
CRITICAL: All modals MUST use the global Modal component with the correct API
Deploy a Modal function from a local Python file
Implements accessible modals and drawers with focus trap, ESC to close, scroll lock, portal rendering, and ARIA attribut...
Använd när du bygger en modal (E-Com Modal) som kräver bekräftelse eller ett aktivt val innan användaren kan fortsätta —...
List deployed Modal functions in the current workspace
Run Python code on cloud GPUs using Modal serverless platform. Use when you need A100/T4/A10G GPU access for training ML...
Invoke a deployed Modal function with JSON arguments
Comprehensive Modal.com platform knowledge covering all features, pricing, and best practices
Modal Labs (modal.com) — run Python on serverless containers with GPUs, batch jobs, and autoscaling. Precision wrapper t...
Extending propositional and predicate logic with modal operators -- necessity and possibility, and their relatives (obli...
React Portal modal implementation patterns for Dr. Sophia AI. Covers createPortal usage, AnimatePresence integration, z-...
Fix SwiftUI sheet presentation issues in Leavn - competing sheets, dismissal patterns, binding synchronization, enum-bas...
Use when animating modals, dialogs, popovers, or overlay content to create smooth entrances and exits
Provides comprehensive guidance for Modao prototyping tool including rapid prototyping, component libraries, and collabo...
Program industrial Modbus RTU/TCP protocols, reading discrete inputs, holding registers, and coils on PLCs.
Show or switch the project's conformance mode between Enforced and À la carte, within the set the organization allows.
Use when the user wants to change optimization aggressiveness, switch between aggressive/balanced/thorough modes, or adj...
Switch this project's pi dispatch mode (off / soft / strict)
Show or set NeatContext routing to auto, ask, or manual for Codex, with an optional default shared with every other Neat...
Babble mode: stream of consciousness, no structure, half-thoughts and dead ends, thinking out loud. Load when switching...
Methodological skill for Test-Driven Development in NestJS backend. This skill should be used when strict quality requir...
Use before routing a /meta-agent request to choose single-agent-creator, team-builder, or agentlas-packager from the use...
Code mode: rules for writing and refactoring code. Style (DRY, SYNC markers, naming), no fallbacks fail loudly, tooling,...
Collaborative mode, the default cognitive pattern: build on ideas, riff, propose, keep forward momentum. Load when switc...
Convergence mode: synthesize scattered thoughts into coherent structure, extract core insights, output actionable next s...
Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types...
Debug mode: observe, hypothesize, test, evaluate, fix-and-stop; no certainty without evidence, no symptom patches. Load...
Central decision table for how a stop-and-wait gate behaves per Claude Code session mode (normal, autonomous/no-pause, p...
Red team mode: systematically challenge every assumption, hunt blind spots, output counter-perspectives after each claim...
Research mode: search before implementing, search for concepts not libraries, overdo it, never trust stale knowledge. Lo...
Selects the active profile from triggering context. Evaluates a rule set against inputs (current time, calendar state, g...
For understanding what each mode does, which mode is best (most appropriate mode) for a given situation, and establishin...
Use this skill when performing deterministic mode selection for session-start. Reads Phase A STATE.md recommendations +...
Writing mode: distill prose, fight length and jargon, loop drafts through the AI-tell catalog until a full pass finds no...
Inspect or change Babysitter model-routing policy by phase.
Build valuation and scenario models to stress-test financial assumptions
This skill should be used when the user asks about business models, unit economics, lean canvas, pricing math, CAC/LTV,...
Create or maintain a source-grounded kpopper knowledge model as a versioned plugin. Use when a reusable domain model sho...
Algorithm/model development and fine-tuning skill. Use for tasks like dataset design/cleaning, supervised fine-tuning (S...
Produce or update a domain-reference kit — the durable glossary + divergences/traps pages for a bounded context. Use for...
Model selection strategy and routing. Use when choosing between models for different task types, subagent configurations...
Use when validating model downgrades for skills or agents. Runs A/B comparison between current and proposed model, score...
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning...
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer...
Audits how model artifacts are accepted, validated, stored, selected, loaded, executed, monitored, and retired. Use when...
Use when validating or evaluating a trained medical-imaging model. Audits split leakage and validation design, computes...
Audit the ceh-* plugins against Claude's per-model prompting guides and open the results as a draft PR. Trigger on "/mod...
Use this skill to audit valuation model suitability, assumptions, formulas, sensitivity, data lineage, and blocked/low-c...
Use when the user wants to pick the cheapest model that still works for a custom subagent, asks whether Haiku or Sonnet...
Choose a model with evidence by running the few prompts that actually matter across candidate models inside a free tier'...
Master Dyna-Q, MBPO, Dreamer - model-based RL with world models and planning
Use this skill when you need to derive test-path candidates from sourced behavior, state, or process models; triggers in...
Use when: benchmark model latency, throughput, or quality.
Model Bias occurs when an AI system produces results that are systematically prejudiced against certain individuals or g...
Identifying, measuring, and mitigating algorithmic bias to ensure equitable outcomes in AI systems.
Model, sculpt, retopologize, and clean production Blender 4.5 assets. Use for hard-surface assemblies, organic or vehicl...
Creates the model brief: purpose, model class, mechanisms, data, validation level, team, timeline and risks.
Building MobX models with proper architecture, BaseModel patterns, Store usage, and validation
Trains and validates prediction models for sports game outcomes. Use when user asks about building a prediction model, t...
Review KV cache, prompt cache, and semantic cache implementations for cross-request context leakage, cache poisoning, si...
Use when the operator explicitly asks for native Codex model or reasoning-effort routing, including an active standing r...
Use when a trained medical-imaging model needs its documentation. Fills a Model Card and a Datasheet for its dataset fro...
Generate the documentation an engineer-built medical-imaging model must carry — a Model Card (Mitchell et al. 2019), a D...
Document a deployed ML/AI model so others can use it responsibly. Use when asked to write a model card, document a model...
Document a machine learning model in a structured, transparent format for stakeholders, reviewers, and future maintainer...
Writes the model card: purpose, limits, data, performance, validation status, risks and appropriate use.
Model documentation skill for generating model cards following Google's model card framework.
Find the model that is currently best for a capability by reading the provider live catalogue, and record it with its so...
When the user needs to evaluate multiple model checkpoints across various benchmarks to identify the best performing mod...
Manage model checkpoint manager operations. Auto-activating skill for ML Training. Triggers on: model checkpoint manager...
Model Checkpoint Manager - Auto-activating skill for ML Training. Triggers on: model checkpoint manager, model checkpoin...
Run a deliberative two-model committee between GPT-5.5 and Claude Opus 4.8. Use when the user needs one consequential de...
Run a deliberative two-model committee between GPT-5.5 and Claude Opus 4.8, chaired by Fable 5. Same two deliberating me...
Run a deliberative two-model committee between GPT-5.5 and Claude Opus 4.8, chaired by GPT-5.6 "Sol." Same two deliberat...
Use this skill when comparing AI or LLM models on benchmarks, capability, cost, latency, context window, or task-specifi...
Blind side-by-side multi-model comparison. Send one prompt to 2-4 models simultaneously, present responses anonymously (...
Compare 3D CAD models using boolean operations (IoU, Dice, precision/recall). Use when evaluating generated models again...
Compare AI models across benchmarks, pricing, and capabilities. Use when the user asks to compare models, evaluate trade...
Use when asked to compare multiple ML models, perform cross-validation, evaluate metrics, or select the best model for a...
Model family compatibility matrix — loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD...