arkan

Search Amazon, extract product data, and present ranked recommendations. Use when user asks to shop on Amazon, find products, compare items, or research purchases. Prioritizes review count over rating.

Write and iterate on blog articles from idea to publishable draft. Use this skill whenever the user wants to write a new article, continue working on a draft, edit or improve an existing article, or mentions /article. Covers the full lifecycle — from brainstorming and outlining to polishing and finalizing. Also triggers when the user says things like "write a blog post about...", "I have an article idea", "help me finish this draft", or "improve this article".

Interact with personal bank accounts via Enable Banking CLI to check balances, browse transactions, analyze spending, forecast cash flow, and manage alerts. Use this skill whenever the user mentions money, bank accounts, balances, transactions, spending, budgets, forecasts, cash flow, or anything related to personal finances. Also trigger when the user asks questions like "how much did I spend", "what is my balance", "my latest transactions", "cash flow forecast", or any financial query. Proactively use this skill even if the user doesn't explicitly say "banking" — any mention of expenses, income, categories like "groceries", "rent", "transport", or account aliases should trigger it.

Stress-test a raw idea before turning it into a project: reformulate, research the market with Exa deep search, grill the assumptions adversarially, then output a decision log with Go/No-Go/Pivot verdict. Use when the user says /brainstorm, 'j'ai une idée', 'je pense lancer', 'je voudrais creer', 'idée de projet', 'idée de boite', 'on devrait faire X', or shares any half-baked product/business/side-project idea they want to vet before commiting. Especially valuable when the idea is fresh, unvalidated, and the user hasn't yet decided to pursue it.

Daily and weekly brief workflows. USE WHEN user says /brief morning, /brief evening, /brief weekly, /brief monthly, or synonyms like 'start my day', 'end of day', 'weekly brief', 'monthly brief'.

Manage client relationships. USE WHEN user asks about clients, follow-ups, client emails, or who needs attention.

Life coach that helps with personal growth, goals, career, relationships, health, productivity, and daily life. USE WHEN user says /coach, asks for life advice, wants accountability, mentions feeling stuck, overwhelmed, unmotivated, or needs help making a life decision. Also triggers on 'coach me', 'I need advice', 'help me decide', 'I'm stuck', 'I don't know what to do'.

Generate a daily summary of all Codex activity by parsing session JSONL logs and writing an Obsidian-compatible markdown note into the vault. Use this skill whenever the user asks to summarize Codex activity, generate a daily Codex report, or when triggered by a scheduled cron. Also triggers for: "resume codex", "activite du jour", "what did Codex do today", "journal codex", "daily recap".

Export Markdown and Obsidian notes to polished PDF documents with Pandoc and Typst. Use when converting `.md` files to PDF, rendering Obsidian callouts or embeds, rendering Mermaid diagrams, applying reusable Typst styling, configuring document branding, running PDF export preflight checks, or creating/updating portable Markdown-to-PDF configuration.

Commit, push, and open a PR

Use when the user needs multi-source research with citation tracking, evidence persistence, and structured report generation. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art". Not for simple lookups, debugging, or questions answerable with 1-2 searches.

Build interactive low-fidelity wireframes and/or high-fidelity prototypes of websites as a deployed web application. Use when the user asks to create wireframes, prototypes, mockups, or design screens for a website or web app.

Progressive UX generation — Phase 1 generates 5 B&W wireframe options instantly (1 safe + 4 exploratory), then Phase 2 renders Clean + Polished color variants via 5 parallel Task agents (one per option). Supports wireframes-only or wireframes+visuals. Extracts optimization intent from arguments when present. Maintains persistent design context. Use when user says "wireframe", "prototype", "UX options", or "layout exploration".

Implement an approved architecture proposal while removing obsolete compatibility paths and preserving the intended final shape.

Autonomous execution of a plan, PRD, or context document. Decomposes the input into discrete tasks, dispatches each to a subagent (using TDD workflow for testable code changes, normal execution for config/docs), then runs an automated code review via Codex and iterates fixes until the review passes (up to 5 review cycles). Supports `--skip-review` (no Codex review) and `--only-review` (review + fix loop on the user's existing uncommitted changes, no implementation). Use this skill whenever the user says '/do', asks to 'implement the plan', 'execute the PRD', 'ship this spec', 'run the plan autonomously', wants a plan/PRD/issue translated into working code without hand-holding, or hands over a docs/plans/*.md file and asks you to build it. Also use when the user says something like 'take this and build it', 'do everything in this document', or 'make it happen' while referencing a planning document, or 'just review what I have' / 'run the review loop on my WIP' (use `--only-review`). Trigger even if the user do

Import GitHub starred repos into the Obsidian vault as individual notes with a .base database view. Fetches stars via gh CLI, creates new notes (with README summary in French, auto-tags) and updates existing notes (stars, forks, dates, topics) in Resources/GitHub-Stars/. Idempotent — safe to run repeatedly. Use this skill when the user wants to sync, import, update, or fetch their GitHub stars, or mentions starred repos, GitHub bookmarks, or gh stars.

Use Zigzag-managed Zellij sessions, agent status, JSON commands, and safe project/worktree workflows.

This skill should be used when the user asks to "read a vault note", "create a note", "search the vault", "manage frontmatter properties", "find backlinks", "check orphan notes", "work with daily notes", "apply a template", "manage bookmarks", "find broken links", "append to a note", "patch a note section", "list vault tags", "manage tasks in vault", "move or rename a note", "delete a note", "generate an obsidian URI", or mentions Obsidian vault operations, vlt CLI, or vault-backed knowledge management. Provides comprehensive guidance for using vlt in agentic AI workflows, CI/CD pipelines, and shell scripting.