Productivity & Workflow Agent Skills

Interview the user about a new project through rounds of grouped clarifying questions (each with a recommended default), then draft and…

Build comprehensive 3-5 year financial models with revenue projections, cost structures, cash flow analysis, and scenario planning for…

Explore vague or ambitious ideas into a right-sized requirements-only unified plan.

Use first for install/update routing — sends setup, doctor, or MCP requests to the correct OMC setup flow

Analyzes YouTube videos to generate structured, trustworthy reports with transcript extraction, visual frame inspection, and actionable…

Delegate a task to the OpenAI codex CLI non-interactively and get its answer back.

Automate Zoho CRM tasks via Rube MCP (Composio): create/update records, search contacts, manage leads, and convert leads.

Generate a commit message for the current changes and print it — nothing else.

1-3-1 decision briefs: problem, three options, one pick.

It turns an idea described in plain words into a ready-made prompt for copying—it asks for the missing context, format, and success…

Aggregates, standardizes, and summarizes Chinese A-share broker research reports, analyst ratings, and consensus target prices.

Track beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.

Cross-verifies academic citations across multiple databases to detect DOI mismatches, author order discrepancies, and metadata errors.

Sales execution across pipeline, discovery, demos, negotiation, and closing.

Process receipts, track expenses in Google Sheets, reconcile records, and generate entertainment supplement tables for Field Museum…

Extract action items from today's Granola/Grain meetings, create Todoist

Navigate through the original three-world shamanic technology.

Notion-as-source-of-truth dispatch board for running your work like an AI agency.

Audit or rewrite Codex prompts, AGENTS.md files, skill instructions, and sub-agent briefs when guidance is bloated, conflicting, stale, or…

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

Use when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions…