← All skill packs

AI Agent Workflow Collection

Skill pack
25 skills0 selected
jansenanalyticsSkills in this pack

Cross-proxy/process error check with aggregation, dedup, periodic monitoring — not bash grep -r error / tail -f / journalctl -f / curl probes.

English

Capture and structure assumptions from pilot plans and hypotheses into a centralized log for ongoing risk monitoring and stakeholder alerts.

English

CI/CD pipeline expert for GitHub Actions, GitLab CI, Jenkins, and deployment…

English

Analyzes and optimizes costs for cloud data…

English

CRE Due Diligence analysis suite — 7 specialist skills for multifamily property analysis including rent roll validation, expense benchmarking, market study, physical inspection, environmental review, title review, and tenant credit assessment.

English

Audit npm dependencies across all package.json files — reports outdated, security issues, and unused…

English

Guidance for verifying documentation accuracy against running OpenStack infrastructure. Use when detecting documentation drift, validating operations procedures against live systems, or confirming that runbooks produce expected results on the deployed cloud. Implements NASA Product Verification (SP-6105 SS 5.3) applied to documentation artifacts.

English

GitHub best practices for pull requests, code reviews, issues, Actions workflows, and repository…

English

Kanban Agent role. USE WHEN user says /kanban-agent OR wants to work on assigned kanban tasks as an agent.

English

Manage persistent Knowledge Graph for specifications. Provides read, query, update, and validation capabilities for codebase analysis caching. Use when: spec-to-tasks needs to cache/reuse codebase analysis, task-implementation needs to validate task dependencies or contracts, spec-quality needs to synchronize provides, or any command needs to query existing patterns/components/APIs. Reduces redundant codebase exploration by caching agent discoveries.

English

Monitor and triage incoming PRs for Aegis. Use when checking PR status, reviewing contributor PRs, or running /loop PR monitoring tasks.

English

React architecture patterns, TypeScript, Next.js, hooks, and testing.

English

Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop).

English

Encrypted credential store — AES-256-GCM secured tokens and secrets in one place.

English

Take screenshots of web pages and UI using Playwright for visual review and…

English

Gestionnaire d'emails Gmail PERSONNELS en français pour scanner, trier et archiver automatiquement les emails de l'INBOX selon des règles prédéfinies. Utiliser pour TOUS les emails personnels (envoyer, lire, trier). Utiliser quand l'utilisateur demande de "scanner les emails", "trier mes emails", "gérer ma boîte mail", "envoyer un email", "envoyer un mail" (sans préciser "professionnel"), ou toute tâche de gestion d'emails. Scanne UNIQUEMENT l'INBOX et déplace les emails vers les labels appropriés (personal/ecole, personal/voyage, personal/commandes, personal/Maison, pro/L'Oréal). Note: Pour les emails professionnels L'Oréal, utiliser o365-manager.

French

git bisect로 특정 코드가 추가/제거된 commit을 자동으로 찾기. file content 변경 시점, function 추가/제거, feature 도입 시점을 찾을 때 사용. binary search로 자동 검색하며 manual good/bad marking 불필요.

Korean

Cross-System Code-Analyse und Developer-Handoff fuer AutomationOne. Versteht Nutzerauftraege, verfolgt Daten- und Steuerfluesse quer durch ESP32, MQTT, Server und Frontend anhand des Repos (Read/Grep/Glob). Liefert evidenzbasierte Befunde mit Dateipfaden und formuliert konkrete, kopierbare Auftraege fuer esp32-dev, server-dev, frontend-dev, mqtt-dev nach Projekt-Patterns — ohne Produktcode zu aendern. Optional: Legacy-Modus vergleicht Debug-Reports unter .claude/reports/current/.

German

Skill de planification et execution de migrations de stack. Analyse un projet pour identifier les breaking changes, genere un plan de migration progressif par lots avec rollback possible, et execute la migration etape par etape. Supporte les montees de version majeures (Chakra v2 -> v3, Next 15 -> 16, Symfony 6 -> 7, etc.). Ce skill devrait etre utilise avant toute montee de version majeure d'une dependance structurante.

French

Analisi post-mortem della giornata di trading. PnL, WR per strategia e citta', skip reasons, filtri, raccomandazioni. Aggiorna memoria persistente. Use when user says "post-mortem", "analisi giornata", "com'e' andata oggi", "recap".

Italian

Используй при создании Project Brief, определении идеи проекта или уточнении scope. Структурированное исследование проблемы, пользователя, решения и границ MVP.

Russian

Generate realistic seed/fixture data based on schema…

Uncertain

Gestion de services avec systemd — units, timers, journalctl, boot et dépendances entre services.

French

Maakt snelle visuele schetsen en mockups als standalone HTML met Tailwind CSS. Gebruik deze skill wanneer de gebruiker iets wil visualiseren, schetsen, of een mockup wil zien. Triggers: "visualiseer", "schets", "hoe ziet dit eruit", "maak een mockup", "toon een voorbeeld", "prototype", "wireframe", "laat zien hoe dit werkt", "hoe zou X eruitzien", "kun je een scherm tekenen", "maak een flow", "toon het datamodel", "architectuuroverzicht". Ook bruikbaar als iemand twijfelt over een UI-beslissing of een concept wil valideren vóór implementatie.

Dutch

Includes Agnt Error Monitor, Assumption Logging, Cost Optimizer (Cloud Data Platforms), and other workflows.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Pack stats

Skills25CategorygeneralStars0

What’s included

Agnt Error Monitor

Cross-proxy/process error check with aggregation, dedup, periodic monitoring — not bash grep -r error / tail -f / journalctl -f / curl probes. 跨代理進程聚合去重監控錯誤。 Use when: check errors, monitor errors, browser errors, HTTP errors, process errors, error summary/dashboard, before bash grep/tail on logs

Assumption Logging

Capture and structure assumptions from pilot plans and hypotheses into a centralized log for ongoing risk monitoring and stakeholder alerts. Use when extracting, tracking

CI CD

CI/CD pipeline expert for GitHub Actions, GitLab CI, Jenkins, and deployment automation

Cost Optimizer (Cloud Data Platforms)

Analyzes and optimizes costs for cloud data platforms

Cre Due Diligence

CRE Due Diligence analysis suite — 7 specialist skills for multifamily property analysis including rent roll validation, expense benchmarking, market study, physical inspection, environmental review, title review, and tenant credit assessment.

Dep Audit

Audit npm dependencies across all package.json files — reports outdated, security issues, and unused packages

Doc Verifier

Guidance for verifying documentation accuracy against running OpenStack infrastructure. Use when detecting documentation drift, validating operations procedures against live systems, or confirming that runbooks produce expected results on the deployed cloud. Implements NASA Product Verification (SP-6105 SS 5.3) applied to documentation artifacts.

GitHub Workflow

GitHub best practices for pull requests, code reviews, issues, Actions workflows, and repository management

Kanban Agent

Kanban Agent role. USE WHEN user says /kanban-agent OR wants to work on assigned kanban tasks as an agent.

Knowledge Graph

Manage persistent Knowledge Graph for specifications. Provides read, query, update, and validation capabilities for codebase analysis caching. Use when: spec-to-tasks needs to cache/reuse codebase analysis, task-implementation needs to validate task dependencies or contracts, spec-quality needs to synchronize provides, or any command needs to query existing patterns/components/APIs. Reduces redundant codebase exploration by caching agent discoveries.

PR Monitor

Monitor and triage incoming PRs for Aegis. Use when checking PR status, reviewing contributor PRs, or running /loop PR monitoring tasks.

React Frontend

React architecture patterns, TypeScript, Next.js, hooks, and testing. Use when working with React component structure, state management, Next.js routing, Vitest, React Te

Research Pipeline

Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop). Goes from a broad research direction all the way to a subm

Secret Vault

Encrypted credential store — AES-256-GCM secured tokens and secrets in one place.

Visual Review

Take screenshots of web pages and UI using Playwright for visual review and iteration

Email Manager

Gestionnaire d'emails Gmail PERSONNELS en français pour scanner, trier et archiver automatiquement les emails de l'INBOX selon des règles prédéfinies. Utiliser pour TOUS les emails personnels (envoyer, lire, trier). Utiliser quand l'utilisateur demande de "scanner les emails", "trier mes emails", "gérer ma boîte mail", "envoyer un email", "envoyer un mail" (sans préciser "professionnel"), ou toute tâche de gestion d'emails. Scanne UNIQUEMENT l'INBOX et déplace les emails vers les labels appropriés (personal/ecole, personal/voyage, personal/commandes, personal/Maison, pro/L'Oréal). Note: Pour les emails professionnels L'Oréal, utiliser o365-manager.

Git Bisect Auto

git bisect로 특정 코드가 추가/제거된 commit을 자동으로 찾기. file content 변경 시점, function 추가/제거, feature 도입 시점을 찾을 때 사용. binary search로 자동 검색하며 manual good/bad marking 불필요.

Meta Analyst

Cross-System Code-Analyse und Developer-Handoff fuer AutomationOne. Versteht Nutzerauftraege, verfolgt Daten- und Steuerfluesse quer durch ESP32, MQTT, Server und Frontend anhand des Repos (Read/Grep/Glob). Liefert evidenzbasierte Befunde mit Dateipfaden und formuliert konkrete, kopierbare Auftraege fuer esp32-dev, server-dev, frontend-dev, mqtt-dev nach Projekt-Patterns — ohne Produktcode zu aendern. Optional: Legacy-Modus vergleicht Debug-Reports unter .claude/reports/current/.

Migration Planner

Skill de planification et execution de migrations de stack. Analyse un projet pour identifier les breaking changes, genere un plan de migration progressif par lots avec rollback possible, et execute la migration etape par etape. Supporte les montees de version majeures (Chakra v2 -> v3, Next 15 -> 16, Symfony 6 -> 7, etc.). Ce skill devrait etre utilise avant toute montee de version majeure d'une dependance structurante.

Post Mortem

Analisi post-mortem della giornata di trading. PnL, WR per strategia e citta', skip reasons, filtri, raccomandazioni. Aggiorna memoria persistente. Use when user says "post-mortem", "analisi giornata", "com'e' andata oggi", "recap".

Project Brief

Используй при создании Project Brief, определении идеи проекта или уточнении scope. Структурированное исследование проблемы, пользователя, решения и границ MVP.

Seed Data

Generate realistic seed/fixture data based on schema analysis

Systemd Manager

Gestion de services avec systemd — units, timers, journalctl, boot et dépendances entre services. Se déclenche avec "systemd", "systemctl", "service Linux", "journalctl"

Visualize

Maakt snelle visuele schetsen en mockups als standalone HTML met Tailwind CSS. Gebruik deze skill wanneer de gebruiker iets wil visualiseren, schetsen, of een mockup wil zien. Triggers: "visualiseer", "schets", "hoe ziet dit eruit", "maak een mockup", "toon een voorbeeld", "prototype", "wireframe", "laat zien hoe dit werkt", "hoe zou X eruitzien", "kun je een scherm tekenen", "maak een flow", "toon het datamodel", "architectuuroverzicht". Ook bruikbaar als iemand twijfelt over een UI-beslissing of een concept wil valideren vóór implementatie.

Showing 24 of 25 skills. Use the list’s page controls above to explore the rest.

Quick start

  1. Choose your skills. Select individual skills above, or choose the entire pack.
  2. Copy the install prompt. Use Copy install prompt above the list.
  3. 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:

Example request
Use the Agnt Error Monitor 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.
AI Agent Workflow Collection | Agent Skills Atlas