Agent Skills en tendance

Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax.

Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up.

Recommends or accepts user-specified experts based on the topic, simulates multi-role dialogue, and summarizes disagreements for targeted chatrooms, expert discussions, or continuing an active chatroom.

Deepline Monitors are provider event feeds (job posts, email replies, funding, intent) that stream into your warehouse and trigger plays.

Explains how an interface effect was built by reading the layers that produce it, or reconstructs from a screenshot.

Expo data fetching skill: covers fetch API, React Query, SWR, error handling, caching, offline support, and Expo Router data loaders.

Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review.

Generate videos with Pruna P-Video and WAN models via inference.sh CLI.

Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files.

Generate and edit images with OpenAI GPT-Image-2 via inference.sh CLI.

Architect game input — action mapping (abstracting keys into named actions), rebinding with conflict detection and persistence, multi-device support (keyboard, gamepad, touch), analog deadzones, and feel features like input buffering and coyote time, plus accessibility.

Helps users find the right Azure RBAC role for an identity with least privilege access, then generate CLI commands and Bicep code to assign it.

Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.

Run `dart analyze` to identify warnings and errors, and use `dart fix --apply` to automatically resolve mechanical lint issues, ensuring code quality during development and before committing.

为短视频、图文和文章生成或修改文字标题、封面文字和视频开头。先按稿件与拍摄状态把素材扩展成面向不同人群的选题供用户挑选，并询问能让观众相信作者的经历或数字，再一屏交付小红书、B 站、抖音、视频号的标题、封面与开头。用户要写标题、封面文字、开头、冷开场或多平台适配时使用；不生成封面图片、视频章节导航或发布风险声明。

Use the Deepline skill to build, enrich, audit, and upload B2B paid ads audiences to Google Customer Match, Meta/Facebook Custom Audiences, or LinkedIn Matched Audiences.

Navigation and routing for Expo Router, covering file-based routes, groups, dynamic routes, tabs, modals, sheets, headers, and search bars.

Optimize TextMeshPro font stacks, dynamic fallback atlases, padding and sampling ratios, SDF16, AutoSize discipline, worldspace vs UGUI, and Memory Profiler font-data capture.

Generate images with Pruna P-Image models via inference.sh CLI.

UX writing and interface copy skill for writing or reviewing any user-facing text.

dbs-decision is a local decision knowledge engineering tool that structures long-term tracking of business, relationships, health, career, learning, or investment issues, supporting decision filing, result backfill, status snapshots, and periodic reviews.

Use the `http` package in Flutter to execute GET, POST, PUT, or DELETE requests to fetch from or send data to a REST API.

Golang CLI command tree library using spf13/cobra — cobra.Command, RunE vs Run, PersistentPreRunE hook chain, Args validators (NoArgs, ExactArgs, MatchAll, custom), persistent vs local flags, command groups, ValidArgsFunction, RegisterFlagCompletionFunc, ShellCompDirective, usage/help template customization, man-page and markdown doc generation, and testing with SetArgs/SetOut/SetErr.

Apply when sequencing an addition, refactor, or rewrite.

Generate videos with ByteDance Seedance 2.0 via inference.sh CLI.

The Stripe Apps skill guides developers in building, modifying, or reviewing Stripe Apps, covering the full development workflow from scaffolding to marketplace publishing.

Scans text for AI writing characteristics and outputs a detection report, diagnosing only by default without rewriting.

Use for CRM audits, duplicate detection, missing or stale fields, job changes, domain checks, acquisitions, parent-child relationships, repair plans, prevention, monitoring, and evaluation.

Generate and edit videos with Alibaba HappyHorse 1.0 models via inference.sh CLI.

Apply when reviewing or shaping code that's hard to trace.

Use when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state and `@Observable` data flow, view composition, resizable layouts, safe areas, display scale, performance, lists, environment, localization, animation, Liquid Glass, and API migration.

Sets up, configures, and debugs URP post-processing effects using the Volume framework.

Use when writing or refactoring unit tests, emphasizing behavior-first, contract testing, determinism, and mocking only at boundaries you do not own.

Use Dart switch expressions and pattern matching to simplify code and ensure exhaustiveness.

Rewrites vague questions into problem specifications that agents can reason about, critique, and verify, while assessing the degree of automation feasibility.

Use this skill to review a Deepline Play result and hand feedback, labels, or approval back to the agent for revision, evaluation, comparison, or bounded iteration.

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax.

Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction.

Generates custom Shader Graph nodes from HLSL code, for creating new nodes or making existing HLSL code work as a reflected function node.

Deepline pre-research skill: discover critical data sources, compare provider coverage, estimate credit cost, and recommend a source plan before building or running a workflow.

Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading.

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

Svelte 5 best practices: runes, snippets, SvelteKit patterns, and TypeScript component development guide.

Technical writing skill for composing, restructuring, or revising any technical document, encoding house style, truth and sourcing rules, and banned constructions.

Write and organize unit tests for Dart and Flutter applications using package:test to ensure correctness and prevent regressions.

Automatically identifies whether the user is solving a specific business problem or seeking a comprehensive business model check, and enters the corresponding diagnostic process.

Before writing any non-trivial change, investigating a bug, or working in unfamiliar code, map the real code and data, quote evidence, and never guess conventions.

Review a finished epic folder in the ticket tree against the evidence it left behind — the epic file, each ticket plan, diffs, commits — and produce a retrospective with sourced findings, action items, and an acceptance decision.