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 70: 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
Cut tool-output noise (test logs, build logs, installs, huge searches) without hiding failures. Use when command output floods the context ("the test output is huge", "stop dumping logs", "why is my context full"), or when setting up quiet-output habits or a test-output filter hook for Claude Code or Codex.
1 skill от този източник на тази страница
Translate a stack trace, red terminal, test failure, build error, or failed CI job into what failed, where it failed, what it means in this project, and the smallest next check. Use before proposing a patch for an error.
1 skill от този източник на тази страница
Only use when the user explicitly invokes this skill by name (e.g. "/readme-shine", "run readme-shine"). Writes a compelling README.md for the current project from a template - a one-line pitch, a Summary and a copy-paste Quick Start first, then deeper material - with every command, path and requirement verified against the repo. "/readme-shine init" writes the built-in template and a starter config for the user to edit. "/readme-shine audit" tests whether a README stands on its own. "/readme-sh
1 skill от този източник на тази страница
Validates a tool against real-world third-party inputs instead of self-made fixtures: official servers, real repositories, real PRs, real version drift, and cross-platform CI. Use when unit tests are green but you need evidence the tool works outside the lab — before publishing, after a major refact
1 skill от този източник на тази страница
Reverse-engineer an existing system from code, configuration, tests, runtime evidence, and operations.
1 skill от този източник на тази страница
Turn a vague defect report into one deterministic failing test before any fix is attempted. Use for "it's broken", "can't reproduce", bug reports with no steps, flaky or intermittent failures, and anything that only fails in CI or in production.
1 skill от този източник на тази страница
Synthesize user research into themes, insights, and recommendations. Use when you have interview transcripts, survey results, usability test notes, support tickets, or NPS responses that need to be distilled into patterns, user segments, and prioritized next steps.
1 skill от този източник на тази страница
Review a pull request for correctness, scope, and tests, with severity-tagged findings. Use on every pull request before a human reviews.
1 skill от този източник на тази страница
Use when a developer needs to turn code-review comments, changed files, test evidence, and unresolved questions into a concise verification-ready handoff. Trigger for requests to audit whether review feedback was addressed, prepare a re-review brief, or separate resolved findings from evidence gaps.
2 skills от този източник на тази страница
Review Sui Move code that integrates OpenZeppelin Contracts for Sui against the library's own patterns and conventions. Use this when a developer wants their integration checked before shipping. Triggers: \"review my Sui Move code\", \"am I using OpenZeppelin correctly\", \"check this integration\", \"is this idiomatic\", \"review before audit\". Checks correct use of OZ primitives, deviations from examples/doc-comments, upheld invariants, test coverage, and code-quality/style. This is an AI cod
Set up a Sui Move smart contract project with OpenZeppelin Contracts for Sui. Use when users need to: (1) install the Sui CLI and Move toolchain, (2) create a new Sui Move package, (3) discover and add OpenZeppelin Sui dependencies to Move.toml via the Move Registry (MVR), (4) learn the integration pattern from the library's examples and API docs before implementing, or (5) understand Sui Move import conventions and build/test commands for OpenZeppelin.
1 skill от този източник на тази страница
Revisar, normalizar e reescrever issues do GitHub como especificacoes claras, testaveis e prontas para implementacao, inclusive revisao de issue especifica ou em lote, melhoria de criterios de aceite e reconciliacao com README/docs/arquitetura/ADR/API/runbooks quando houver conflito ou duplicidade de fonte canonica. Sob `entregar-issue`, executar somente quando o readiness gate falhar, corrigir apenas pontos bloqueantes, reutilizar fontes e registro documental, versionar mudancas materiais e ret
1 skill от този източник на тази страница
Build a structured, high-quality AI prompt using the RICE-POT framework (Role, Instructions, Context, Example, Parameters, Output, Tone). Use this whenever the user wants to create, write, fix, structure, or improve a prompt — especially for generating test cases, code, documents, or any repeatable AI task — or mentions "RICE-POT", "prompt template", "build me a prompt", "structure this prompt", "help me write a prompt", or hands over a rough/messy prompt to clean up. Trigger this even when the
1 skill от този източник на тази страница
Response formats and plain-language rules for the scpi-sim repository (SCPI instrument simulator plus Python driver). Use this skill whenever reviewing or critiquing code in this repo, flagging bugs, explaining an SCPI / IEEE 488.2 / driver / testing concept, proposing or discussing code structure, or helping when the user is stuck on why something does not work. Trigger it on phrases like "review this", "is this right", "what's wrong with", "explain X", "how should I structure Y", "I'm stuck on
1 skill от този източник на тази страница
Use when an idea or request must become one spec file before any code. Authors the next specs/NNNN-slug.md as Status: Draft with testable acceptance criteria and open questions.
4 skills от този източник на тази страница
Entry point for the project's AI-native SDLC (intent, spec, plan, test, code, review). Use when starting any non-trivial feature, bugfix or refactor, when resuming work after /clear or a harness switch, or when the user asks "where are we" or "what's next".
Stages 4 and 5 of the SDLC. For each approved plan.md item, write a test and prove it fails for the right reason (sdlc_check.py --red), make the smallest change that turns it green, run the gate, and tick the box. Use when a plan item is approved, or when the user says to implement or continue implementing.
Stages 1 to 3 of the SDLC. Check the change against intent.md, write the new behavior into spec.md, and add plan.md items that name their files and tests, then get the operator's approval before any code. Use when a feature, bugfix or refactor is requested and the spec or an approved plan item does not exist yet.
Stage 6 of the SDLC. Review the change against intent.md, spec.md, the plan item and REVIEW.md with fresh context (a separate subagent or session), then fix each finding test-first or ask the operator to defer it. Use when implementation is done and green, before opening a PR, or when asked to review the current diff.
1 skill от този източник на тази страница
Systematically critique and improve any output, document, or skill. Use when: reviewing your own work, improving a draft, stress-testing a framework, or iterating on anything that needs to be better. Triggers: 'critique this', 'what's wrong with this', 'how can I improve this', 'review my work', 'iterate on this'.
3 skills от този източник на тази страница
Improve a skill, instruction, or control after a repeated failure or an explicitly requested process change, using a small tested correction.
Execute an authorized change or implementation plan to a verified result, including resumption and an optional test-first mode.
Verify a named version through scenarios derived from acceptance criteria and risk, including UI, data persistence, and test-strategy planning.
1 skill от този източник на тази страница
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
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