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 49: 24 записа в 10 групи по репозиторий. Всички записи от страницата са показани. Номерът пази позицията от избраната подредба.
5 skills от този източник на тази страница
Generate an architecture overview document from a pull request or local git diff. Detects the forge type (GitHub, Forgejo, GitLab) from the current repo and uses the appropriate CLI. Supports PR mode (pr brief #N, architecture-brief PR #N) and local diff mode (git brief, architecture-brief, architec
Create or update a README.md file for a project. Review the full project structure and generate a comprehensive, well-structured README that covers installation, usage, and key features.
Use when writing or editing Markdown documentation (*.md files). Covers GFM formatting, content structure, headings, lists, code blocks, links, images, tables, and front matter.
Correct Mermaid diagram syntax reference covering all types (flowchart, sequence, class, ERD, state, C4, git, gantt, pie). Emphasizes parser-compatible patterns to avoid rendering errors in GitHub, Obsidian, VS Code, and other tools. Use when creating, visualizing, or documenting software architectu
Use when writing or editing technical documentation (manuals, procedures, work instructions, warnings, cautions, notes, maintenance guides, user guides). Applies ASD-STE100 Simplified Technical English Issue 9 rules.
4 skills от този източник на тази страница
Reproducible token/cost benchmark — runs a fixed task corpus through the real auto-router decision logic and compares it against a 'no routing, everything to cloud STANDARD' baseline. Turns the README's savings claim into a checkable number instead of an assertion. Use when the user wants proof of token savings, a benchmark for a PR/README, or numbers to back an integration pitch (e.g. Hermes).
Live ANSI dashboard of the belt's decisions — routing, token savings, micro-NN outputs, escalations, cache hits — either a built-in scripted scenario (no LLM, no network, works on a bare machine) or tailing a real project's event log. Use when the user wants to see/demo what the routing belt is doing, record a README GIF, or watch live decisions while an agent works.
Generate documentation with a local model drafting and the cloud only refining (0 cloud tokens for the draft), plus a local session review that summarises what a work session did. Use to write README/module docs/CHANGELOG/guides/ADRs cheaply, or to produce end-of-session notes/learnings from a transcript.
Scoped documentation map for multi-component projects (server + client + tools + …). Detects components, classifies every doc as global vs component-scoped, and produces a per-component index (DOCS.md) listing local docs + links to the relevant global docs — so an LLM coder bounded to one component loads only its scope, not every other component's documentation. Frames token cost (full project docs vs scoped load) and treats .md as LLM-facing, .html as human reference. Use when a project has sev
1 skill от този източник на тази страница
Use when writing, editing, refactoring or fixing code in any project — creating or changing functions, modules, services, routes, jobs, the data layer, components and hooks. Applies to small tweaks and bug fixes too, and even when the user says nothing about style. Also use before committing or opening a PR with code changes, or when asked to review naming, magic numbers, function size, line spacing and scoping, error handling or the lint gate.
7 skills от този източник на тази страница
Use when writing a cover letter for a job application. Say the thing the resume cannot, or send nothing.
Use when writing prompts for an LLM. Produce specific, delimited, example-driven prompts and parse model output defensively with a fallback path.
Use when a repo has no README or needs a refresh. Scans code and generates accurate docs.
Use when writing or editing an agent skill file. Enforces trigger-first descriptions, lessons over logs, and progressive disclosure.
Use when writing docs, a README, or a changelog. Write task-first, failure-aware docs that a stranger can act on in five minutes.
Use when making factual claims, writing docs, or citing sources. Ground in verifiable evidence.
Use when optimising a .docx resume for ATS parsers. Build linear Word documents whose text survives machine extraction and still reads well to a human.
1 skill от този източник на тази страница
Write clear technical README documentation with installation, examples, verification and limitations. 문서 리드미 작성 설치 안내.
1 skill от този източник на тази страница
Rewrite or create clear, accurate technical writing, documentation, explanations, and notes. Use for structured product documentation, including cloud and developer guides, when source material must be preserved and the output should be natural, accessible, and easy to scan.
1 skill от този източник на тази страница
Classify and organize a folder of company files (documents, spreadsheets, PDFs, emails, exports) by department, document type, sensitivity, date, counterparty and personal data, using the jev-organize CLI and TypeSafe's Jev model on OpenRouter. Use when the user wants to sort, clean up, index, audit or map a pile of company data; find which files hold personal data, passwords or payment details; build an AI-readable index of a shared drive; or answer questions like "which contracts do we have wi
1 skill от този източник на тази страница
Store, evaluate, and compare text or Markdown revisions against context and reusable criteria with Jev through OpenRouter. Use for iterative work on resumes, essays, specifications, cover letters, webpages, and similar documents. The coding agent owns editing and iteration; Jev Score is the system of record and evaluator.
1 skill от този източник на тази страница
Chinese AI/tech writing de-AI editor for posts, X/Twitter threads, technical essays, product notes, model reviews, and public-writing drafts. 默认用作者本人口吻，可点名切换到专业商务风、技术科普风、亲和对话风、学术研究风。 Use when the user asks to 去AI味, 改得像本人, 写推特post, 精修中文AI技术文章, or complains about AI-flavored shells such as 不是A而是B, 真正/其实/本质上, 更重要的是, 冒号讲义腔, 句子缺主语, 动词缩成一个字, 被动语态与幽灵主语, 模糊归因, 同一个对象换着叫, 空泛总结, 顺滑但没作者判断的稿子.
2 skills от този източник на тази страница
The whole company works on one goal given by the human (for example "launch in Belgium" or "prepare the pitch for bakeries"). The Director plans, each needed role delivers one document, the auditor reviews, and the Director reports. Use when the human types sprint "<goal>".
The whole company works on one goal given by the human (for example "launch in Belgium" or "prepare the pitch for bakeries"). The Director plans, each needed role delivers one document, the auditor reviews, and the Director reports. Use when the human types sprint "<goal>".
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