analyse-channel-packaging
Skill2 starsChanged 48 days agoMITView on GitHub
Extract a channel's profile and banner branding before generating new packaging. Triggered by "analyse my banner", "what is this channel's visual brand", "review my channel packaging". In Spanish, "analiza mi banner", "cómo es la marca visual de este canal", "revisa mi packaging de canal".
In this repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- analyse-thumbnailsSkill
- channel-analyticsSkill
- channel-identitySkill
- channel-kickoffSkill
- competitor-boardSkill
- competitor-ideationSkill
- competitor-mappingSkill
- competitor-scanSkill
- image-generation-coreSkill
- image-refinementSkill
- keywords-seoSkill
- likeness-preservationSkill
- memory-reviewSkill
- monetisationSkill
- packagingSkill
- script-writingSkill
- thumbnail-best-practicesSkill
- thumbnail-inspirationSkill
- transparencySkill
- youtube-banner-specSkill
- youtube-profile-specSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Before generating a banner or a profile picture, your own or inspired by another channel.
- Very specific: line 38
Cross against the positioning: Read memory/channel_positioning.md: the packaging either backs the channel's promise or contradicts it.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Channel packaging analysis
WHEN
Before generating a banner or a profile picture, your own or inspired by another channel. Without seeing the current brand, whatever gets generated will be generic or will break an identity that already works.
EXECUTION ORDER
- Download and measure both pieces
Returns the avatar and banner downloaded, with the resolution, contrast and saturation of each.python3 tools/view_channel_packaging.py [--channel ID] --md - Open both files with the image reading tool. The pixels tell you whether there is contrast; they do not tell you what it conveys.
- Read the banner by its centre band. This is the most common reading
error: on mobile the top and bottom thirds are cropped away entirely. A
banner is judged by what survives in that strip, not by what you see on a
desktop. See
youtube-banner-spec. - Analyse the elements
- Colour scheme, and whether avatar and banner agree with each other.
- Banner typography: tagline, hierarchy, legibility when small.
- Avatar: is it recognisable at 32x32, its size in the comments?
- Banner zones: what sits in the safe band and what is lost to the crop.
- Identity elements: logos, signature colours, repeated motifs.
- Cross against the positioning. Read
memory/channel_positioning.md: the packaging either backs the channel's promise or contradicts it. That crossing is the analysis; describing colours is not. - If you are going to generate, load
youtube-banner-specoryoutube-profile-specdepending on the piece, and pass the current packaging as a reference:
Identity elements are preserved unless a full, explicit rebrand was asked for.python3 tools/generate_image.py --type banner --prompt "..." \ --ref data/packaging/<channel_id>_banner.jpg:packaging --dry-run
SOURCES
view_channel_packaging is derived: pixel metrics over images from the API.
The brand reading is the agent's judgement over files it has opened, and is
declared as such. channel_positioning.md is config, with its date.
OUTPUT
A brief in 5-8 bullets: what works, what is lost on mobile, what contradicts the positioning, and what would stay untouched in a redesign.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

