Loading...
Loading...
Found 1,441 Skills
Multi-perspective dialectical reasoning with cross-evaluative synthesis. Spawns parallel evaluative lenses (STRUCTURAL, EVIDENTIAL, SCOPE, ADVERSARIAL, PRAGMATIC) that critique thesis AND critique each other's critiques, producing N-squared evaluation matrix before recursive aggregation. Triggers on /critique, /dialectic, /crosseval, requests for thorough analysis, stress-testing arguments, or finding weaknesses. Implements Hegelian refinement enhanced with interleaved multi-domain evaluation and convergent synthesis.
Use when writing type annotations on variables. Use when TypeScript can infer the type. Use when code feels cluttered with types.
Apply Hyva UI template-based components to a Hyvä theme. This skill should be used when the user wants to add, install, or apply a Hyva UI component (such as header, footer, gallery, menu, minicart, etc.) to their Hyvä theme. It lists available non-CMS components and their variants, displays component README instructions, and copies component files to the theme directory.
Load PROACTIVELY when task involves deploying, hosting, or CI/CD pipelines. Use when user says "deploy this", "set up CI/CD", "add Docker", "configure Vercel", or "set up monitoring". Covers platform-specific deployment (Vercel, Railway, Fly.io, AWS), Dockerfile creation, environment variable management, CI/CD pipeline configuration (GitHub Actions), preview deployments, health checks, rollback strategies, and production monitoring setup.
This skill should be used when you need to create, open, or edit a pull request (PR), or the user asks to "create a PR", "open a PR", "submit a PR", "raise a PR", "file a PR", "make a PR", "create a pull request", "open a pull request", "new PR", or any variation requesting GitHub pull request creation.
Safe, phase-gated refactoring: CHARACTERIZE with tests, PLAN incremental steps, EXECUTE one change at a time, VALIDATE no regressions. Use when renaming functions/variables, extracting modules, changing signatures, restructuring directories, or consolidating duplicate code. Use for "refactor", "rename", "extract", "restructure", or "migrate pattern". Do NOT use for bug fixes or new feature implementation.
Build identity-preserving character generation workflows and pipelines in ComfyUI. Selects the optimal identity method (InfiniteYou, FLUX Kontext, PuLID, InstantID, IP-Adapter) based on use case requirements. Handles face preservation, likeness transfer, cross-domain conversion (3D to photo), multi-reference consistency, iterative character editing, and character variation generation. Triggers on requests to generate consistent characters, preserve identity across images, create face-swapping workflows, or convert 3D renders to photorealistic portraits. Does NOT cover general image generation without identity preservation, model training/LoRA fine-tuning, animation, technical explanations, or workflow debugging.
Grafana OSS core features — dashboards, panels, visualization types, data sources, template variables, alerting, annotations, provisioning, RBAC, service accounts, and configuration. Use when building dashboards, configuring data sources, setting up provisioning YAML, managing users and permissions, writing PromQL/LogQL/TraceQL in panels, or configuring Grafana server settings.
Generate on-brand marketing images via Codex's built-in image_generation tool. Trigger when user asks to: (a) create marketing assets (ad / logo / slide / product-mockup / scene / lighting-transform / LinkedIn-or-social carousel) for a specific brand, (b) extract or build a brand profile (DESIGN.md) from URL / Tailwind config / tokens.json / Figma Variables / CSS custom props / description / existing brand asset, (c) maintain on-brand consistency across multiple image jobs for the same brand. Do NOT trigger for: UI code generation, frontend reference imagery (use imagegen-frontend-web instead), video generation, or general image editing without brand context.
Run a Bayesian A/B test on conversion data using PyMC. Use when the user wants to compare two variants (landing pages, emails, pricing, UI changes) and decide which to ship using posterior probabilities and expected loss instead of p-values. Covers Beta-Binomial model, ROPE, expected loss, sample-size guidance, and ArviZ diagnostics.
Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.
Solve LP, MILP, QP (beta) with cuOpt Python API — linear/quadratic objectives, integer variables, scheduling, portfolio, least squares.