Claude Skills by AgentShekel

[PROTOCOL] Tier-aware per-engagement acceptance methodology shared by all agency managers (marketing / dev / design). Defines per-tier (S/M/L) protocols: S has no manager phase, M adds Opus adversary, L adds cross-family consilium. Managers are JUDGES between producer and adversary, not re-runners. Reference-only — loaded by `*-manager` agents via skills frontmatter, not triggered by keywords.

[PROTOCOL] Single intake point for any agency task (marketing / dev / design). Classifies the domain, captures acceptance criteria, hands off to the matching domain lead. Does not plan, dispatch, or execute work. Use when: "мне надо агенси задачу", "агенси задача", "задача для агенси", "agency task", "agency work", "route agency".

[METHODOLOGY] AI platform visibility audit process (ChatGPT, Perplexity, Gemini, Claude, DeepSeek, Copilot, Yandex Neyro) with persistent projects, brand/competitor/segment management, intent-based prompt generation, source analysis, history tracking, trend comparison. Preloaded by marketing-ai-visibility-specialist agent.

[METHODOLOGY] Multi-format banner design (social, ads, web hero, print) with multiple art direction options and AI-generated visual elements. Preloaded by marketing-banner-designer agent.

[METHODOLOGY] Industry benchmark research — reverse-engineer how the fastest-growing companies in a given industry actually scaled (source harvest → company synthesis → cross-company meta-synthesis → private application layer). Evidence-disciplined, primary-source-first. Standalone capability — not wired into the agency cascade; has its own entry-point trigger. Use when: "мне надо провести исследование", "мне надо ресёрч", "ресёрч индустрии", "индустриальный ресёрч", "конкурентный анализ мет...

[METHODOLOGY] Brand voice, visual identity, messaging frameworks, asset management, brand consistency, tone of voice, style guides. Preloaded by design-brand-strategist agent.

[METHODOLOGY] Code review standards across 11 review dimensions, process, quality gates. Preloaded by code-reviewer agent.

[METHODOLOGY] Universal quality coding process (plan, TDD, reviews). Preloaded by dev-backend-engineer, dev-frontend-engineer, dev-fullstack-engineer agents.

[TOOL] Direct MCP integration with Codex CLI as agency tool. Codex (GPT-5-class) is available as MCP server, exposing tools `mcp__codex__codex` (start session) and `mcp__codex__codex-reply` (continue). Use Codex for: image generation, UI mockups, vision/multimodal review, cross-family second opinion. Reference- only — loaded by visual designers (design-visual-designer, marketing-banner- designer, design-ui-designer, design-presentation-designer) and adversary scripts via skill frontmatter.

[METHODOLOGY] CI/CD pipeline setup, deployment configuration, automated deploy workflows (GitHub Actions, Vercel, Railway, Fly.io, AWS, VPS), secrets management in CI. Preloaded by dev-devops-engineer agent.

[METHODOLOGY] AI-generated visual assets pipeline — logo generation (55 styles, Gemini AI), corporate identity program (50 deliverables, CIP mockups), icon design (15 styles, SVG, Gemini 3.1 Pro), social photos (HTML→screenshot, multi-platform). Preloaded by design-visual-designer agent.

[METHODOLOGY] Token architecture (primitive→semantic→component), CSS variables, spacing/typography scales, component specifications. Preloaded by design-ui-designer agent.

[METHODOLOGY] Decompose a design engagement plan into atomic task files (engagement/tasks/*.md). Each task = one specialist + one deliverable + measurable done-when. Enables targeted re-dispatch on iter-2 REJECT instead of re-running the whole brand/UI phase. Pure reference — invoked by design-lead at Phase 2.5 (after plan.md, before dispatch). Mandatory for size: L. Recommended for size: M with ≥2 specialists. Skipped on size: S (single deliverable).

[METHODOLOGY] AI-First development methodology (spec-driven pipeline, project structure, skills/agents ecosystem, quality gates). Preloaded by dev-lead and dev-* lead agents.

[PROTOCOL] Documentation backfill after an engagement changes code, architecture, deployment, or public contracts. Defines when to trigger, which doc files to update, and what the diff artefact must contain. Preloaded by lead agents (dev-lead, design-lead, marketing-lead). Pure reference — no triggers, not invoked by secretary.

[METHODOLOGY] Project documentation maintenance in .claude/skills/project-knowledge/ (audit, edit, consistency, status tracking). Preloaded by dev-technical-writer agent.

[PROTOCOL] Minimal contract every dispatched specialist (engineer, designer, copywriter, analyst, etc.) follows when running inside an agency engagement. Carve-out from engagement-protocol — the 6-bullet specialist subset only, without lifecycle / cross-domain / archival detail. Preloaded by specialist agents via skills frontmatter. Pure reference — no triggers.

[PROTOCOL] Canonical contract for agency engagement lifecycle: artefact schemas, state files, iteration budget, escalation rules, cross-domain handoff, observability. Single source of truth referenced by agency-intake, leads, managers, directors, and pipeline skills. Pure reference — no triggers, not invoked by the secretary as a router target.

[METHODOLOGY] Feature pre-filter (codebase exploration, feasibility check, GO/NO-GO verdict) — runs before user-spec to prevent wasted effort. Preloaded by dev-product-analyst agent.

[METHODOLOGY] Dev infrastructure setup (framework init, folder structure, Docker, pre-commit hooks with gitleaks, testing infrastructure, .gitignore). Preloaded by dev-devops-engineer agent.

[METHODOLOGY] Decompose a marketing engagement plan into atomic task files (engagement/tasks/*.md). Each task = one specialist + one deliverable + measurable done-when. Enables targeted re-dispatch on iter-2 REJECT instead of re-running the whole phase. Pure reference — invoked by marketing-lead at Phase 2.5 (after plan.md, before dispatch). Mandatory for size: L. Recommended for size: M with ≥2 specialists. Skipped on size: S (single specialist, single deliverable).

[METHODOLOGY] Post-deploy verification (execute AVP from tech-spec on live environment, verify acceptance criteria from user-spec + tech-spec, pick up deferred criteria from pre-deploy QA report) using MCP tools (Telegram MCP, Playwright, curl, bash). Preloaded by post-deploy-qa agent.

[METHODOLOGY] Pre-deploy acceptance testing (run test suite — unit/integration/E2E, verify acceptance criteria from user-spec and tech-spec, no live environment needed). Preloaded by pre-deploy-qa agent.

[METHODOLOGY] Strategic HTML presentation design with Chart.js, design tokens, responsive layouts, copywriting formulas, contextual slide strategies. Preloaded by design-presentation-designer agent.

[METHODOLOGY] New project planning (adaptive interview, tech decisions, fill project-knowledge documentation in one session). Preloaded by dev-product-analyst agent.

[METHODOLOGY] Guide for writing effective prompts for LLMs based on Anthropic + OpenAI 2025-2026 guidelines. Pure reference — invoked via slash command or explicit Skill tool call, not auto-triggered by keywords.

[METHODOLOGY] Comprehensive security analysis against OWASP Top 10 standards (authentication, user input, database queries, external APIs). Preloaded by security-auditor agent.

[METHODOLOGY] Semantic drift analysis process (topical deviation, underlinked content, misaligned queries, junk drift) using Yandex data, producing interactive HTML report with radial visualization. Preloaded by marketing-web-analyst agent.

[METHODOLOGY] Comprehensive SEO audit process orchestrating Yandex data sources (Webmaster, Metrika, Wordstat, Search) into a unified report with recommendations. Preloaded by marketing-seo-specialist agent.

[METHODOLOGY] Guide for creating/updating skills with specialized knowledge and workflows. Pure reference — invoked via slash command or explicit Skill tool call, not auto-triggered by keywords.

[METHODOLOGY] Design test scenarios for skills through user interview. Reads the target skill, interviews about scope and edge cases, saves scenario files for skill-testing to execute. Pure reference — invoked via slash command or explicit Skill tool call, not auto-triggered.

[METHODOLOGY] Execute test scenarios prepared by skill-test-designer. Spawns parallel runners with and without the skill, interacts as user persona, grades acceptance criteria, produces detailed test report. Pure reference — invoked via slash command or explicit Skill tool call, not auto-triggered.

[PROTOCOL] Generic system-optimization (skill-evolution) methodology shared by the three domain director-optimizers (dev / design / marketing). The SkillOpt loop adapted to a creative/dev agency: event-driven reflect → bounded edit → gate → slow-update over the agent/skill corpus, with a cross-family proposer and judge-only directors. Reference- only — loaded by `*-director` agents via skills frontmatter, not triggered by keywords.

[METHODOLOGY] Tech-spec decomposition into atomic task files with parallel creation and validation. Preloaded by dev-tech-architect agent.

[METHODOLOGY] Tech-spec creation (architecture, decisions, testing strategy, implementation plan) from approved user-spec. Preloaded by dev-tech-architect agent.

[METHODOLOGY] Testing strategy (when to write which tests, test quality standards, test pyramid). Preloaded by dev-qa-engineer agent.

[METHODOLOGY] Accessible UI implementation with shadcn/ui (Radix UI + Tailwind), Tailwind CSS utility-first styling, canvas-based visual designs, responsive layouts, dark mode, theming. Preloaded by design-ui-designer agent.

[METHODOLOGY] UI/UX design intelligence database (50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, 25 chart types across 10 stacks — React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, HTML/CSS). Preloaded by design-ux-designer agent.

[METHODOLOGY] User-spec creation through adaptive interview with codebase scanning and dual validation. Preloaded by dev-product-analyst agent.

[PROTOCOL] Cross-cutting validation chains. Defines which validators to run, in what order, with which triggers, across marketing / dev / design domains. Preloaded by lead agents (marketing-lead, dev-lead, design-lead). Pure reference — no triggers, not invoked by secretary.

[TOOL] Unified Yandex analytics hub configuration (shared tokens, cross-service workflows across Webmaster, Metrika, Wordstat, Direct, Search, seo-auditing, semantic-drift). Preloaded by marketing-web-analyst and marketing-traffic-lead agents.

[TOOL] Yandex Direct API v5 client (campaigns, ads, bids, keywords, spend reports, CTR, conversions). Preloaded by marketing-ppc-specialist agent.

[TOOL] Yandex Metrika API client (traffic overview, sources, devices, conversions, popular pages, audience geography, demographics). Preloaded by marketing-web-analyst and marketing-ppc-specialist agents.

[TOOL] Yandex Cloud Search API v2 client (position tracking, competitor analysis, SERP monitoring). Preloaded by marketing-seo-specialist agent.

[TOOL] Yandex Webmaster API v4 client (indexing status, search queries from SERP, crawl errors, backlinks, sitemaps, site diagnostics, SQI history). Preloaded by marketing-seo-specialist agent.

[TOOL] Yandex Wordstat API client (top queries up to 2000, associations, dynamics, regional stats, CSV export, missed-demand analysis from Yandex Direct XLSX). Preloaded by marketing-keyword-researcher and marketing-seo-specialist agents.