What it does
This repo is a collection of 370 skills
- Connects Instruction files the AI reads
- Account or key Not confirmed yet (README not read yet)
- Category Coding
Maker’s original description
365 free AI marketing skills (zh-TW/en) for ChatGPT, Claude, Gemini, Claude Code & Cursor — copywriting, ads budget, margin, CRM, email. 365 個免費 AI 行銷 SkillsFor makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/backtrue-thinkwithblack-skill)Use together with
MCP servers that connect the AI to services for the same work
Fallow
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
Desktop Commander
MCP server for terminal commands, file operations, and process management
Similar Skills
Same kind of work, ordered like the Skills list
| This one thinkwithblack-skill | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| Maker | backtrue | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skills | 370 | 1 | 1 | 1 | 1 |
| GitHub stars | 274 | 463,670 | 233,682 | 148,887 | 143,987 |
| Last code change | Nov 11, 2026 | Nov 17, 2026 | Apr 20, 2026 | Nov 17, 2026 | Nov 16, 2026 |
| License | MIT | MIT | – | Apache-2.0 | MIT |
370 skills (instruction sets) by backtrue that an AI reads and follows · not an MCP server
Pick the skill to install
Install only the ones you use. Open a skill to see how to install it
This set has 370 skills, too many to install at once: every installed skill’s description loads into every chat, so the AI picks the wrong one more easily. Pick only the ones you use from the list below
Showing 29 of 370 See all on GitHub
- forecast-event-profit
Use historical campaigns and a recent baseline to estimate promotional CPM, conversion rate, and average order value, building ad-budget, revenue, and contribution-profit scenarios with backtesting. Use for campaign forecasting such as Black Friday and modeling instruction; use the existing sensiti…
- inf-05-07
Calculate the repeat-purchase interval, mean, and median for a specified cohort using customer identifiers and valid order dates. Use for questions about the average days between first and second orders across five years of records or how to calculate this in a spreadsheet; perform the measurement…
- mk-001
從商品頁、規格與使用說明整理可引用事實及缺件,適用「這些資料能拿來說什麼」;交付有來源的商品事實表,著重事實盤點,尚不挑選主打賣點
- mk-002
Derive differentiators and customer benefits from existing product facts. Use for “Which features should we lead with?” Delivers evidence-backed selling-point candidates when product materials are already available
- mk-003
Compare an existing selling point with product facts and competitor evidence. Use for “Could a competitor make the same claim?” Delivers a uniqueness comparison and evidence gaps for an existing claim
- mk-004
Customer-value check for selling points. Use when the task requires the customer benefit associated with each selling point. Apply this method to the specified inputs and verify the deliverable
- mk-005
Selling-point evidence matching. Use when the task requires a claim, evidence, and gap comparison table. Apply this method to the specified inputs and verify the deliverable
- mk-006
Prioritizing three lead selling points. Use when the task requires lead selling-point priorities and reasons for trade-offs. Apply this method to the specified inputs and verify the deliverable
- mk-007
Turning features into customer benefits. Use when the task requires a feature, advantage, and benefit translation table. Apply this method to the specified inputs and verify the deliverable
- mk-008
Turning selling points into usage scenarios. Use when the task requires creative angles that place specifications in everyday situations. Apply this method to the specified inputs and verify the deliverable
- mk-009
Functional value proposition. Use when the task requires one sentence linking a functional problem and its solution. Apply this method to the specified inputs and verify the deliverable
- mk-010
Emotional value proposition. Use when the task requires source-supported emotional benefits and communication boundaries. Apply this method to the specified inputs and verify the deliverable
- mk-011
Social-role value proposition. Use when the task requires a draft connecting role identity with product value. Apply this method to the specified inputs and verify the deliverable
- mk-012
One-sentence brand positioning. Use when the task requires one sentence stating who it serves, what it solves, and how it differs. Apply this method to the specified inputs and verify the deliverable
- mk-013
Competitive advantage comparison. Use when the task requires a comparison of brand differences within the evidence available. Apply this method to the specified inputs and verify the deliverable
- mk-014
Diagnosing unfocused selling points. Use when the task requires locations where copy departs from the core value and directions for revision. Apply this method to the specified inputs and verify the deliverable
- mk-015
Customer-clue inventory. Use when the task requires separate columns for raw clues, sources, knowns, and unknowns. Apply this method to the specified inputs and verify the deliverable
- mk-016
Persona candidate creation. Use when the task requires audience hypothesis cards that do not fabricate real identities. Apply this method to the specified inputs and verify the deliverable
- mk-017
Interpreting customers' core values. Use when the task requires what customers value and the original evidence for it. Apply this method to the specified inputs and verify the deliverable
- mk-018
Grouping purchase motivations. Use when the task requires groups with different motivations for buying the same product. Apply this method to the specified inputs and verify the deliverable
- mk-019
Customer pain-point inventory. Use when the task requires a list of customer problems, their impacts, and evidence. Apply this method to the specified inputs and verify the deliverable
- mk-020
Distinguishing needs from wants. Use when the task requires a comparison of necessary solutions and desired feelings. Apply this method to the specified inputs and verify the deliverable
- mk-021
Interpreting high and low willingness-to-pay clues. Use when the task requires observable signals and questions to validate. Apply this method to the specified inputs and verify the deliverable
- mk-022
Expanding scenarios with 5W1H. Use when the task requires a table of people, tasks, times, places, and reasons. Apply this method to the specified inputs and verify the deliverable
- mk-023
Separating users from buyers. Use when the task requires role hypotheses such as personal use, gifting, and purchasing for someone else. Apply this method to the specified inputs and verify the deliverable
- mk-024
Time-based scenario angles. Use when the task requires a scenario question bank for usage times or seasons. Apply this method to the specified inputs and verify the deliverable
- pmax-copy
Produce, rewrite, and review Google PMAX text assets. Use when the user requests PMAX ads, headlines and descriptions, stronger reasons to click, or a complete copy rewrite. Start from Persona, USP, and evidence; establish the entry point, need scenario, and landing page, then express the same scen…
- simplify-member-rules
Organize existing points, membership, subscription, and digital-benefit rules into explanations customers can understand. Check each scenario for unchanged benefits before and after rewriting, and design comprehension tests that do not reveal answers. Use when rules are excessive, names are confusi…
- write-marketing-rollout-plan
Also use for phased consumer demand leading to business orders and store visits, or for creator experiences combining onsite sales with later promotional content. Turn existing marketing ideas into a strategy and advertising rollout for a quarter or specified period that managers can understand. De…
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Claude CodeCodexCursor
From the maker’s README and the folders in the repo
Install
Pick a skill first
This repo has 370 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 274
Stars are for the whole repo, not each skill - Maker
- backtrue
- License
- MIT
- Last code change
- Nov 11, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 30
- Topics
- agent-skills, ai-marketing, chatgpt, claude, claude-code, claude-skills, copywriting, cursor, digital-marketing, ecommerce, email-marketing, gemini