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 150: 24 записа в 13 групи по репозиторий. Всички записи от страницата са показани. Номерът пази позицията от избраната подредба.
1 skill от този източник на тази страница
Select and reason about quantum error-correcting codes and logical operations in a hardware-agnostic way. Use for surface/color/LDPC/bosonic code tradeoffs, transversal gates, code switching, state preparation, and logical error budgets.
2 skills от този източник на тази страница
Audits the doctrine, agent instructions, skills and declared stack for drift against the real code. Use when the user asks for a quarterly or rules audit, roughly every 90 days, or before an end-of-quarter consolidation.
Audits the doctrine, agent instructions, skills and declared stack for drift against the real code. Use when the user asks for a quarterly or rules audit, roughly every 90 days, or before an end-of-quarter consolidation.
1 skill от този източник на тази страница
Staged recall background-check research on a product or food — a product/food name, a SKU/UPC/lot code, a description of a product, a description or URL of a product/food website, a TikTok/Facebook/Instagram post about a product, a news article, or a recall notice/text/email the user received. Use when the user asks whether something is recalled now or was recalled in the past, whether it is part of an outbreak investigation, whether a recall message/post/article/site is real or a scam, or wants
5 skills от този източник на тази страница
Use when building HTML email templates with React components, adding a visual email editor to an application using the React Email visual editor, rendering emails to HTML, or sending emails with Resend. Covers welcome emails, password resets, notifications, order confirmations, newsletters, transactional emails, and the embeddable email editor component.
Use when working with the Resend email API — sending transactional emails (single or batch), receiving inbound emails via webhooks, managing email templates, tracking delivery events, managing domains, contacts, broadcasts, webhooks, API keys, automations, events, viewing API request logs, or setting up the Resend SDK. Always use this skill when the user mentions Resend, even for simple tasks like "send an email with Resend" — the skill contains critical gotchas (idempotency keys, webhook verifi
Operate the Resend platform from the terminal — send emails (including React Email .tsx templates via --react-email), manage domains, contacts, broadcasts, templates, webhooks, API keys, logs, automations, and events via the `resend` CLI. Use when the user wants to run Resend commands in the shell,
Use when building or changing Cloudflare Sandbox apps on @cloudflare/sandbox@next (Sandbox SDK 1.0 preview)—code execution, AI runners, interpreters, CI-like jobs, terminals, files, mounts, tunnels, preview URLs, lifecycle, or errors. Not for the default stable package (use sandbox-stable) or for porting stable to @next (use sandbox-migrate-to-next).
Use when building or changing Cloudflare Sandbox apps on the current stable @cloudflare/sandbox package (default npm tag)—commands, sessions, files, ports, tunnels, terminals, bridge, production, or deprecated-API cleanup while staying on stable. Not for @cloudflare/sandbox@next (use sandbox-next) or for porting to 1.0 (use sandbox-migrate-to-next).
3 skills от този източник на тази страница
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
2 skills от този източник на тази страница
Cadre RenooLab spécialisé pour préparer, améliorer puis créer le profil RenooLab d'un artisan à partir de ses informations réelles : identité, métier, SIRET, zone, expérience, assurances, spécialités, bio et coordonnées. Toujours charger lorsque l'artisan lui-même demande explicitement à rejoindre RenooLab, créer ou améliorer son profil RenooLab. Récapituler toutes les données et obtenir sa confirmation juste avant creer_profil_artisan. Ne jamais utiliser pour un tiers, fournisseur ou négociant
Cadre RenooLab spécialisé pour diagnostiquer puis développer une entreprise artisanale, un négoce ou un fournisseur BTP : positionnement, prestations, planning vide, acquisition, prospects, visibilité, contenu, vente, devis non signé, fidélisation, services, KPI, CRM et demandes dispersées entre WhatsApp, papier et e-mail. Toujours charger pour croissance, clientèle, différenciation, communication ou outils. Un fournisseur voulant rejoindre RenooLab relève de ce workflow, jamais du profil artisa
3 skills от този източник на тази страница
Use when an agent has a Tianheng check violation or reported Tianheng warning/baselined finding in a Rust workspace and needs to repair product code toward the accepted boundary reason; reads the structured reaction, freezes the constitution, makes the smallest code repair, and reruns the reaction without weakening law. Do not use to create a new boundary, amend a Constitution, handle exit-class 2 configuration or scan failures as drift, or fix unrelated Rust diagnostics.
Use when a user asks to retire code comments in a Rust workspace already governed by Tianheng and the open question is which comments an accepted boundary already holds; inventories structural claims in `//` and `//!` comments, admits only a claim held by an enforced and unbaselined boundary, deletes exactly those with per-deletion coverage evidence, and routes every remaining claim onward. Do not use to delete comments as a style mandate, to rewrite or narrow a human-authored sentence, to touch
Use when a diff, branch, patch, or working tree adds or changes Tianheng Constitution boundaries, reasons, baselines, proof fixtures, or generated projections and needs adversarial review before human acceptance; verifies intent authority, observability, reaction evidence, minimality, amendment scope, compatibility, and projection freshness, then returns findings-first ACCEPT_CANDIDATE, REVISE, or REJECT without editing. Do not use to create or repair law, review product-code-only changes, accep
2 skills от този източник на тази страница
The shared vocabulary and reply shape for a code review thread — the two badges a finding carries, the provenance badges saying who flagged and who endorsed it, the verdict badge an answer carries, which answers a given ask accepts, the confidence ladder, the cite rules, and who resolves. Loaded by /review-pr (the reviewer's side) and /revise (the author's side) so one edit changes both. Load it before authoring a finding or answering one.
Work on your own code — review local changes with crit, or close out reviewers' threads on your open PRs. With no argument it finds the PRs across your repos where feedback is waiting on you and lets you pick. One selection runs the crit loop you drive in the browser; several fan out one agent per PR. Pass `--autonomous` to drop the human gate.
1 skill от този източник на тази страница
Use when the user explicitly requests structured code review, review-fix verification, or reconciliation of repeatedly changing review findings. Maintain an evidence-based finding ledger and distinguish defects from optional improvements. Not for unrelated coding or policy-source monitoring.
1 skill от този източник на тази страница
代码审核：双轴审查（Standards 轴+Spec 轴），阶段末必做。当需要对 diff（固定点…HEAD）做仓库规范+Fowler smell 与 Spec/DoD 双轴独立审查、并行子 agent 审查后汇总、输出分级问题清单（P0阻断/P1记录/P2可选）时触发。关键词：代码审核、code review、双轴审查、standards、spec、P0/P1/P2、smell、阶段末评审。
1 skill от този източник на тази страница
Use when code changes need review before merge. Read-only senior code reviewer with verdict blocks. Edit-locked — never modifies files.
1 skill от този източник на тази страница
RFX1427 (Personal) AI financial news scanner and analysis framework. Market Scan auto-runs on session start, fetching all 10 verified sources in tiered stages S0→F3 into one merged newest-first pool (stop-early at pool quota), output locked to Bahasa Melayu. Deep Analysis and SEC Verification are follow-up tools offered after the report. SEC Verification auto-chains after Deep Analysis (mandatory for Swing/Investor; shown for Scalper/Intraday with RELEVANT/NOT RELEVANT verdict). Python scraping
1 skill от този източник на тази страница
Decode QR codes from local PNG or JPEG attachments and return the exact embedded text or useful web destination without runtime downloads. Use when the user asks to scan, read, extract, or surface a QR destination; resolve public HTTP or HTTPS redirects without interacting with the destination.
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