attribution-engine

0
0
Source

Helps creators clearly credit collaborators, tools, and partners in a way platforms understand. Reduces confusion, missed disclosures, and avoidable issues before content goes live.

Install

mkdir -p .claude/skills/attribution-engine && curl -L -o skill.zip "https://mcp.directory/api/skills/download/8108" && unzip -o skill.zip -d .claude/skills/attribution-engine && rm skill.zip

Installs to .claude/skills/attribution-engine

About this skill

Attribution Engine

1. What this skill does

Attribution Engine helps creators prepare clear, platform-aware credits and disclosures before publishing.

It focuses on clarity, consistency, and platform alignment, so your work travels cleanly across feeds, remixes, and reposts without unnecessary confusion later.

This skill does not tell you what you are legally required to do.
It helps you organize and format information using each platform’s own rules.


2. Important note before we begin

Before using this skill, you will see a short notice:

This tool helps format attribution and disclosure information using publicly available platform guidance.
It does not provide legal advice, determine compliance, or guarantee outcomes. You remain responsible for how and where content is published.


3. Why attribution matters in 2026

Attribution is no longer just courtesy.

Platforms now use attribution and disclosure signals to decide:

  • how content is labeled
  • how far it travels
  • whether it is limited, flagged, or reviewed

Small mismatches, like forgetting a native toggle or using the wrong AI label, can quietly reduce reach or trigger reviews.

This skill helps you catch those issues early.


4. Core concepts (plain language)

Attribution

Who should be credited publicly for the work.

Example:

  • Performer
  • Producer
  • Visual artist
  • Brand partner
  • Tool or system used

Disclosure

Whether viewers need to be told something important about how the content was made or funded.

Examples:

  • AI-assisted editing
  • Synthetic or altered media
  • Paid or gifted brand relationships

Provenance

How the content came into being.

Examples:

  • Fully human-authored
  • Human-authored with AI assistance
  • Fully AI-generated

5. Human vs AI labels (avoiding over-labeling)

Not all AI use is the same.

Over-labeling simple edits as “AI-generated” can cause platforms to treat your work as low-effort or mass-produced.

This skill helps distinguish between:

  • AI-Generated
    Content created autonomously by a system with no meaningful human editorial control.

  • Human-Authored, AI-Assisted
    Content where a person made the creative decisions and used tools for help such as cleanup, mastering, or compositing.

Example:

“Human-authored with AI-assisted mastering.”

This helps preserve trust without self-demotion.


6. Commercial relationships and brand credits

Hashtags alone are no longer enough.

If a post involves a material connection, such as:

  • sponsorship
  • gifted products
  • affiliate links
  • paid usage

most platforms expect you to use their native branded content tools.

This skill will:

  • flag when attribution suggests a commercial relationship
  • remind you to enable the platform’s built-in partnership or branded toggle

Example warning you may see:

This credit appears promotional. Make sure the platform’s native paid partnership setting is enabled before publishing.


7. Platform-aware formatting

Each platform treats attribution differently.

The Attribution Engine adapts output based on:

  • character limits
  • “read more” cutoffs
  • native labels and toggles
  • visible vs hidden metadata

Supported platforms include:

  • YouTube
  • TikTok
  • Instagram
  • Spotify
  • YouTube Music
  • SoundCloud
  • Tidal
  • Netflix
  • Amazon Music

You can also name any other platform. The skill will reference that platform’s current public documentation when available.


8. Metadata does not always survive uploads

Many platforms strip file metadata during upload.

To reduce loss:

  • the skill can generate a visible attribution string for captions or descriptions
  • and a reference ID you can keep internally

Example visible string:

Ref OP-2026-ALPHA | Auth R. Mutt | Human-AI Collaborative

This helps attribution survive reposts and re-uploads.


9. Collaborators and consent clarity

Attribution records are not contracts.

Listing collaborators here:

  • does not define ownership
  • does not imply revenue splits
  • does not replace agreements

This skill treats attribution as documentation, not legal representation.


10. How this fits with other skills

Attribution Engine works best alongside:

  • Creator Rights Assistant
    Organizes rights, licenses, and internal records at creation time.

  • Content ID Guide
    Helps you understand and organize information when automated claims appear.

Together, they support a calmer, more predictable content lifecycle.


11. What this skill does not do

This skill does not:

  • validate licenses
  • determine ownership
  • predict platform actions
  • guarantee reach or safety
  • advise on how to bypass systems

It exists to reduce avoidable mistakes and save time.


12. Simple example

Input:
Video with original music, light AI color correction, and a gifted product.

Output:

  • Suggested credit string for YouTube description
  • Reminder to enable branded content toggle
  • Human-authored, AI-assisted disclosure language
  • Platform-specific formatting notes

No guessing. No legal claims. Just clarity.


13. Summary

Attribution Engine helps creators explain their work clearly in the language platforms expect.

It reduces confusion, protects context, and supports transparency without over-labeling or over-promising.

Clean inputs lead to calmer outcomes.

fivem

openclaw

Fix, create, or validate FiveM server resources for QBCore/ESX (config.lua, fxmanifest.lua, items, housing/furniture, scripts, MLOs). Use when asked to debug resource errors, convert ESX↔QB, update fxmanifest versions, add items, or source scripts from GitHub. Also use for SSH key generation for SFTP access.

582395

a-stock-analysis

openclaw

A股实时行情与分时量能分析。获取沪深股票实时价格、涨跌、成交量,分析分时量能分布(早盘/尾盘放量)、主力动向(抢筹/出货信号)、涨停封单。支持持仓管理和盈亏分析。Use when: (1) 查询A股实时行情, (2) 分析主力资金动向, (3) 查看分时成交量分布, (4) 管理股票持仓, (5) 分析持仓盈亏。

802305

research-paper-writer

openclaw

Creates formal academic research papers following IEEE/ACM formatting standards with proper structure, citations, and scholarly writing style. Use when the user asks to write a research paper, academic paper, or conference paper on any topic.

85173

keyword-research

openclaw

Discovers high-value keywords with search intent analysis, difficulty assessment, and content opportunity mapping. Essential for starting any SEO or GEO content strategy.

465118

html-to-ppt

openclaw

Convert HTML/Markdown to PowerPoint presentations using Marp

36494

weread

openclaw

WeChat Reading (微信读书) CLI tool for fetching notes and highlights. Use when: (1) user asks about weread/微信读书 notes or highlights, (2) fetching today's or recent reading notes, (3) exporting book highlights, (4) managing reading bookshelf, (5) any task involving reading notes from WeChat Reading.

12186

You might also like

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

3,2252,761

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

4,2661,833

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

2,2231,672

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

2,3641,519

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

2,6701,284

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

2,0751,001