Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add VKirill/claude-lane-stack --skill yandex-direct-creativesgit clone --depth 1 https://github.com/VKirill/claude-lane-stackWrote 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/vkirill/claude-lane-stack/yandex-direct-creatives)<a href="https://agentmods.dev/skills/vkirill/claude-lane-stack/yandex-direct-creatives"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/yandex-direct-creatives/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/vkirill/claude-lane-stack/yandex-direct-creatives"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/yandex-direct-creatives.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00111 | $0.02423 |
| Opus 5.5 | $0.00044 | $0.00969 |
| Sonnet 5.5 | $0.00022 | $0.00485 |
| Haiku 4.5 | $0.00011 | $0.00242 |
Grade A, and why
yandex-direct-creatives 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 1mo 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this skill when
- Пишешь объявления для Яндекс.Директа любого формата (ТГО, РСЯ-баннер, СмартБаннер, МастерКампания)
- Получил CSV-выгрузку из Key Collector — нужно разбить на кампании / группы / объявления
- Выбираешь шаблон под intent (informational / transactional / branded / navigational)
- Проверяешь будет ли заголовок / текст в рамках лимитов Direct
- Подбираешь минус-слова из не-целевых intent в том же CSV
- Планируешь структуру naming (
[intent]_[geo]_[product]для кампаний,[cluster_id]_[marker]для групп) - Готовишь batch ≥ 100 креативов — нужен canary-план
- Получил ссылку на лендинг + CSV кластеров → нужны рекламные объявления Direct
Do not use this skill when
- Реально вызываешь Direct API (Ads.add, moderate, polling статусов) →
yandex-directskill для envelope + services - Юр-проверка для регулируемых ниш (медицина, фарма, БАД, азартные игры, алкоголь) →
legal-ru-marketingskill - Google Ads / VK Ads / TG Ads → их специализированные skills
- SEO-семантика / органический поиск →
seo-specialistагент или SEO skills - Контент-план / посты в соцсетях (не реклама) →
copywriter
Purpose
Скилл даёт ads-specialist знания и шаблоны для написания качественных объявлений Яндекс.Директа по кластерам Key Collector CSV. Покрывает: per-field лимиты (с учётом правила «пунктуация в отдельном счётчике для доп. заголовка + текст»), стилистические запреты, intent-шаблоны, стратегию маппинга кластеров на структуру Direct, canary-протокол для batch'ей. Финальная валидация ложится на Direct API при загрузке — клиентского валидатора в скилле нет.
Capabilities
Landing page research (ОБЯЗАТЕЛЬНО перед креативами)
→ references/landing-page-research.md
Лимиты и модерация
Per-field лимиты символов для всех форматов Direct (ТГО, РСЯ, Видео, СмартБаннер, МастерКампания, ДинамическиеОбъявления): заголовок 1 — 56 симв., заголовок 2 — 30 симв. + 15 пунктуации, текст — 81 симв. Ограничения по возрастным маркерам (18+), лимиты на уровне аккаунт / кампания / группа.
What ships with it
10 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/ad-formats.md 11 KB
- references/benchmarks-2026.md 10 KB
- references/campaign-types.md 12 KB
- references/cluster-to-campaign-strategy.md 9.5 KB
- references/composition-templates.md 16 KB
- references/csv-workflow.md 13 KB
- references/landing-page-research.md 6.2 KB
- references/limits-and-moderation.md 16 KB
- references/style-and-avoid.md 12 KB
- references/targeting-and-keywords.md 13 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.
- 1mo ago First seen · 153 lines · 111 tokens per session scan A 3a18356a6ff3
yandex-direct-creatives is a skill published in the GitHub repository VKirill/claude-lane-stack (122 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 2,423 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
eval-agents
Audit custom subagent definitions for Claude Code (.claude/agents/.md) and Codex (.codex/agents/.toml): loadability against the native schema, description overlap, model tier, tool scope, and headless-safe instructions. Use when onboarding to a project with agents, after adding or importing agents, or when the parent…
self-assessment
Interactive skill assessment with personalized learning path generation.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
source-command-methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.