Навыки: Разработка

Correct code hygiene by detecting AI slop with a three-phase HIGH/MEDIUM/LOW certainty scan, safely auto-fixing only det...

Use when the user says deslop, debloat, tidy, simplify, clean a diff, cleanup codebase, or deslop branch diff, or remove...

Remove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up boiler...

Audit and harden existing codebases (especially AI-generated / vibe-coded ones) for production readiness. Use when the u...

Clean up AI-generated code changes by reviewing diffs against main and removing stylistic or structural artifacts (over-...

Destructible environment skill for fracturing and debris systems.

Use this skill when the user wants to detect individual trip or route anomalies, such as unusually long distance, unusua...

Scan a code artefact systematically against two complementary recognition catalogues — the

Identify code quality issues and anti-patterns. Use when reviewing code for maintainability problems.

Infer and verify install/test/lint/build commands for the repo.

Use when investigating implicit assumptions in code — ordering dependencies, unvalidated environment variables, assumed...

Detect which Language Server Protocol (LSP) servers are available for the current project and configure codemunch to use...

Determine if a string value should be translated or left as-is. Use when filtering localization keys, validating transla...

投前 AI 图真实性质检。待检图 → 风险等级 + 8 项逐条判定 + 可直接追加到 prompt 的修正句，可自动重跑直到达标。当用户说「投前检测」「图片质检」「检查有没有崩」「上架前把关」「这图能不能用」时使用。

Identify anomalies and outliers in datasets using machine learning algorithms.Use when analyzing data for unusual patter...

Detects fileless malware and in-memory attacks that execute entirely in RAM without writing persistent files to disk, ev...

This skill covers detecting sophisticated cyber-physical attacks that follow the Stuxnet attack pattern of modifying PLC...

Detects sophisticated cyber-physical attacks that follow the Stuxnet pattern of modifying PLC logic while spoofing senso...

Detect process injection techniques (T1055) including classic DLL injection, process hollowing, and APC injection by ana...

Use when building detections as versioned, tested code. Covers Sigma rule authoring, detection pipelines, unit testing d...

Beginner-friendly reverse-engineering workflow for Detection Engineering. Use it to collect evidence, choose static or d...

Runs attacker techniques and confirms whether detections actually fire, producing an honest ATT&CK coverage map that sep...

Engenharia reversa de specs para sistemas legados. Use quando precisar extrair specs executaveis, regras de negocio, con...

执行msProbe数据比对并分析比对结果，定位确定性计算问题首个输入一致输出不一致的API。

Run deterministic, scriptable pre-PR verification gates (build, full test suite, coverage threshold, branch naming, chan...

Gray-box end-to-end testing for React Native apps with Detox. Covers .detoxrc.js configuration, build and test commands,...

Start the Trigger.dev dev server Arguments: --profile <name>.

Drive a scoped feature through implementation, validation, and a reviewable handoff using the target repository’s conven...

Development workflows for WordPress ATmosphere plugin including wp-env setup, testing commands, linting, and build proce...

This skill should be used when the user asks to 'start a feature', 'build a feature', 'implement a feature', 'develop',...

Developer assistant (ATI successor). Provides a quick project overview via headless scan and routes to the available cod...

Full development environment - builds the project and runs 1 server plus 4 clients. Use when the user wants to test mult...

LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/h...

Boot and drive the tbh-meter app + reader locally to see a change working — what runs on macOS (UI only; the reader is w...

Start, stop or troubleshoot the local development stack. Use when the user wants to run the app, see it in the browser,...

Start, stop or troubleshoot the local development stack. Use when the user wants to run the app, see it in the browser,...

feature branch + worktree에서 작업 후 현재 브랜치로 merge까지 자동 수행

Orchestrate TDD-based development workflow – plan with test-first approach, save to Obsidian vault, split into trackable...

Writing and changing code: Ponytail simplicity, grounded style rules, local and feature-wide systematic debugging, compl...

Capture a screenshot or animated GIF for a forge-gpu lesson and update its README

Route full software-development architecture work from product intent through design, implementation, testing, release,...

Add an asset pipeline lesson — hybrid Python + C track for asset processing, procedural geometry, and web frontend

Add an audio lesson — sound playback, mixing, spatial audio, DSP effects, with SDL GPU scenes and forge UI

Drive the user's dedicated Chrome AI window with the dev-browser CLI to open sites, click, fill forms, read pages, take...

Bug fix pipeline — chains root cause analysis, requirements, planning, plan review, implementation, and code review. Use...

Full feature development pipeline — chains requirements, planning, plan review, implementation, and code review stage sk...

Implement a plan using TDD loop with TaskManagement progress tracking. Reads Implementation Steps from plan file, dispat...

构建或修改生产代码，同时保留既有架构、真实行为、复用路径和可验证交付证据。