Total 57,837 skills
Showing 12 of 57837 skills
Use when you need to write or improve integration tests — including Testcontainers with @ServiceConnection, @DataJdbcTest persistence slices, TestRestTemplate or MockMvcTester for HTTP, data isolation, and container lifecycle management for Spring Boot 4.0.x. This should trigger for requests such as Review Java code for Spring Boot integration tests; Apply best practices for Spring Boot integration tests in Java code; Write @SpringBootTest integration tests with Testcontainers; Configure dynamic properties for Spring integration tests; Review Spring Boot integration test profiles. Part of Plinth Toolkit
Use when you need to review, improve, or troubleshoot a Maven pom.xml file — including dependency management with BOMs, plugin configuration, version centralization, multi-module project structure, build profiles, or any situation where you want to align your Maven setup with industry best practices. This should trigger for requests such as Review pom.xml to improve it; Apply Maven best practices to pom.xml; Improve Maven POM configuration; Review Maven dependency management and plugin configuration; Modernize Maven build conventions for a Java project. Part of Plinth Toolkit
Turn an analytic geometry problem into a self-contained interactive teaching webpage: left column with problem statement + dynamic console (a variable parameter slider driving real-time recalculation of geometric quantities + theoretical range/fixed value indication), middle column with step-by-step explanations using KaTeX, right column with 2D Canvas dynamic geometry drawing board (ellipse/hyperbola/parabola/circle + moving lines/moving points + vectors + annotations + brush doodling). Supports three entry points—given text problems, random problem generation, and solving problems after uploading and recognizing problem images. Covers problem types such as finding standard equations, chord lengths, vector dot product ranges/fixed values, triangle area maxima/minima, fixed points, fixed values (product of slopes), loci, and eccentricities. Uses a unified method of "setting parametric line x=my+c + simultaneous equations + Vieta's formulas + substitution/constant separation", driven by sympy for precise calculations (answers, coordinates, step values, and theoretical ranges of the interactive engine are consistent from the same source). Other agents can also call this skill to generate such webpages. It parallels edu-solid-geometry in form but uses Canvas-2D + KaTeX (instead of Three.js). Trigger words: 解析几何, 圆锥曲线, 椭圆, 双曲线, 抛物线, 直线与圆锥曲线, 焦点弦, 弦长, 数量积取值范围, 向量数量积, 定点问题, 定值问题, 斜率之积, 三角形面积最值, 轨迹方程, 离心率, 解这道解析几何题, 随机出一道圆锥曲线题, 这张图里的解析几何题; analytic geometry, conic sections, ellipse, hyperbola, parabola, chord length, dot product range, fixed point, fixed value, locus, eccentricity, interactive analytic geometry solution page.
Build with the Terra API Planned Workouts product (pre-release) – define a structured workout once and Terra API pushes it to users' devices. Use when pushing planned or structured workouts to Garmin, COROS, Wahoo, Suunto, TrainingPeaks, Huawei, Zepp, Hevy, or Apple watches, building training plans or workout templates, working with intervals, warmups, targets (HR, power, pace, cadence, RPE, zones), FTP or threshold-based personalization, athlete parameters, swimming or strength templates, or handling provider coercion warnings when a device cannot represent a feature.
Rewrite text that sounds AI-generated while keeping the writer's facts, meaning, and voice. Use when editing or reviewing prose for inflated claims, sales language, vague sources, repetitive structure, stock AI words, passive voice, filler, or chatbot artifacts. Based on Wikipedia's "Signs of AI writing."
Write tests from a feature spec, treating the spec and its flow contract as the source of truth, stubbing pending tests where implementation is missing and halting when code and spec disagree. Use when the user says "write tests from this spec", "fill the coverage gaps", "prove this wizard works", or after spec-assess-coverage identifies what is untested.
Sweep every spec in the estate for maintenance debt — partial behaviours with no ticket, ageing future behaviours, roll-up statuses that disagree with their behaviours, long-standing open questions, and modules with no specs at all. Use when the user asks "what state are our specs in", "review the spec estate", "which open questions are blocking work", or on a periodic cadence. Reports only.
Complete the incomplete behaviours in current scope — read the scoped specs, build a queue, and keep working across turns until the definition of done is satisfied. Use when the user says "run the implementation plan", "continue the plan", "finish the scoped work", "complete the incomplete behaviours", "ship B4", or names a chunk ID.
Use when a user is installing DaVinci Resolve for the first time, switching machines, configuring a media drive for video editing, or asking about backup/proxy settings. Triggering symptoms include phrases like "just installed Resolve", "set up DaVinci Resolve", "drop frames during playback", "where should my media live", "how do I configure backups", or any DaVinci Resolve installation/preferences question.
Use when a user needs branded titles, animated lower-thirds, or a logo intro for their video — uses Resolve's Text+ node and Fusion's animation modifiers to create reusable title templates. Triggering symptoms include phrases like "add a name lower third", "animated logo intro", "title card with gradient", "save title as a template", "introduce a guest", or any DaVinci Resolve title/text question.
Use this whenever a user shares a Figma design link or mentions Figma and wants to build UI from a design, turn a frame into code, extract design tokens or a theme, export icons or images, inspect a node for measurements, sync a component and token library to code, generate documentation specs or usage guidelines for a component or pattern, or review a design and leave feedback as Figma comments. Trigger it even when the user does not say the word Figma, as long as they paste a figma.com link or refer to a design frame, component, variables, or design tokens.
Use when a user has podcast, interview, or talking-head audio that needs cleanup — denoise, de-hum, level dialogue, and duck music under voice. Triggering symptoms include phrases like "podcast audio is noisy", "background hum in interview", "music too loud under voice", "level out my voiceover", "fix my podcast", or any DaVinci Resolve Fairlight audio cleanup question.