AGENT SKILLS · ミッション装備 / ssheleg

ssheleg · Agent Skills

20 skills with substantive source documentation and an official publisher or observed installation demand. Read each skill’s original documentation through its card.

ssheleg

コミュニティ

skill-search

Use when starting any task, as its first step, to decide whether an installed skill should drive it. Searches the whole installed catalogue, including skills the host hides from its listing, by concepts in English and Russian, then opens the matching SKILL.md. Triggers - "which skill", "find a skill", «какой скилл», «найди скилл», «первый шаг». NOT for building or auditing a skill (make-skill).

導入数: 3
GitHub Stars: 4
更新日: 10月24日

telegram-bots

Use when building, adding or auditing a Telegram bot on the HTTP Bot API: polling or webhooks, update dedup, keyboards, Telegram Stars payments, files and rate limits. Not for user accounts (telegram-userbots) or the web layer (telegram-miniapps). Opt out: no telegram, без телеграма. Triggers - "telegram bot", "bot api", "aiogram", "setWebhook", "telegram stars", "телеграм бот", "вебхук телеграм", "звёзды телеграм".

導入数: 3
GitHub Stars: 4
更新日: 10月24日

quest-native

Use when building or reviewing a native Meta Quest app in C or C++ against OpenXR: manifest and Gradle, loader, frame loop, swapchains, Vulkan, passthrough, required SDK levels. NOT for Unity, Unreal, Spatial SDK (quest-spatial), WebXR (quest-webxr), profiling (quest-perf) or Store submission (quest-store). Opt out: no xr, без xr. Triggers - "OpenXR app" / "приложение на OpenXR", "native Quest app" / "нативное приложение для Quest", "xrCreateInstance".

導入数: 3
GitHub Stars: 1
更新日: 10月24日

agent-interop

Use when an agent talks to anything outside its process: an MCP server or client, A2A and agent cards, the MCP Registry, an agent gateway, calls on behalf of a person. Triggers: "MCP server" / "MCP-сервер", "A2A", "agent card" / "карточка агента", "MCP registry", "шлюз для агентов". Not for one server's tool design (agent-harness) or skill construction (make-skill).

導入数: 2
GitHub Stars: 4
更新日: 10月24日

make-skill

Use when creating, auditing, packaging or publishing an agent skill or Claude Code plugin to the Agent Skills standard and Anthropic's platform rules. Triggers - "make a skill" / "сделай скилл", "skill audit" / «аудит скилов», "wrap it in a plugin" / "заверни в плагин", "publish a skill" / "опубликуй скилл", "retrofit a skill to the standard" / "приведи скилл к стандарту". NOT for releasing a repo that ships no skill; opt out with "no make-skill" / «без make-skill».

導入数: 2
GitHub Stars: 4
更新日: 10月24日

ad-tracking

Use when wiring or auditing ad pixels and conversion tracking on the web: GA4, Google Ads, Meta Pixel and CAPI, LinkedIn Insight Tag, under Consent Mode v2 and GDPR/DMA. Not for running the campaigns, or the charge itself (stripe-billing). Opt out: no wiring, без обвязки. Triggers - "conversion tracking", "meta pixel", "consent mode", "GA4", "CAPI", "отслеживание конверсий", "пиксель Meta", "ретаргетинг".

導入数: 2
GitHub Stars: 4
更新日: 10月24日

frontend-performance

Use when building or auditing web pages for speed: Core Web Vitals (LCP, INP, CLS), Lighthouse and PageSpeed scores, render-blocking resources, bundle size, fonts and caching. Not for visual design (sheleg-design) or conversion work. Opt out: no wiring, без обвязки. Triggers - "PageSpeed", "Lighthouse", "Core Web Vitals", "bundle size", "performance budget", "ускорить сайт", "медленно грузится", "вес бандла".

導入数: 2
GitHub Stars: 4
更新日: 10月24日

google-auth

Use when a Node.js or Python server authenticates to Google: OAuth 2.0 flows, server-side ID token verification, service accounts, Application Default Credentials, Workload Identity Federation, API keys. Not for end-user web sign-in (google-signin). Opt out: no wiring, без обвязки. Triggers - "google auth", "google-auth-library", "service account", "ADC", "verifyIdToken", "авторизация Google", "сервисный аккаунт".

導入数: 2
GitHub Stars: 4
更新日: 10月24日

stripe-billing

Use when connecting a product to Stripe, fixing a payment bug ("баг в оплате") or auditing a live integration: checkout, renewals, refunds, cancellation and the retention coupon, and the webhook that grants an entitlement. Not for crypto (crypto-payments). Opt out: no wiring, без обвязки. Triggers - "add Stripe", "Stripe checkout", "subscription billing", "webhook signature", "cancel subscription", "подключить Stripe", "оплата подпиской", "вебхук Stripe".

導入数: 2
GitHub Stars: 4
更新日: 10月24日

brand-voice

Use when defining, calibrating or checking how a product speaks (tone of voice, terminology, canonical facts, per-surface register, locales). Triggers: "tone of voice" / "тон оф войс", "brand voice" / "голос бренда", "brandbook" / "брендбук", "our terminology" / "наша терминология". Not for writing the text itself (copywriting). Refusal phrase "no brand" / «без бренда».

導入数: 2
GitHub Stars: 6
更新日: 10月24日

copywriting

Use when writing or editing any text a user reads (UI strings, errors, landings, store listings, posts, video scripts, ads, email). Triggers: "write copy" / "напиши текст", "App Store description" / "описание для App Store", "microcopy" / "микрокопия", "video hook" / "хук ролика". Not for defining the voice (brand-voice) or the look (sheleg-design). Refusal phrase "no brand" / «без бренда».

導入数: 2
GitHub Stars: 6
更新日: 10月24日

ux-audit

Use when verifying the codebase against the UX scenario base (batched, evidence-backed, report in docs/ux/audits/). Triggers: "ux audit" / "UX-аудит", "run the scenarios" / "прогони по сценариям". Not for a whole-project audit (project-audit) or editing scenarios (ux-scenarios).

導入数: 2
GitHub Stars: 6
更新日: 10月24日

ux-flows

Use when designing or improving how users move through a product (flows, screen states, wireframes, Figma mockups, funnels, paywalls). Triggers: "user flow" / "юзер флоу", "add a screen" / "добавь экран", "mockups" / "макеты", "funnel" / "воронка", "paywall" / "пейволл". Not for the visual system (sheleg-design). Refusal phrase "no scenarios" / «без сценариев».

導入数: 2
GitHub Stars: 6
更新日: 10月24日

evidence-docs

Use when writing or reviewing anything read as true: a decision record, ADR, README, acceptance report, runbook, changelog, audit finding, or a claim that something was verified. Applies the ten canons of evidence-backed documentation and routes to the doctrine enforcing each; also a documentation gate or decision register. Not for: drafts, chat answers, commit messages; 'без доков' opts out.

導入数: 2
GitHub Stars: 6
更新日: 10月24日

project-audit

Use when someone asks what is true of a whole project: finished, half-built, broken, unexplored ('project audit', 'аудит проекта'). Discovers the project, runs probes, reads production evidence, leaves a JSON sidecar, an HTML report on request. Read-only: proposes board rows, commits nothing. Not for: one deliverable inside a run, a diff review, a skill's construction; 'без диагностики' opts out.

導入数: 2
GitHub Stars: 6
更新日: 10月24日

telegram-userbots

Use when a Telegram job needs a user account rather than a bot token: reading history a bot cannot see, acting as a person, bulk export with Telethon or another MTProto client, and the ban risk that comes with it. Not for ordinary bots (telegram-bots) or the web layer (telegram-miniapps). Opt out: no telegram, без телеграма. Triggers - "telethon", "pyrogram", "mtproto", "userbot", "FloodWaitError", "юзербот", "мтпрото", "сессия телеграм".

導入数: 2
GitHub Stars: 4
更新日: 10月24日

quest-perf

Use when a Meta Quest app drops frames, judders, overheats or must be profiled: frame budget per refresh rate, Dynamic Resolution, foveation, SpaceWarp, OVR Metrics, Perfetto or RenderDoc captures. NOT for the render loop itself (quest-native), Store VRCs (quest-store) or phone and desktop profiling. Opt out: no xr, без xr. Triggers - "dropped frames" / "просадка кадров", "Quest performance" / "производительность на Quest", "шлем греется".

導入数: 2
GitHub Stars: 1
更新日: 10月24日

quest-tooling

Use when setting up or driving the Meta Quest toolchain on a development machine: the metavr CLI and MCP server, Meta's agent skills, connecting a headset, managed tools, XR Simulator, no headset at all. NOT for app code (quest-native), reading a capture (quest-perf) or submitting a build (quest-store). Opt out: no xr, без xr. Triggers - "metavr", "connect the headset" / "подключить шлем", "adb к шлему", "XR Simulator".

導入数: 2
GitHub Stars: 1
更新日: 10月24日

quest-webxr

Use when the XR experience runs in the Meta Quest Browser: WebXR with IWSDK, three.js or A-Frame, PWA packaging with Bubblewrap, Horizon Billing and remote debugging. NOT for native OpenXR (quest-native), an APK submission (quest-store) or three.js depth off the headset (web3d-dev). Opt out: no xr, без xr. Triggers - "WebXR", "immersive-vr session" / "иммерсивная сессия", "three.js on Quest" / "three.js на Quest", "PWA для Quest", "IWSDK".

導入数: 2
GitHub Stars: 1
更新日: 10月24日

agent-evals

- Use when measuring whether an agent actually works — building an eval suite, judging a trajectory rather than a final answer, turning production traces into regression fixtures, calibrating an LLM judge against human labels, or gating a release on offline evals. Covers the three observability primitives (run, trace, thread) crossed with three eval granularities (single-step, full-turn, multi-turn), the offline/online/ad-hoc timing axis, pass-fail rubrics over scalar scores, cheap code checks b

導入数: 1
GitHub Stars: 4
更新日: 10月9日

MIT4 ファイル

詳細を見る →