Menu
SkillsMP has collected 28 skills from earlyaidopters/gumroad-resources. Open a skill to review its source and details.
Showing 28 of 28 collected skills.
Research and diagnose which AI personal-assistant operating model fits a user, including whether to stay put, use Grok Bot, Hermes Agent, Claude Cowork, ChatGPT Work, OpenClaw, or build an owned system. Use for assistant comparisons, switch decisions, product…
Personal Higgsfield replacement. Routes a plain-English idea to the best pay-as-you-go image or video model, refines the prompt for that model, calls the API via scripts/generate.py, saves the output, and logs cost to a running receipts ledger. Use when the…
Build premium editorial DOM websites — expressive serif display type, soft warm canvases, rounded media plates, alternating feature rows, card rails, calm scroll reveals. No WebGL, no scroll-scrubbed video. Use for product/SaaS landing pages, brand sites,…
Build award-tier immersive websites with WebGL, scroll choreography, shaders, or pre-rendered video — including turning a supplied video into a scroll-scrubbed site where scroll drives the playhead. Use for any request to build a cinematic, animated, 3D, or…
Transform rough ideas, bullet points, or text outlines into professional PowerPoint pitch decks. Create investor presentations, sales decks, or business proposals with proper structure and design. Use when the user mentions pitch deck, investor presentation,…
Generate a Claude Code usage report, extract key takeaways, save to Obsidian vault, and email a clean summary. Use when you say "monthly insights", "insights email", "email me my report", or "monthly review".
Implements a sophisticated multi-paradigm data transformation pipeline with configurable ETL stages, supporting both batch and streaming modalities across heterogeneous data sources with automatic schema inference and adaptive type coercion mechanisms.
Cleans, validates, and transforms CSV files for analysis. Use when user says "clean this CSV", "fix my data", "prepare this spreadsheet for analysis", "validate this dataset", or uploads a .csv file that needs processing.
Plans and creates sprint tasks in Linear from project context. Use when user says "plan this sprint", "create sprint tasks", "help me plan the next sprint", or "break this down into tickets". Works with Linear MCP for task creation.
Personal model benchmark built from YOUR own Claude Code history. Use when the user says /benchmark, "benchmark this model", "is <model> actually better", "test the new model on my workload", or when Claude Code upgrades to a new default model and they want a…
Cross-runtime skill optimizer. Use this skill when the user wants to package an Agent Skill so it runs in both Claude Code and OpenAI Codex from a single portable source. Also use when the user wants to import an existing skill (Claude Code or Codex) into the…
Use when the user wants to package a skill so it runs in both Claude Code and Codex from one source, import an existing skill into the portable format, install to Claude or Codex, or troubleshoot cross-runtime drift.
Demonstrates how the polyskill optimizer works. Use when you want to see a worked example that round-trips between Claude Code and Codex with every primitive exercised: dynamic injection, MCP dependencies, bash tool declarations, and front-loaded descriptions.
Use when you want to see a worked example that round-trips between Claude Code and Codex with every primitive exercised: dynamic injection, MCP dependencies, bash tool declarations, and front-loaded...
Chain all brain skills together. One command to search your Obsidian vault, extract insights, and synthesize a comprehensive brief on any topic.
Extract key insights, tasks, and connections from vault search results. Second step in the brain brief pipeline.
Search the Obsidian vault for all notes related to a topic. First step in the brain brief pipeline.
Generate a comprehensive brief from vault search results and extracted insights. Final step in the brain brief pipeline.
Write a 3-email launch nurture sequence (teaser, value, CTA). Reads previous launch outputs if available.
Consolidate all launch assets into a single professional PDF. Reads all previous launch outputs and packages them into one deliverable.
Chain all launch skills together. One command to go from idea to complete launch kit with market research, sales page, emails, social posts, and a PDF brief.
Research competitors, pricing, and positioning gaps for a new offer. Use when launching a product, course, or service and you need to understand the landscape first.
Generate complete landing page copy with pricing tiers for a new offer. Reads the market scan first if available.
Generate LinkedIn post copy and Twitter/X thread copy to announce a new offer. Reads previous launch outputs if available.
Automatically extract and track action items from meeting transcripts. Use when processing transcripts, reviewing meeting notes, or when the user asks about outstanding tasks or deadlines.
Automatically draft follow-up emails after meetings. Use when a meeting transcript is processed, when the user mentions sending follow-ups, or when action items are extracted from a meeting.
Mine your own Claude Code conversation logs to extract one model's reasoning discipline and port it to the model you run now. Use when someone wants to capture how a model like Fable 5 or Opus thinks, measure its working habits from real session logs, or turn…
Interview a business owner about their day-to-day tools, build a tailored data map, render a Pantry → Prep → Plate HTML visualization with recipes, a 30-day build plan, and an interaction-layer Sankey, plus generate plain-English Claude Code recommendations…