发现 Skills

Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods. Use when the user says help me brainstorm or help me ideate.

Proactively monitors conversation token usage and warns when approaching limits. Tracks usage patterns and predicts when limits will be reached based on current pace.

Remove isLoading and errorMessage fields from state classes and use context.isWaiting() and context.isFailed() instead

Analyze staged/unstaged Git changes, generate a Conventional Commits summary and description, execute the commit, push to the remote repository, and optionally create a GitHub Pull Request. Use when: committing code, generating commit messages, pushing to Git, creating conventional commit messages from diffs, saving changes, preparing a Git commit with summary and body, opening a pull request, creating a PR after push.

Inline text editing implementation within the file browser preview pane using a tmux PTY backend, coordinating cursor movement, text manipulation, and editor state management. Covers entry/exit lifecycle, dimension and viewport calculations for accurate rendering, confirmation dialogs for destructive edits, click-away detection to commit or cancel changes, mouse-event forwarding so terminal-aware interactions remain responsive, and app-level key routing to selectively capture or propagate shortcuts. Use when working on inline editing features, text input components, or debugging editor rendering/input issues in the file browser plugin.

Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.

Activate this skill when a student provides study material (PDF or pasted notes) and a syllabus, and wants to prepare for an exam. Extracts key definitions, points, keywords, diagrams, exam-ready sentences, and practice questions strictly from the provided material.

Python library for working with geospatial vector data including Shapefiles, GeoJSON, and GeoPackage files. Use it when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving reading, writing, or analyzing vector geographic data. Supports PostGIS databases, interactive maps, and integration with matplotlib, folium, and cartopy. Useful for tasks like buffer analysis, spatial joins between datasets, dissolving boundaries, clipping data, calculating areas and distances, reprojecting coordinate systems, creating maps, or converting between spatial file formats.

Advise on or generate git workflow artefacts: branch naming, commit messages following Conventional Commits, PR descriptions, and merge strategies. Use when a user needs git workflow guidance, wants a commit message written, or is setting up branching conventions for a project.

Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.

This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptor sets, pretrained models (ChemBERTa), convert SMILES to features for QSAR and molecular machine learning.

This skill should be used when converting academic papers into promotional and presentation formats including interactive websites (Paper2Web), presentation videos (Paper2Video), and conference posters (Paper2Poster). Use this skill for tasks involving paper dissemination, conference preparation, creating explorable academic homepages, generating video abstracts, or producing print-ready posters from LaTeX or PDF sources.

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria, methodology assessment, statistical validity, reporting-standards compliance (CONSORT/STROBE/PRISMA), and constructive feedback. Best for actual review writing and manuscript revision. For evaluating claim/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.

RNA velocity analysis with scVelo. Estimate cell-state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy/scVI-tools for trajectory inference.

Lease amendment drafting, standard lease template refresh, expansion/contraction option analysis, and build-to-suit proposal evaluation for Leasing and Asset Management.

Use this skill when users ask for Structurizr DSL, architecture diagrams, ADR integration, workspace or admin API automation, plugins, MCP server usage, static-site exports, or Java/DSL modeling workflows.

Edit existing PowerPoint files or templates with XML-safe workflows. Use for template-based deck updates: analyze layouts, map content to slides, duplicate/reorder/delete slides safely, edit slide XML in parallel, clean orphaned assets, and repack validated PPTX output.

Stage, commit, and push changes (no PR). Use when: "commit and push", "push my changes", "ship it"

Get best practices for C# async programming

name: seedance-ecommerce-ad description: Generate e-commerce product advertisement video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants product ads, e-commerce videos, product ...

This skill should be used EVERY TIME you're writing TypeScript with Effect, especially when the user asks about "Effect best practices", "Effect code style", "idiomatic Effect", "functional programming", "no loops", "no for loops", "avoid imperative", "Effect Array", "Effect Record", "Effect Struct", "Effect Tuple", "Effect Predicate", "Schema-first", "Match-first", "when to use Schema", "when to use Match", "branded types", "dual APIs", "Effect guidelines", "do notation", "Effect.gen", "pipe vs method chaining", "Effect naming conventions", "Effect project structure", "data modeling in Effect", or needs to understand idiomatic Effect-TS patterns and conventions.

This skill should be used when the user asks about "Effect concurrency", "fibers", "Fiber", "forking", "Effect.fork", "Effect.forkDaemon", "parallel execution", "Effect.all concurrency", "Deferred", "Queue", "PubSub", "Semaphore", "Latch", "fiber interruption", "Effect.race", "Effect.raceAll", "concurrent effects", or needs to understand how Effect handles parallel and concurrent execution.

Patterns for writing Playwright E2E tests — POM structure, selector hierarchy, flow specs, waits, role contexts, dialog handling. Use when authoring or reviewing anything under /e2e.