Productivity & Workflow Agent Skills for ChatGPT

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

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…

Design persistent AI agent personas with distinct voices, durable memory, and clear operating rules.

Aggregates, reconciles, and finalizes multi-agent engineering task results into comprehensive project-level integration reports.

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

Set up an agentic OS — either inside an Obsidian vault (bundled command-center dashboard, 5 auto-installed plugins, button bar wired to…

Generate AGENTS.md (cross-tool agent context — Codex CLI, Aider, Cursor, etc.) and wire CLAUDE.md as a symlink so Claude Code reads the…

Orchestrates a rigorous three-round debate between three AI personas to reach a reasoned consensus on complex topics.

Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block…

Aligns product thinking and refines fuzzy problem definitions by actively challenging assumptions and structuring collaborative…

Operate the AI-film production team and govern reusable assets from an approved director package.

Engineering operating model for teams where AI agents generate a large share of implementation output.

Analyze your past Claude Code conversations to measure AI fluency.

When the user wants to price an AI product, choose a charge metric, design pricing tiers, or optimize margins.

Decide whether a new AI tool, model, or technique is worth adopting — define the job to test it on, set decision criteria before trying…

Create new specialized agent

Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views.