Software Development AI Skills

Author and maintain versioned Selenium WebDriver tests with Java and JUnit 5. Use for creating, debugging, or running Selenium specs, implementing Page Objects, handling explicit waits, capturing…

Detects .NET intent for any C#, ASP.NET Core, EF Core, Blazor, MAUI, Uno Platform, WPF, WinUI, SignalR, gRPC, xUnit, NuGet, or MSBuild request from prompt keywords and repository signals (.sln,…

Verify and close - cross-check coverage, run the VERIFY table, deliver the verdict, harvest durable lessons into decisions, close the bundle, and never claim remote state from local evidence.

Detect quality drops in AI output and prompt re-anchoring. Auto-triggers after repeated corrections, context confusion, or when user says "something seems off", "you're not getting this".

Read and verify legacy Remotion Integrator records for a pre-v0.9 task. Never dispatch this stage in a new v1 production; the Parent assembles verified Builder media directly.

为新项目或尚未建立文档管理体系的已有项目，规划并建立文档入口、资料分工和维护方式。 用户要求“建立文档管理体系”“首次配置文档治理”时使用；暂保留只读文档审计、日志统计与归档。 单独优化 Agent 入口、日常同步或执行复盘，交给对应 Skill。

Use as the FIRST action on any research, investigation, or codebase-understanding request — "research X", "investigate X", "look into X", "dig into X", "search X", "explore X", "understand X", "why is…

Dependency upgrades: outdated/vulnerable deps planned into semver waves (patch/minor batched, majors gated and changelog-read), applied incrementally with lockfiles regenerated and tests green after…

Dependency upgrades: outdated/vulnerable deps planned into semver waves (patch/minor batched, majors gated and changelog-read), applied incrementally with lockfiles regenerated and tests green after…

Upgrade Stellar/Soroban smart contracts using OpenZeppelin's upgradeable module. Use when users need to: (1) make Soroban contracts upgradeable via native WASM replacement, (2) use Upgradeable or…

Access Telnyx LLM inference APIs, embeddings, and AI analytics for call insights and summaries. This skill provides JavaScript SDK examples.

Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with…

The transparency content type — turn what's actually happening inside the business into founder/personal-brand content that builds trust: build-in-public updates, founder story, how-it's-made content,…

一键发布 Markdown 到微信公众号草稿箱。基于 wenyan-cli，支持多主题、代码高亮、图片自动上传。

Manage Git worktrees for parallel Claude Code development. Use this skill when engineers ask to "create a worktree", "run parallel Claude sessions", "work on multiple features simultaneously", or need…

Investigate, reproduce, and safely fix a bug with regression protection. Composes context, diagnosis, architecture, code quality, and testing guardrails into a reproduce-first repair workflow. Use…

Drive CI green on a pushed, review-clean feature PR — On-Call diagnoses failures and hands fix tasks to the SWE. Output: a CI-validated feature PR. Trigger after /squid-review passes.

Launcher for the Ralph-style queue drain script — emits the right `node ralph-loop.mjs` invocation based on the user's filter and bounds. The actual loop runs as a Node script that spawns one `claude…

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create…

完成已实现功能的验证、Git 提交/推送、PR 或部署交付。按用户在会话中已授权的动作执行，核对仓库、提交与真实部署结果；单纯本地收尾不自动公开发布。

Fetch and analyze protein structures from RCSB PDB. Use this skill when: (1) Need to download a structure by PDB ID, (2) Search for similar structures, (3) Prepare target for binder design, (4)…

Use when writing, fixing, editing, or refactoring TypeScript functions. Enforces Clean Code principles—maximum 3 arguments, single responsibility, no flag parameters.

Create patent-style technical diagrams including flowcharts, block diagrams, and system architectures using Graphviz with reference numbering

Add runtime configuration to specx Python services with `pydantic-settings`. Use when creating settings classes, environment variables, `.env.example`, injecting settings at delivery, infrastructure,…

Remote Wiki knowledge-base Q&A (Knowledge Base Bridge). Platform skill, mounted on demand by tester/frontend/backend/architect; invoked by name from content skills.

Profiles Meta Quest and Horizon OS application CPU performance using simpleperf — workload classification, CPU hotspot recording, kernel overhead measurement. Use when diagnosing whether an app is…

Audit and port an iOS app to iPhone Duo, Apple's first foldable iPhone. Use when asked to support, adapt, prepare, test, or review an app for iPhone Duo, foldable iPhone, the inner/outer display,…

Produces a tailored Sanity Studio upgrade plan by inspecting the repository's installed versions, config, and source, then reporting only the breaking changes that actually apply. Covers Studio v3 and…

The smart data fetching layer for Vue.js. ALWAYS use when writing code importing "@pinia/colada". Consult for debugging, best practices, or modifying @pinia/colada, pinia/colada, pinia colada,…

Use when implementing logging, error tracking, or monitoring in Frappe v14-v16. Covers frappe.logger() for file-based logging, frappe.log_error() for Error Log DocType entries, request logging, Sentry…

Implement HTTP data fetching in Angular v20+ using resource(), httpResource(), and HttpClient. Use for API calls, data loading with signals, request/response handling, and interceptors. Triggers on…

Protocol for tracking files immediately after agent creation

Fullstack development toolkit with project scaffolding for Next.js/FastAPI/MERN/Django stacks and code quality analysis. Use when scaffolding new projects, analyzing codebase quality, or implementing…

Skill inspect web/mobile applications bằng browser tools, phân tích DOM elements, xác định locators ổn định, debug UI automation failures, và hỗ trợ sinh Page Object classes.

Use when the user wants a next-action recommendation based on current state — reads handoff/git/lessons/STATE and proposes top-3 by impact. Trigger: '/next', 'what should I do next', 'next action'.…

Core concepts and best practices for `package:test`. Covers `test`, `group`, lifecycle methods (`setUp`, `tearDown`), and configuration (`dart_test.yaml`).

This skill should be used when the user invokes "/matplotlib" to plot data from the current context using matplotlib (via uv) and output the resulting image path.

Migrate Python LangChain, LangGraph, or Deep Agents applications to Pydantic AI and, when the source uses harness features, Pydantic AI Harness. Use for LangChain agents, chains, LCEL, direct…

当 spec-start 需要为新 Spec 创建 GitHub Flow 工作分支，spec-update 需要复用/校验当前 Spec 分支，或 spec-end/spec-update 需要提交、推送、创建 PR、合并后清理分支时使用。也用于发版管理：建立或维护 release 分支、打版本 tag、发补丁版本、把修复 cherry-pick 到多条发布线、核对 tag…

3D Game Development workflow skill. Use this skill when the user needs 3D game development principles. Rendering, shaders, physics, cameras and the operator should preserve the upstream workflow,…

Read a Hyperliquid account from the desk computer - positions and margin, spot balances, open orders including trigger details, fills, funding paid, ledger updates, order status by oid or cloid,…

Audit PHP web application source for critical vulnerabilities using PHP's specific sink and footgun catalog — object injection via unserialize and phar:// POP chains, type-juggling and magic-hash auth…

每兩週交易檢討：歸因每筆成交是「系統決策」還是「你自己決策」、算基準校正 α、驗影子訊號、更新規則命中率帳本，輸出「本期該改哪一條規則」。Usage - /trade-review [2w|4w|since YYYY-MM-DD]

Use when you want guided mining of git history, structured change-story clustering, or comprehensive rationale recovery before documenting. Class boots only suggest capture — for in-session change…

Record the problem, deployment setting, metric, baseline, and fold count before any model code. Ask every missing decision in one turn, from `frame show`. Does not write Python, estimator…

Find duplicate ownership, hidden second sources of truth, and contract drift in layered codebases. Use when reviewing normalization, validation, defaulting, canonicalization, persistence mapping,…

初始化、升级、诊断、校验和迁移 Lzheng 本地训练系统，并把增肌、减脂、力量与综合健身计划、训练复盘和健身工作台串成单一主源闭环。用于用户刚下载/刚安装、说开始建立健身系统、想增肌/减脂/提升力量、新电脑搭建、系统升级或工作台异常排查；首次使用时由 AI 自然语言接管引导，不要求用户先找 README、命令或 Skill 名称。

Apply strategic approaches to code commenting including when to comment, optimal comment density, performance considerations, and integration with development workflow. Use when establishing…

Review GitHub pull requests with a findings-first engineering mindset. Use when auditing diffs for bugs, regressions, security issues, missing tests, or risky design choices, and when producing…

Adds schema tests and data quality validation to dbt models. Use when working with dbt tests for: (1) Adding or modifying tests in schema.yml files (2) Task mentions "test", "validate", "data…

从已完成写作的微信公众号文章中提取观点、对比、流程或已核实数据，并交给固定渲染器一次生成当前主题的公众号正文与原生 HTML 信息模块。用于已选定排版主题后增强手机端扫读体验，同时不生成正文图片、不调用图片模型、不让 Agent 临时编码排版的场景。