Pirate metrics — Acquisition, Activation, Retention, Referral, Revenue — адаптация под…
EnglishUnified brand compliance validation across visual, verbal, and legal dimensions. Use when relevant to the task.
EnglishUse when the user needs a detailed content brief with keyword targets, outline, structure, voice guidelines, and SEO requirements for a specific piece of content.
EnglishAdding new data models - schema, shared zod, entity pattern, and oRPC routes. Use when user asks to create a new entity, model, or feature that needs database tables.
EnglishCreates contextual design briefs before any visual work begins. Establishes product purpose, user specificity, design principles, and anti-goals. Prevents generic "template" design by requiring specific context.
EnglishGenerate Email-Bison-formatted subject + body for step 1 + step 2 from a situation-mining artifact + offer tier + entity. Emits a JSON artifact that the /marketing:launch-campaign command ingests. Triggers on write email copy, draft sequence, email copywriting, generate outbound copy, email drafting for, campaign copy for, EB-format email, per-vertical email preset. Adapted from Revgrowth1/ai-gtm-workflows workflow 10 (MIT).
EnglishUse when the user wants to decompose a JIRA Epic into sub-tasks with story point estimates. Trigger: 拆單, 'split tasks', 拆解, 'decompose', 'break down tasks', 子單, 'sub-tasks', 'epic breakdown', 評估這張單, 'evaluate this ticket'.
EnglishUse when reviewing code changes, auditing documentation accuracy, validating technical claims before merge, or user says "verify claims", "factcheck", "audit…
English9-language quality gate validation: linting, formatting, type checking, and test execution. Validates code changes meet quality standards before completion. Use when: (1) after code implementation, (2) before PR creation, (3) as part of /orchestrator Step 6, (4) manual quality check. Triggers: /gates, 'quality gates', 'run validation', 'check quality', 'validate code'.
EnglishТестируемая гипотеза — We believe / Will result in / We'll know when [metric] reaches…
EnglishJobs to Be Done (JTBD) framework by Clayton Christensen. Analyzes requirements through the lens of what 'job' customers hire products to do. Covers functional, emotional, and social jobs. Use when understanding underlying customer motivations or reframing features as outcomes.
EnglishJTBD-канва для B2B продуктов — functional, emotional, social jobs отдельно для buyer и…
EnglishObjectives & Key Results для B2B продуктовых команд — квартальный цикл, measurable key…
EnglishPlan and prioritize product roadmaps using frameworks like RICE, MoSCoW, and ICE.
EnglishE2E-тестирование через Playwright для CI/CD — автоматизированные spec-файлы, page objects, visual regression, pipeline интеграция. Для ручного тестирования в Antigravity → $qa-browser-testing.
EnglishJournalism source verification and fact-checking workflows. Use when verifying claims, checking source credibility, investigating social media accounts, reverse image searching, or building verification trails. Essential for reporters, fact-checkers, and researchers working with unverified information.
EnglishTooling — Biome (lint/format) и Bun (runtime/package manager). biome.json конфиг, ключевые правила, Bun scripts, pre-commit hooks, CI pipeline, миграция с ESLint+Prettier. Активируй при настройке tooling, добавлении линтера, или при вопросах «как настроить Biome/Bun».
EnglishWeighted Shortest Job First — SAFe-style приоритизация для enterprise B2B (cost of delay / job…
EnglishGénère des contrats API cohérents entre Frontend (Next.js) et Backend (NestJS) avec types synchronisés, validation standardisée et error handling uniforme. À utiliser lors de la création d'APIs, DTOs, types frontend/backend, ou quand l'utilisateur mentionne "API", "DTO", "types", "contract", "validation", "frontend-backend", "synchronisation".
FrenchКарта допущений по осям value / usability / feasibility / viability — приоритизация гипотез для…
Russian雲端基礎設施安全檢查清單與最佳實踐。 Use when: 部署到雲端平台、配置 IAM、設定 CI/CD pipeline、實作 IaC、配置監控或管理 secrets。 Triggers: "cloud security", "IAM policy", "CI/CD security", "Terraform security", "Cloudflare WAF", "雲端安全", "基礎設施安全".
Chinese
AGENT SKILLS ATLASIncludes Aarrr Metrics, Brand Compliance, Content Brief, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Aarrr Metrics
Pirate metrics — Acquisition, Activation, Retention, Referral, Revenue — адаптация под B2B
Brand Compliance
Unified brand compliance validation across visual, verbal, and legal dimensions. Use when relevant to the task.
Content Brief
Use when the user needs a detailed content brief with keyword targets, outline, structure, voice guidelines, and SEO requirements for a specific piece of content.
Data Model
Adding new data models - schema, shared zod, entity pattern, and oRPC routes. Use when user asks to create a new entity, model, or feature that needs database tables.
Design Brief
Creates contextual design briefs before any visual work begins. Establishes product purpose, user specificity, design principles, and anti-goals. Prevents generic "template" design by requiring specific context.
Email Copywriting
Generate Email-Bison-formatted subject + body for step 1 + step 2 from a situation-mining artifact + offer tier + entity. Emits a JSON artifact that the /marketing:launch-campaign command ingests. Triggers on write email copy, draft sequence, email copywriting, generate outbound copy, email drafting for, campaign copy for, EB-format email, per-vertical email preset. Adapted from Revgrowth1/ai-gtm-workflows workflow 10 (MIT).
Epic Breakdown
Use when the user wants to decompose a JIRA Epic into sub-tasks with story point estimates. Trigger: 拆單, 'split tasks', 拆解, 'decompose', 'break down tasks', 子單, 'sub-tasks', 'epic breakdown', 評估這張單, 'evaluate this ticket'.
Fact Checking
Use when reviewing code changes, auditing documentation accuracy, validating technical claims before merge, or user says "verify claims", "factcheck", "audit documentatio
Gates
9-language quality gate validation: linting, formatting, type checking, and test execution. Validates code changes meet quality standards before completion. Use when: (1) after code implementation, (2) before PR creation, (3) as part of /orchestrator Step 6, (4) manual quality check. Triggers: /gates, 'quality gates', 'run validation', 'check quality', 'validate code'.
Hypothesis Template
Тестируемая гипотеза — We believe / Will result in / We'll know when [metric] reaches [threshold]
Jtbd Analysis
Jobs to Be Done (JTBD) framework by Clayton Christensen. Analyzes requirements through the lens of what 'job' customers hire products to do. Covers functional, emotional, and social jobs. Use when understanding underlying customer motivations or reframing features as outcomes.
Jtbd Canvas
JTBD-канва для B2B продуктов — functional, emotional, social jobs отдельно для buyer и end-user
Kano Model
Классификация фич — must-have / performance / delighters / indifferent / reverse
Moscow Prioritization
Приоритизация по Must / Should / Could / Won't — для coarse scope cuts
Okr Framework
Objectives & Key Results для B2B продуктовых команд — квартальный цикл, measurable key results
Product Roadmap
Plan and prioritize product roadmaps using frameworks like RICE, MoSCoW, and ICE. Use when creating a roadmap, reprioritizing features, mapping dependencies, choosing bet
QA E2E Playwright
E2E-тестирование через Playwright для CI/CD — автоматизированные spec-файлы, page objects, visual regression, pipeline интеграция. Для ручного тестирования в Antigravity → $qa-browser-testing.
Rice Scoring
Приоритизация по Reach × Impact × Confidence / Effort
Source Verification
Journalism source verification and fact-checking workflows. Use when verifying claims, checking source credibility, investigating social media accounts, reverse image searching, or building verification trails. Essential for reporters, fact-checkers, and researchers working with unverified information.
Tooling Bun Biome
Tooling — Biome (lint/format) и Bun (runtime/package manager). biome.json конфиг, ключевые правила, Bun scripts, pre-commit hooks, CI pipeline, миграция с ESLint+Prettier. Активируй при настройке tooling, добавлении линтера, или при вопросах «как настроить Biome/Bun».
Wsjf Scoring
Weighted Shortest Job First — SAFe-style приоритизация для enterprise B2B (cost of delay / job size)
API Contracts Generator
Génère des contrats API cohérents entre Frontend (Next.js) et Backend (NestJS) avec types synchronisés, validation standardisée et error handling uniforme. À utiliser lors de la création d'APIs, DTOs, types frontend/backend, ou quand l'utilisateur mentionne "API", "DTO", "types", "contract", "validation", "frontend-backend", "synchronisation".
Assumption Mapping
Карта допущений по осям value / usability / feasibility / viability — приоритизация гипотез для тестирования
Cloud Infrastructure Security
雲端基礎設施安全檢查清單與最佳實踐。 Use when: 部署到雲端平台、配置 IAM、設定 CI/CD pipeline、實作 IaC、配置監控或管理 secrets。 Triggers: "cloud security", "IAM policy", "CI/CD security", "Terraform security", "Cloudflare WAF", "雲端安全", "基礎設施安全".
Showing 24 of 34 skills. Use the list’s page controls above to explore the rest.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Aarrr Metrics skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.