Development skills

Get productive with agentic coding assistants — task framing, iterative prompting, file-scoped workflows, review loops, and multi-file refactors. Use when pairing with an AI coding agent on real codebases.

The English summary is being prepared. Showing the original description.

Write readable, maintainable code: naming, small functions, clear control flow, and honest abstractions. Use when writing new code, refactoring, or reviewing for readability.

The English summary is being prepared. Showing the original description.

Build with Meta's Code Llama — open code models for generation, infilling, and long-context code tasks.

The English summary is being prepared. Showing the original description.

Build with Mistral's Codestral code models — efficient open code generation with fill-in-the-middle.

The English summary is being prepared. Showing the original description.

Professional C: memory ownership, defensive programming, build hygiene, and systems-level correctness. Use when writing, reviewing, or maintaining C code.

The English summary is being prepared. Showing the original description.

Encode and decode Base64 correctly with URL-safe variants, padding rules, and binary handling.

The English summary is being prepared. Showing the original description.

Bash scripting guidance — safe scripting patterns, quoting, error handling, pipes, and maintainable shell code.

The English summary is being prepared. Showing the original description.

Master Bitwarden: vaults, collections, self-hosting options, CLI, and organization administration. Use when using Bitwarden personally or running it for a team, including self-hosted setups.

The English summary is being prepared. Showing the original description.

Ship iOS/Android apps with Capacitor: web codebase, native plugins, live updates, and store builds. Use when wrapping a web app as native mobile apps.

The English summary is being prepared. Showing the original description.

Anthropic Claude API guidance — messages API, tool use, prompt caching, extended thinking, and production patterns.

The English summary is being prepared. Showing the original description.

Integrate third-party APIs reliably: auth, pagination, retries, webhooks, rate limits, and contract testing. Use when connecting to external REST/GraphQL APIs or building resilient API clients.

The English summary is being prepared. Showing the original description.

Create polished, code-driven Remotion motion explainers from scripts, narration, subtitles, product specifications, reference videos, UI recordings, diagrams, or abstract concepts. Use for product launches, AI demonstrations, UI interactions, algorithms, scientific principles, electrical systems, data flows, architecture, charts, equations, and concepts best expressed with React, SVG, Canvas, WebGL, or Three.js. Prioritize continuous spatial logic, visible cause and effect, precise interaction states, editable parameters, deterministic rendering, and evidence-backed visual QA.

The English summary is being prepared. Showing the original description.

Review code for quality, bugs, and improvements. Use when user wants code review or quality assessment.

The English summary is being prepared. Showing the original description.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

The English summary is being prepared. Showing the original description.

Set up a new git worktree for parallel development. Creates the worktree, copies .env files, installs dependencies, and generates Prisma client. TRIGGER when user asks to set up a worktree, work on a branch in isolation, or needs a separate environment for a branch or PR.

The English summary is being prepared. Showing the original description.

Automate GitHub Copilot CLI in GitHub Actions workflows. USE FOR: installing/running `copilot -p` in workflow steps, choosing GITHUB_TOKEN vs a personal access token (COPILOT_GITHUB_TOKEN) for authentication, setting the copilot-requests write permission, minimal-permission tool allowlisting (--allow-tool, --deny-tool, --no-ask-user, -s/--silent, --output-format=json), triggers (schedule, workflow_dispatch, push), the recommended GitHub Agentic Workflows (gh-aw) alternative to direct CLI invocation, and security/cost considerations (fork PR prompt-injection risk, billing attribution, cost centers). DO NOT USE FOR: embedding the Copilot agent runtime into your own application (use copilot-sdk instead); general GitHub Actions authoring unrelated to Copilot; the Copilot code review or PR features outside of CLI automation.

The English summary is being prepared. Showing the original description.

Create polished Python terminal user interfaces and skill scripts with Textual and Rich. Use when: building TUI apps; adding interactive terminal workflows; designing tabs, progress bars, checkboxes, radio buttons, tables, charts, forms, status views, keyboard navigation, color, or responsive terminal layouts; making Python scripts visually appealing and informative. Every skill script defaults to a TUI on an interactive terminal and provides --no-tui for deterministic stream output. DO NOT USE FOR: browser GUIs; desktop-native GUIs; plain shell commands with no interactive workflow; non-Python applications.

The English summary is being prepared. Showing the original description.

Repository and solution-level scaffolding best practices for .NET: .slnx solution format, Directory.Build.props shared MSBuild properties, Directory.Packages.props central package management (CPM), .editorconfig, SourceLink, deterministic/reproducible builds, global.json SDK pinning. USE FOR: scaffolding a new .NET repo or solution; choosing .sln vs .slnx; sharing MSBuild properties (TargetFramework, LangVersion, Nullable, ImplicitUsings, TreatWarningsAsErrors, EnforceCodeStyleInBuild, EnableNETAnalyzers, Deterministic) across every project; configuring SourceLink for debuggable NuGet packages; central package version management and GlobalPackageReference; pinning the SDK with global.json; .editorconfig code-style rules; CI-only ContinuousIntegrationBuild flag; reproducible/deterministic builds and packages; repo root file checklist. DO NOT USE FOR: C# language feature choices (use csharp-best-practices); benchmarking (use dotnet-benchmarking); generic math (use dotnet-generic-math).

The English summary is being prepared. Showing the original description.

C# 11+ generic math with static abstract interface members in System.Numerics. USE FOR: writing generic numeric algorithms; constraining type parameters to INumber<T>/IFloatingPoint<T>/ITrigonometricFunctions<T>; implementing custom numeric types with operator overloads; defining static abstract interfaces (IAngleUnits pattern); CreateChecked/Saturating/Truncating cross-type conversions; AdditiveIdentity/MultiplicativeIdentity; singleton bridge pattern for static abstract at runtime; ISpanFormattable/ISpanParsable; generic Sum/Average/Lerp methods; Half/float/double/decimal compatibility. DO NOT USE FOR: Unity math; pre-.NET 7 System.Math/MathF workarounds; Python/JavaScript numerics.

The English summary is being prepared. Showing the original description.

Write and optimize C#/.NET enumerables, iterators, and LINQ usage. USE FOR: choosing IEnumerable<T>/IReadOnlyCollection<T>/IReadOnlyList<T>/ICollection<T>/IList<T>/IAsyncEnumerable<T> for params/returns; foreach codegen and value-type vs reference-type enumerator performance (List<T>, arrays, Span<T>, ImmutableArray<T>, ArraySegment<T>); avoiding boxed enumerator allocations; Count() vs Any() vs Count property complexity traps; First()/Single()(OrDefault) cost and predicate-overload collapsing; ToList()/ToArray() allocation cost vs lazy evaluation; returning Enumerable.Empty<T>()/yield break instead of null; writing yield-based iterators, lazy validation, coroutines, behavior trees; writing async iterators with await foreach/yield return, EnumeratorCancellation/WithCancellation token propagation, ConfigureAwait; handling enumerables via reflection/Roslyn (NetFabric.Reflection/CodeAnalysis). DO NOT USE FOR: SIMD/vectorized span math (dotnet-simd); generic math over numeric types (dotnet-generic-math).

The English summary is being prepared. Showing the original description.

Build, run, and publish .NET applications from a single C# file without a .csproj, using .NET 10 SDK file-based apps. USE FOR: dotnet run file.cs; dotnet run --file; shebang/shell-executable C# scripts; colon-prefixed directives (sdk, package, project, property, include); converting a file-based app to a project with dotnet project convert; publishing file-based apps with native AOT; packaging a file-based app as a .NET tool (PackAsTool); user secrets for file-based apps; flat *.run.json launch profiles; dotnet build/clean/publish/pack/restore on a .cs file; build caching behavior and dotnet clean file-based-apps; folder layout to avoid project-file cone conflicts. DO NOT USE FOR: traditional .csproj solution scaffolding (use dotnet-solution-setup); C# language idioms unrelated to the SDK/CLI (use csharp-best-practices); benchmarking (use dotnet-benchmarking).

The English summary is being prepared. Showing the original description.

Embed the GitHub Copilot agent runtime into your own application using the Copilot SDK. USE FOR: CopilotClient/createSession setup, streaming responses, custom tools, permission handlers, hooks (pre/post-tool-use, session-start), custom agents and sub-agent delegation, MCP servers, skill and plugin directories, session persistence, fleet mode, steering/queueing, calling the SDK from skill scripts/ to run one bounded non-deterministic AI step inside an otherwise deterministic script, and choosing an auth/deployment path (CLI setup, backend services, multi-tenancy, GitHub OAuth, BYOK). Covers Node.js/TypeScript (@github/copilot-sdk), Python (github-copilot-sdk), Go (github.com/github/copilot-sdk/go), Rust (github-copilot-sdk crate), .NET (GitHub.Copilot.SDK), and Java (copilot-sdk-java). DO NOT USE FOR: authoring SKILL.md files consumed by VS Code Copilot (use create-skill instead); using the Copilot IDE extension or chat UI directly; general LLM/chat API integration unrelated to the Copilot SDK.

The English summary is being prepared. Showing the original description.

Create and maintain GitHub Copilot CLI custom agents (.agent.md files). USE FOR: authoring .github/agents or ~/.copilot/agents profiles; frontmatter fields (description, target, name, model, tools, mcp-servers, disable-model-invocation, user-invocable, deferred-tool-loading, skills, reasoning-effort, sidekick); writing descriptions that drive auto-delegation (the CLI routes on description quality, like skills); building orchestrator + specialist squads with the task tool; /fleet parallel subagents; built-in agents (explore, task, research, code-review, rubber-duck, security-review, general-purpose); subagent depth/concurrency limits; list_agents and write_agent coordination. DO NOT USE FOR: VS Code-only fields beyond target (agents: allowlist, handoffs) or GitHub.com cloud agent configuration; MCP server authoring; SKILL.md authoring (use create-skill).

The English summary is being prepared. Showing the original description.

Install, verify, and integrate codebase-memory-mcp (CBM) — a local C binary indexing a codebase into a persistent knowledge graph (functions, classes, call chains, routes) queryable via 15 tools. USE FOR: creating or editing any agent/skill/prompt/subagent that reads, searches, or reasons about a codebase — CBM's CLI must replace grep/ripgrep/glob-and-read exploration for structural questions (who calls X, dead code, architecture overview, diff impact, Cypher queries); checking whether `codebase-memory-mcp` is installed; installing/updating it; checking whether a project's index is fresh/in sync (`index_status`); choosing CLI vs MCP (always prefer the CLI, far fewer tokens per call than MCP); picking the right CBM tool per workflow stage (discovery, verification, implementation, review). DO NOT USE FOR: semantic/business-logic code review; non-code repos with nothing to index.

The English summary is being prepared. Showing the original description.