Намерете инструкция, прочетете оригиналния файл и подгответе команда за своя инструмент.
31 301 skills в каталога
Как подбирам и измервамДанните имат нужда от нова проверка.Последна успешна проверка: 23.09.2026 г.
Проверката на източника не означава, че всяка инструкция е изпробвана от Level8. Каталогът не обхваща непременно всички публични хранилища.
Търсене в целия индекс. Метаданните показват посоченото от източника; липсващите стойности остават означени.
Датата в GitHub е отделна от първата поява в моя индекс. Филтърът по дата изключва записите без посочено обновяване.
Страница 63: 24 записа в 18 групи по репозиторий. Всички записи от страницата са показани. Номерът пази позицията от избраната подредба.
1 skill от този източник на тази страница
Fixture skill with channel and version mismatch. Use when testing release channel rules.
4 skills от този източник на тази страница
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or eslint-disable suppressions, skipped or deleted tests, assertions stripped out, unimplemented stubs, thresholds edited down. Use when no quality bar is written down, when the user says "set u
Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why — a systematic approach to finding and fixing the root cause rather than guessing.
1 skill от този източник на тази страница
A beginner-safe, model-agnostic software-building workflow. Use when a non-coder or early learner is planning, changing, testing, deploying, or reviewing software with Cursor, Claude Code, Codex, or another AI coding tool; when an AI asks for approval; or when the user wants plain-language explanations, small reversible steps, proof that a change works, and a trustworthy record of decisions.
1 skill от този източник на тази страница
Use when implementing features or fixes from a spec via OpenCode with TDD. Writes production code only after failing tests. Write permission.
1 skill от този източник на тази страница
Organises and retrieves Markdown memory on the hosted CentricMem librarian (search, notes, decisions, transcripts). Use when starting a session, resuming after context compress / checkpoint / new chat, filing Non-Micro work, searching project memory, connecting an agent key, or refreshing this Skill. On session start, compare the loaded copy (see REFERENCE Skill refresh) against cm_health / ambient skill_latest and refresh if stale.
1 skill от този източник на тази страница
Author and verify one Maestro flow for a checklist ref, then register it in docs/checklist-map.yaml. Invoked by the checklist API's authoring path, or by hand when a checklist item has no coverage yet.
1 skill от този източник на тази страница
Build, debug, test, review and govern Claude Mods - Claude Code plugins that keep their logic in a TypeScript hooks module of function hooks (register(on, options); hooks ($, e, next) composed like Koa middleware over the engine interface $). Use it whenever the user mentions Claude Mods, mods, function hooks, a hooks module, "modules" in hooks.json, on("tool.call"), $.ui / $.tool / $.fs, next(e), next.to, .catch, /plugin-types, claude plugin test, CLAUDE_CODE_ENABLE_FUNCTION_HOOKS, ui.render, p
1 skill от този източник на тази страница
Build, debug, test, review and govern Claude Mods - Claude Code plugins that keep their logic in a TypeScript hooks module of function hooks (register(on, options); hooks ($, e, next) composed like Koa middleware over the engine interface $). Use it whenever the user mentions Claude Mods, mods, function hooks, a hooks module, "modules" in hooks.json, on("tool.call"), $.ui / $.tool / $.fs, next(e), next.to, .catch, /plugin-types, claude plugin test, CLAUDE_CODE_ENABLE_FUNCTION_HOOKS, ui.render, p
2 skills от този източник на тази страница
Use when writing, fixing, editing, or refactoring Go tests. Enforces Clean Code principles—fast tests, boundary coverage, one concept per test.
Use when writing, fixing, editing, or refactoring TypeScript tests. Enforces Clean Code principles—fast tests, boundary coverage, one assert per test.
1 skill от този източник на тази страница
Use para revisar código em busca de falhas, riscos e testes ausentes.
1 skill от този източник на тази страница
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
1 skill от този източник на тази страница
以现有 PDF 工程为底板复制出新 PDF 项目：业务与广告逻辑照搬，UI 按 Figma 换肤， 广告改走 adSdk。路径必须打散；类名/方法名轻度改、保持可读。applicationId 固定 com.test.app，签名 / google-services / 测试广告 ID 一并复制。Use for 新 PDF 项目、 完成 PDF 项目、从 Figma 做 PDF、复制 PDF16、换皮 PDF、打散类名路径。
1 skill от този източник на тази страница
Build a complete, tested, documented GoHighLevel (GHL) snapshot for any business vertical, in six user-gated phases — research the business from the web, plan every sub-account object (custom values/fields, tags, pipelines, calendars, forms/surveys, funnels/sites, templates, workflows, dashboard), build it via Chrome browser automation, test it against customer personas, write a click-by-click onboarding guide, and clean up. Use when the user says /create-ghl-snapshot, asks to create/build/desig
2 skills от този източник на тази страница
Commission DALI/DALI-2 lighting buses with an agent: short-address assignment (0-63), clash resolution, 16 groups, 16 scenes, DT8 devices, and emergency ballast tests per IEC 62386. Use when bringing up or extending a DALI installation (KNX/DALI gateways, Tridonic/Philips/Osram gear). Never energize unverified wiring.
Commission DALI/DALI-2 lighting buses with an agent: short-address assignment (0-63), clash resolution, 16 groups, 16 scenes, DT8 devices, and emergency ballast tests per IEC 62386. Use when bringing up or extending a DALI installation (KNX/DALI gateways, Tridonic/Philips/Osram gear). Never energize unverified wiring.
1 skill от този източник на тази страница
Finds sensitive data exposure risks — PII/secrets written to logs, over-returning API responses, data at rest without encryption, sensitive data in URLs, test fixtures with real data, secrets in git history, and temporary/backup file leaks. Use when auditing how a project handles, stores, logs, or transmits sensitive data.
1 skill от този източник на тази страница
Find the root cause of a bug, test failure or production incident by forming and killing hypotheses rather than changing code until symptoms stop. Use when something is broken, intermittent, or when a first fix did not hold.
2 skills от този източник на тази страница
This skill should be used when a user wants to debug, stress-test, compare, audit, review, or post-mortem a consequential decision. It audits objectives, constraints, options, evidence, assumptions, reasoning, dependencies, causal claims, failure modes, alternatives, feasibility, stakeholders, agency, reversibility, decision boundaries, and reassessment triggers. It does not take ownership of the user's decision.
This skill should be used when a user wants to debug, stress-test, compare, audit, review, or post-mortem a consequential decision. It audits objectives, constraints, options, evidence, assumptions, reasoning, dependencies, causal claims, failure modes, alternatives, feasibility, stakeholders, agency, reversibility, decision boundaries, and reassessment triggers. It does not take ownership of the user's decision.
1 skill от този източник на тази страница
Document a design decision between 2 options with explicit criteria, scenario testing, and a confidence-rated recommendation. Use when torn between two directions and need a defensible, written rationale - not just a gut call.
Пазя съществуващия каталог и добавям намерени SKILL.md файлове след прочит на метаданните. Наличният индекс остава използваем, когато проверката е частична.
Платформата и нивото описват записаното в източника. Те не са гаранция за съвместимост. Български текст се показва само когато в каталога има отделен превод; иначе виждате оригинала с означен език.
Общите звезди показват натрупана популярност. За „Набират интерес“ се сравнява измереният темп при достатъчен интервал. ≥ означава непълна извадка. Под един час не изчислявам дневен темп; методът и изминалият период се показват до записа.
Проверете файла, лиценза и нужния достъп преди употреба. Нито каталогът, нито четенето на SKILL.md изпълняват външни инструкции.
Темата Agent Skills в GitHub