Automated summary
Manages and audits a Yandex Direct account through API v5: scored audits, campaign CRUD, keywords, performance reports, budget analysis and negative keywords.
Strengths
- Covers the full account lifecycle: audit, creation, keywords, reporting, optimization and budget
- Built on bundled references (50+ audit checks, 0-100 scoring system, benchmarks) that back up its recommendations
- Ships explicit optimization rules such as the 3x Kill Rule on CPA and detection of underspending or overspending campaigns
- Sub-command interface (/direct audit, report, optimize…) backed by a dedicated API wrapper script
Limitations
- Requires an OAuth credentials file (~/.secrets/yandex-direct.json) and working Yandex Direct API access
- Several commands write to live campaigns and budgets; no dry-run mode or write-confirmation step is described
- Russian-market and API v5 specific; audit quality depends on the bundled reference files (benchmarks, scoring) being present
Use it when an advertiser wants to audit, operate or optimize an existing Yandex Direct account from inside Claude Code.
Avoid it without valid API credentials, or when the goal is managing Google Ads / Meta Ads campaigns rather than Yandex Direct.
Security analysis
CautionThe skill performs standard Yandex Direct API management. It handles a long-lived OAuth token in plaintext and relies on unshown shell wrapper scripts plus Bash/WebFetch, which are powerful but used for a genuine advertising API purpose. No destructive or exfiltrating behavior is visible, so it warrants caution rather than a risky rating.
- •Reads OAuth credentials (client_id, client_secret, oauth_token) from plaintext ~/.secrets/yandex-direct.json
- •Delegates network calls to shell scripts (scripts/yd-api.sh, yd-report.sh, yd-audit.sh) whose contents are not shown and cannot be verified
- •Grants Bash and WebFetch, so it can execute arbitrary shell and make outbound requests — legitimate here but powerful
- •No evidence of obfuscation, curl|sh, rm -rf, or exfiltration to third parties; token is used only against api.direct.yandex.com
Examples
Проведи полный аудит моего аккаунта Яндекс.Директ: оценка 0-100, найденные проблемы и приоритетный план действийСделай отчёт по кампаниям Яндекс.Директ за последние 30 дней: CTR, CPC, конверсии и расходПроанализируй отчёт по поисковым запросам и добавь неэффективные запросы в минус-слова на уровне кампанииname: direct description: > Yandex Direct (API v5) advertising audit, management, and optimization. Full account audits, campaign management, keyword operations, reporting, budget analysis, and optimization recommendations for Russian market PPC. Triggers on: "Яндекс Директ", "Yandex Direct", "директ", "РСЯ", "YAN", "direct audit", "direct campaigns", "direct report", "direct optimize". argument-hint: "audit | campaigns | create | keywords | report | optimize | budget | negative" allowed-tools:
- Read
- Grep
- Glob
- Bash
- WebFetch
Yandex Direct — PPC Audit & Management (API v5)
Authors: Nick Serebrov & Kobe 🐍
Full-cycle Yandex Direct management: account audits, campaign CRUD, keyword management, reporting, optimization, and budget analysis.
Quick Reference
| Command | What it does |
|---------|-------------|
| /direct audit | Full account audit (all campaigns), scoring 0-100 |
| /direct campaigns | List campaigns with statuses and key metrics |
| /direct create | Create campaign (Search/YAN) with ad groups, keywords, ads |
| /direct keywords | Keyword management (list, add, update bids, pause) |
| /direct report | Performance stats (CTR, CPC, conversions, spend) |
| /direct optimize | Optimization recommendations (pause losers, adjust bids) |
| /direct budget | Budget spend analysis and forecasting |
| /direct negative | Negative keyword management (campaign & shared sets) |
API Configuration
Credentials: ~/.secrets/yandex-direct.json
{ "client_id": "...", "client_secret": "...", "oauth_token": "..." }
Endpoint: https://api.direct.yandex.com/json/v5/
Auth: Authorization: Bearer {oauth_token}
API wrapper script: scripts/yd-api.sh
Orchestration Logic
/direct audit
- Load credentials from
~/.secrets/yandex-direct.json - Fetch all campaigns via API (
campaignsservice) - Fetch ad groups, keywords, ads, sitelinks for each campaign
- Run 50+ checks from
references/yandex-audit.md - Score using
references/scoring-system.md - Compare metrics against
references/benchmarks.md - Generate report with grade (A-F), findings, and prioritized action plan
/direct campaigns
- Call
campaigns.getwith fields: Id, Name, Status, State, Statistics, DailyBudget, Strategy - Format table with status indicators
- Show key metrics if available (impressions, clicks, spend)
/direct create
- Gather: campaign name, type (SEARCH/YAN), geo, budget, strategy
- Create campaign via
campaigns.add - Create ad groups via
adgroups.add - Add keywords via
keywords.add - Create ads via
ads.add(TextAd for search, TextImageAd for YAN) - Add sitelinks and callouts
/direct keywords
- Fetch keywords via
keywords.getwith campaign/adgroup filter - Operations: add, suspend, resume, update bids, delete
- Show quality metrics where available
/direct report
- Use Reports service (
/json/v5/reports) - Build TSV report request with selected fields
- Available presets: campaign, adgroup, keyword, search_query
- Date ranges: today, yesterday, last7, last30, custom
- Parse and format results
/direct optimize
- Run report for last 30 days
- Identify: zero-conversion keywords (spend > 2x avg CPA), low CTR ads, expensive placements
- Cross-reference with
references/benchmarks.md - Generate recommendations sorted by impact
- Apply 3x Kill Rule: flag anything with CPA > 3x target
/direct budget
- Fetch campaign budgets and daily spend
- Calculate run rate, projected monthly spend
- Flag underspending (< 70% of budget) and overspending campaigns
- Budget sufficiency check vs strategy requirements
/direct negative
- Fetch negative keywords at campaign and ad group level
- Fetch shared negative keyword sets (
negativekeywordsharedsets) - Analyze search query report for new negatives
- Add/remove negatives via API
Quality Gates
- Never recommend broad match keywords without auto-strategy (Yandex best practice)
- 3x Kill Rule: flag keywords/groups with CPA > 3x target for pause
- Budget sufficiency: daily budget should support ≥10 clicks at current CPC
- Moderation: always check ad moderation status before optimizing
- Learning phase: don't change strategy settings during first 7 days
- UTM: all ads must have UTM parameters for Metrika attribution
Reference Files
Load on-demand, NOT at startup:
references/yandex-audit.md— 50+ audit checks (YD01-YD55)references/scoring-system.md— Weighted scoring (0-100, grades A-F)references/benchmarks.md— Russian market benchmarks (CTR, CPC, CVR)references/bidding-strategies.md— Yandex Direct bidding strategy guidereferences/compliance.md— Yandex moderation rules & ad policiesreferences/image-specs.md— Image sizes and specs for YAN (RSY) ads
Scripts
scripts/yd-api.sh— Generic API v5 call wrapperscripts/yd-report.sh— Reports service wrapperscripts/yd-audit.sh— Automated audit data collection
Subagents
agents/audit-yandex.md— Audit subagent for parallel campaign analysis
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/yandex-direct-ppc-audit-management-api-v5-ms47vogd/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/yandex-direct-ppc-audit-management-api-v5-ms47vogd' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/yandex-direct-ppc-audit-management-api-v5-ms47vogd/download' --output '.skill-downloads/yandex-direct-ppc-audit-management-api-v5-ms47vogd/SKILL.md.part' && mv '.skill-downloads/yandex-direct-ppc-audit-management-api-v5-ms47vogd/SKILL.md.part' '.skill-downloads/yandex-direct-ppc-audit-management-api-v5-ms47vogd/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Original excerpt: Quick Reference
| Command | What it does |
|---|---|
/direct audit | Full account audit (all campaigns), scoring 0-100 |
/direct campaigns | List campaigns with statuses and key metrics |
/direct create | Create campaign (Search/YAN) with ad groups, keywords, ads |
/direct keywords | Keyword management (list, add, update bids, pause) |
/direct report | Performance stats (CTR, CPC, conversions, spend) |
/direct optimize | Optimization recommendations (pause losers, adjust bids) |
/direct budget | Budget spend analysis and forecasting |
/direct negative | Negative keyword management (campaign & shared sets) |
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/yandex-direct-ppc-audit-management-api-v5-ms47vogd/SKILL.md' && test -s '.skill-downloads/yandex-direct-ppc-audit-management-api-v5-ms47vogd/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/direct' && cp -R '.skill-downloads/yandex-direct-ppc-audit-management-api-v5-ms47vogd' '.claude/skills/direct'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/yandex-direct-ppc-audit-management-api-v5-ms47vogd'openskills read 'yandex-direct-ppc-audit-management-api-v5-ms47vogd'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/yandex-direct-ppc-audit-management-api-v5-ms47vogd/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Writing Fragments
Content
Mine raw writing fragments through a relentless interview, without imposing structure. Capture ideas, quotes, and leading words for later use.
UI Copywriting & Auditing
Content
Write or audit user-facing UI copy including buttons, errors, empty states, and tooltips across the monorepo, following the design system source of truth.
Music MIDI Extraction
Content
Extracts the MIDI or score from an existing music production via the CogMusic MCP tool and confirms availability.