Навыки: Тестирование

Deep reference for caching — what to cache, cache-aside vs read/write-through/write-behind, TTLs with jitter, eviction (...

Implement effective caching at every layer: in-memory, Redis, CDN, and browser. Activate whenever the user asks about ca...

Backend caching patterns with Redis including write-through, write-behind, cache-aside, and invalidation strategies. Use...

Understand the caching architecture, Cache Components (PPR), and revalidation mechanisms. Use when debugging stale conte...

Maintain and diagnose CachyOS-specific optimized repositories, kernels, chwd hardware profiles, sched-ext scheduling, an...

Rebuild and validate 2D CAD drawings on Linux — exact redraw from a source DXF/DWG, PDF-to-DXF conversion, or image-to-C...

创建、修改和核对CAD乔木树组的名称数量、完整成员串线和自由引出，处理图例中心拾取、头尾连接、分组与邻注避让。用于乔木组标注，不用于灌草面积引出或一般尺寸。

Use when the user asks to create a design doc, design document, specification, or technical spec (create workflow → Dire...

Measure test coverage and identify untested code. Use when assessing test completeness.

Calculate inventory accuracy from system balances, counted quantities, variance tolerances, and count scope.

Use when estimating total daily energy expenditure to set caloric targets for weight management or performance

Calibration testing for agents and skills. Generates synthetic problems with known outcomes (quasi-ground-truth), runs t...

Adapt large reasoning models for optimization tasks using expert-guided hint correction. Generate high-quality training...

Standardized camera movement vocabulary for Veo 3 video generation. Use when creating video prompts that require specifi...

Use when implementing cameras — smooth follow, screen shake, camera zones, and transitions for 2D and 3D

Use when integrating, porting, configuring, or debugging CAN bus libraries, CANBus-Triple, MCP2515, CAN frames, bit timi...

审查新提交或修改的 CANNBot Skill 是否符合入库质量要求。当用户需要评审 SKILL.md、检查新增 cannbot skill、审查 GitCode PR 中的技能变更、验证测试/开发/NPU/Ascend 相关 skill...

Review new narrative or lore content against established canon for chronology, geography, terminology, world rules, char...

Reference catalog of canon enforcement principles, epistemological operating rules, metascience diagnostic filters, adve...

Screen US stocks using William O'Neil's CANSLIM growth stock methodology. Use when user requests CANSLIM stock screening...

Use when making browser games or visualisations with the HTML Canvas 2D API and no engine — fixed logical resolution wit...

Visual regression for canvas-rendered matrix progressions. Tests filmstrip strips that show how 2D data evolves visually...

Lint canvas files for staleness, missing fields, inconsistent evidence types, and orphaned references. Run periodically...

HTML5 Canvas 2D and WebGL rendering, animation frames, buffer memory lifecycle, and offscreen workers.

Senior CAPA Officer specialist for managing Corrective and Preventive Actions within Quality Management Systems. Provide...

CAPA system management for medical device QMS. Covers root cause analysis, corrective action planning, effectiveness ver...

Discover available agents, skills, quality commands (lint, test, typecheck), tech stack, verification capabilities, and...

This skill should be used when the user asks to "C API test failures", "C API unit test issues", "modifier tests failing...

This skill should be used when the user asks to "verify C API test naming", "check test naming convention", "validate te...

Ranks competing uses of capital (reinvest in the core, M&A, debt paydown, buyback, dividend, cash buffer) by value creat...

Plan, generate, revise, assemble, and quality-check local AI short videos with reusable Capsule Cinema recipes. Use when...

Check SRT or WebVTT captions and subtitles against published standards (Netflix English, BBC subtitle guidelines, DCMP C...

Capture API response test fixture.

Auto-capture screenshots and GIFs of the running app for PR documentation using Playwright and project context from chal...

The capture state machine, hotkeys and audio pipeline in Struq Voice. Use whenever a task involves capture state, the se...

Systematic retrospective to capture decisions, lessons, and insights from completed work

Sanity-check a greenhouse gas inventory before it goes into a report or gets audited. Use when asked to review a carbon...

Embody Carl Jung - AI persona expert with integrated methodology skills

共享 page 下用例离开起点后必须 UI 返回并断言。触发：往返闭合、case round trip、复位超时、scope 共享 page。

Intelligent QA assistant that automates writing test cases from project documentation. Use when the user wants to genera...

Tune CATLASS kernel performance by adjusting TileShape, DispatchPolicy, Swizzle, and Kernel type parameters. Change one...

Persistent terse-output overlay with safety and verification escape hatches. Use when the user explicitly says caveman o...

Manual one-shot reference card for Caveman levels and companion skills. Use only when explicitly invoked as $caveman-hel...

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment...

Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR",...

Comprehensive toolkit for detecting and eliminating "AI slop" - generic, low-quality AI-generated patterns in natural la...

Use when implementing new observable behavior or fixing a behavioral defect through tests, or when deciding whether a ch...

Injects mistake-derived test requirements into the TDD pipeline