Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add sh0tn1k/telegram-ads/plugin install telegram-adsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sh0tn1k/telegram-ads/prepare-and-manage-tg-ads)<a href="https://agentmods.dev/skills/sh0tn1k/telegram-ads/prepare-and-manage-tg-ads"><img src="https://agentmods.dev/badge/skills/sh0tn1k/telegram-ads/prepare-and-manage-tg-ads/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sh0tn1k/telegram-ads/prepare-and-manage-tg-ads"><img src="https://agentmods.dev/badge/skills/sh0tn1k/telegram-ads/prepare-and-manage-tg-ads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00178 | $0.17333 |
| Opus 5 | $0.00089 | $0.08667 |
| Sonnet 5 | $0.00036 | $0.03467 |
| Haiku 4.5 | $0.00018 | $0.01733 |
Grade A, and why
prepare-and-manage-tg-ads scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 734 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare and Manage Telegram Ads
Purpose
Готовить, анализировать и давать операционные рекомендации по Telegram Ads: креативы, таргетинг, CPM/bid, бюджет, причины отклонения, оптимизация (stop/scale/adjust). Связывать рекламную статистику с воронкой и выручкой бота через UTM/campaign_id. Любое действие с внешними последствиями выполняется только после явного approval от the operator.
When to use
Hermes Goal pre-routing. Если запрос на рекламу сформулирован как цель в естественном языке (например, «запусти рекламу чтобы было 5 платящих»), сначала должна пройти Hermes Goal validation / routing layer. Этот skill получает только валидированный goal context или draft/plan request. Ad launch/change остаётся approval-gated: не вызывать live Telegram Ads actions без отдельного явного approval. Если project не imported / нет context intake — вернуть NEEDS_PROJECT_CONTEXT, а не готовить project-bound ad diagnosis.
- Подготовка новой Telegram Ads кампании (черновики креативов, таргетинг, диапазон CPM, бюджет).
- Ревью результатов уже идущей кампании (CTR/CPC/CPA/ROAS, downstream-конверсия).
- Диагностика отклонения объявления и переписывание креатива под политику Telegram.
- Рассмотрение изменения CPM/bid/бюджета.
- Создание новых вариантов объявлений (A/B под сегмент и метрику).
- Подготовка approval-запроса перед запуском/остановкой/изменением живой кампании.
When not to use
- До того как определены аудитория/сегмент/эксперимент — кроме случая, когда явно нужен только черновик.
- Для запуска, изменения или остановки живых кампаний без явного approval.
- Для написания постов в канал, онбординга, paywall-текстов (это другие skills).
- Для не-Telegram рекламных каналов, кроме концептуальной адаптации идеи.
- Для диагностики воронки/активации без рекламного контекста (используй analyze-funnel-and-metrics).
Required inputs
Минимум для осмысленной работы:
- цель кампании и целевая метрика (task_created, payment_completed, paid_conversion и т.п.);
- сегмент/аудитория и оффер (или явный запрос на черновик до их определения).
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/ads_watcher_integration.md 12 KB
- references/browser_profile_manager.md 20 KB
- references/direct_playwright_recovery.md 5.7 KB
- references/feature-branch-merge.md 4.7 KB
- references/live_diagnostics.md 7.2 KB
- references/operating_discipline_methodology.md 9.3 KB
- references/parser_diagnostics.md 22 KB
- references/placement_field_matrix.md 8.2 KB
- references/restart_safety_protocol.md 14 KB
- references/snapshot_failure_semantics.md 8.2 KB
- references/snapshot_reference.md 3.2 KB
- references/staged-patch-workflow.md 6.8 KB
- references/telegram_ads_tool_contract.md 6.2 KB
- references/tool_error_diagnostics.md 15 KB
- references/workflow_authoring.md 11 KB
- references/workflow_design.md 8.6 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago Changed · +4 lines 5c41c5ec1c91
- 12d ago First seen · 730 lines · 178 tokens per session scan A bf1750c2c239
prepare-and-manage-tg-ads is a skill published in the GitHub repository sh0tn1k/telegram-ads (0 stars, last pushed 11d ago), licensed MIT. It adds 178 tokens to every session and 17,333 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…