Loading...
Loading...
Found 2,440 Skills
Extract structured PII spans from text using the OpenAI Privacy Filter 1.5B model reversed — returns what, where, and which type instead of masking.
Finds and inspects data assets within Google Cloud. Relevant when any of the following conditions are true: 1. The user request involves finding, exploring, or inspecting data assets in Google Cloud, such as: - BigQuery datasets, tables, or views - BigLake catalog or tables - Spanner instances, databases or tables - etc. 2. You need to retrieve the schema, metadata, or governance policies for a GCP data asset. 3. You have a keyword or topic (e.g., "sales data") but lack the specific table or resource ID. 4. You are attempting to find data using `bq ls`, as this skill offers a superior approach. Don't use when: - Assets are outside Google Cloud
Create, extract, refine, review, critique, or iterate on the brand identity at `stardust/brand-profile.json` and `stardust/brand-board.html` (and `.impeccable.md`) — philosophy, logo, colors, typography, componentStyle, motifs, photography direction, voice, tone, content pillars, personas, spacing. Ingests guidelines (PDF, URL, or conversation) or iterates on an existing profile. Use when the user provides brand guidelines, when the user asks to change, refine, refactor, review, improve, polish, critique, or iterate on any aspect of brand identity, or whenever the user asks to modify a file at `stardust/brand-profile.json`, `stardust/brand-board.html`, or `.impeccable.md`.
Monospace-driven, matrix-inspired design with high-contrast elements, compact density, and a hacker-chic aesthetic.
Tracks how competitors position themselves online — scrapes homepages, features, pricing, and blogs to extract messaging, value props, CTAs, and pricing models. Compares against previous snapshots to surface positioning shifts with before/after tracking. Produces messaging matrices, content gap analysis, white space maps, and battlecard inputs. Use when anyone asks about competitor messaging, positioning, website copy, content strategy, or how competitors present themselves. Triggers: "competitor positioning", "messaging comparison", "content gap", "what changed on their site", "competitor homepage", "landing page teardown", "marketing battlecard", "how do they describe their product", "share of voice", "counter-messaging". Do NOT use for business signals like funding/hiring (use competitor-intel), single-company deep dives (use company-deep-dive), or meeting prep (use meeting-prep).
Implements the Syncfusion Blazor DataGrid (SfGrid) for efficient tabular operations such as sorting, filtering, paging, grouping, editing, aggregates, virtualization, lazy‑load grouping, and row or column spanning. Use this skill when building data‑grid workflows in Blazor Server, WebAssembly, Web App, or MAUI applications. Supports Excel/PDF export, virtual or infinite scrolling, customizable templates, and grid state persistence for consistent and optimized data‑grid behavior.
Designing in-product tours, tooltips, and contextual help that teach product capabilities without becoming friction. Trigger logic, tour architecture, contextual placement, completion tracking. Honest about tooltip-spam (visual noise that users develop blindness to), one-and-done (help invisible at the moment of need), and contextual-when-needed (surfaces help at the moment friction occurs) patterns. Triggers on product tour, in-product tooltip, contextual help, walkthrough, feature tour, hint system, in-app guidance, tour platform. Also triggers when feature adoption is low, when users miss key product capabilities, or when an in-product help system is being scoped for the first time.
Write a blueprint (plan file) for a multi-step task (Step 3 of /task). Runs one brainstorming round then writes ai-workspace/plans/<name>.md from TEMPLATE.md. Skipped for one-sentence scope. Does NOT review — that is /review (Step 4).
Expo / React Native OpenTelemetry style: bootstrap guards, init ordering, inline endpoint + ingest key, mobile-compatible exporters, and product action spans.
Python OpenTelemetry style: module-scope tracers/meters, decorators for bounded work, error spans, logs, and no wrappers.
Enforce a configuration-driven design system when generating UI. Ensures consistent spacing, colors, typography, dark mode, interactions, and accessibility across all AI-generated components.
Linear operators for large-scale inverse problems with matrix-free representations. Use when Claude needs to: (1) Define linear operators for forward/adjoint operations, (2) Solve inverse problems (deconvolution, imaging, tomography), (3) Apply signal processing transforms (FFT, convolution, derivatives), (4) Compose operators for complex workflows, (5) Perform regularized inversion with smoothness or sparsity constraints, (6) Process seismic or image data at scale.