Coding & Dev Tools
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
-
zad111ak-ai Skill Adaptive LoopsSelf-healing and self-learning loops for AI agents. Auto-recover from errors, remember what works.
- zad111ak-ai Bundle Memory Guardian
Automatic memory preservation hooks for Hermes sessions.
- zad111ak-ai Skill Memory Compactor
Автоматическое сжатие памяти при заполнении. Группировка, дедупликация, архивация в скиллы. Чтобы не упираться в лимит 2.2K и не терять важное.
- zad111ak-ai Skill Post Mortem Analyzer
Автоматический разбор провалов и дорогих операций. Замкнутый цикл обучения: ошибка → анализ → исправление → предотвращение.
- zad111ak-ai Skill Skill Trigger System
Проактивная система триггеров для скиллов. Контекстные/поведенческие/временные триггеры автоматически подгружают скилл → исполняют → выгружают. Как операционная система для навыков.
- zad111ak-ai Skill Auto QA Gates
Автоматические проверки качества перед ответом пользователю. 5 быстрых чеков, которые занимают 2 секунды в голове и предотвращают 90% ошибок.
- zad111ak-ai Skill Harvest Usage
Практическое использование Harvest для веб-скрейпинга: scrape, extract, crawl. Конкретные команды и примеры из жизни.
- zad111ak-ai Skill Self Hosted AI
Запуск AI локально: Ollama, Llama 3, подключение к Telegram-ботам, n8n. Полный гайд от установки до продакшна.
- zad111ak-ai Skill Reflexive Trigger Boost
Усилитель триггеров — активное сканирование контекста после каждого действия. Вместо 'если X, то Y' — 'после каждого шага проверь, а не пора ли?' Повышает частоту срабатывания скиллов.
- zad111ak-ai Skill Omniroute Mastery
Работа с OmniRoute: роутинг моделей,灰ые запросы, провайдеры, fallback, оптимизация расходов. Конкретные конфиги и команды.
- zad111ak-ai Skill Decision Framework
Быстрый фреймворк для принятия решений. Выбор инструмента, подхода, стратегии за <5 секунд. Минимизация analysis paralysis.
-
iberi22 Skill Xavier2 ContextXavier2 as the central context engine for SWAL - intelligent memory, decision-making, and context orchestration. Xavier2 is the CEO brain that stores memories, coordinates agents, and maintains project state.
- iberi22 Bundle Worldexams Curator
Curador de contenido para WorldExams. Se encarga del control de calidad, formato y alineación pedagógica de los bundles generados.
- iberi22 Bundle Worldexams Validator
Validador automático para WorldExams. Verifica integridad técnica y calidad pedagógica, activando regeneración automática si es necesario.
- iberi22 Skill Web Design Guidelines
Web Design Guidelines
-
spences10 Bundle Deslop 2Clean AI-generated code noise. Use when reviewing diffs, removing unnecessary comments, tightening verbose code, or desloping recent changes.
- spences10 Skill Asshole 2
Stop dismissing pre-existing test/build failures. Use when reporting test results, build output, or any command output containing errors or failures.
- spences10 Bundle Plugin Dev 2
Validate Claude Code plugin projects. Use only for .claude-plugin manifests, plugin marketplaces, or claude plugin validation.
- spences10 Bundle Structured Rpi 2
Plan risky or ambiguous work before implementing. Use when refactoring, designing unclear features, comparing approaches, or needing user checkpoints.
- spences10 Bundle Techdebt Finder 2
Find technical debt patterns in codebases. Use when asked to find duplicated code, inconsistent patterns, or refactoring opportunities.
- spences10 Bundle Sveltekit Data Flow 2
SvelteKit data flow guidance. Use when working with load functions, form actions, server/client boundaries, serialization, or invalidation.
- spences10 Bundle Sveltekit Remote Functions 2
Implement SvelteKit remote functions. Use for query(), query.live(), form(), command(), and prerender() patterns in .remote.ts files.
-
vostrikovva Skill NestjsNestJS modules, DI, pipes, and guards in TypeScript. Use when the backend is Nest, not a raw Express app.
- vostrikovva Skill Typescript
TypeScript strict typing for app and library code. Use when writing or reviewing TypeScript, fixing type errors, or when the project uses tsconfig strict. Prefer typed APIs over any.
- vostrikovva Bundle Implement
Implement a piece of work based on a spec or set of tickets.
- vostrikovva Bundle Grill Me
A relentless interview to sharpen a plan or design.
- vostrikovva Bundle Grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
- vostrikovva Bundle Teach Me
Teach a named technology in chat: brief motivation, then Q&A with beginner code hints. Use only when the user explicitly invokes this skill or asks to apply teach-me. Never edit project files.
- vostrikovva Bundle To Tickets
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).
- vostrikovva Bundle Code Review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
- vostrikovva Skill Which Skill
Recommend which Cursor skill to apply for a user request. Use only when the user explicitly invokes this skill or asks to apply which-skill. Covers Cursor built-in skills and skills from this catalog. Triggers include какой скилл нужен, which skill, what skill do I need.
- vostrikovva Bundle Grill With Docs
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
-
future3ooo Bundle DiagnoseDisciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
- future3ooo Skill Grill Me
Interview the user relentlessly about a plan or design until every branch of the decision tree is resolved.
- future3ooo Skill Grilling
Reusable one-question-at-a-time interview primitive for other skills. Use when another skill needs to stress-test a plan, walk a design tree, resolve decision dependencies, or grill user input into shared understanding.
- future3ooo Bundle Code Review
Review a diff since a fixed point along independent Standards and Spec axes. Use for PRs, branches, WIP changes, or governed completion review.
Frequently asked questions
What are Coding & Dev Tools agent skills?
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
Which Coding & Dev Tools skills are most installed?
Popular Coding & Dev Tools skills on SkillMD right now include adaptive-loops, memory-guardian, memory-compactor. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Coding & Dev Tools skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.