Workflow·Design & Media

Video Source Comparison

This skill should be used when the user asks "compare these videos", "which source is better", "compare blu-ray vs web", "which release…

You say
Install this skill Read the source first Free Written by robbyt · unverified publisher
Context cost
1.3k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 5.1 kBtext throughout, nothing executable
Licence
free to use
Last change
no release on file
Servers it uses
Noneruns standalone

What it does

This skill should be used when the user asks "compare these videos", "which source is better", "compare blu-ray vs web", "which release should I use", "compare video quality", or needs to evaluate multiple versions of the same content to determine which has better quality.

Installed, it changes the agent in these ways.

What this skill changes about the agent is not written down here yet. The listing was collected from its source, and the description is in its own SKILL.md.

Workflow

Runs a procedure end to end.

Filed under

Design & Media

The skill itself

This is the whole product. A skill is instructions the model reads, so there is nothing behind the listing you cannot see first — the front matter loads with every session, and the body below it loads when the skill triggers.

SKILL.md5.1 kB · 170 lines
--- name: source-compare description: This skill should be used when the user asks "compare these videos", "which source is better", "compare blu-ray vs web", "which release should I use", "compare video quality", or needs to evaluate multiple versions of the same content to determine which has better quality. ---
6# Video Source Comparison
7
8Compare multiple video sources to determine which has better quality. Higher bitrate or resolution does not automatically mean better quality.
9
10## Core Principle
11
12Quality = how closely video resembles original master.
13
14When comparing sources:
15- Both derive from some common master
16- The better source is closer to that master
17- Technical specs (bitrate, resolution) are secondary to actual visual quality
18
19## Comparison Workflow
20
21### Step 1: Gather Metadata
22
23Run MediaInfo on both sources:
24```bash
25mediainfo source_a.mkv > source_a_info.txt
26mediainfo source_b.mkv > source_b_info.txt
27```
28
29Compare:
30- Resolution
31- Bitrate
32- Encoder used
33- Color space parameters
34- HDR metadata (if applicable)
35
36**Note**: Higher numbers don't guarantee better quality.
37
38### Step 2: Extract Comparison Frames
39
40Choose frames that reveal quality differences:
41
42**Good comparison frames**:
43- Dark scenes with gradients (reveals banding)
44- Scenes with fine texture (hair, fabric, foliage)
45- High motion scenes (reveals compression)
46- Scenes with text or sharp edges (reveals filtering)
47- Areas with strong colors (reveals color handling)
48
49**Extract frames with ffmpeg**:
50```bash
51# Extract frame at specific timestamp
52ffmpeg -ss 00:15:30 -i source.mkv -frames:v 1 frame_15m30s.png
53
54# Extract multiple frames
55ffmpeg -ss 00:10:00 -i source.mkv -frames:v 1 frame1.png
56ffmpeg -ss 00:25:00 -i source.mkv -frames:v 1 frame2.png
57ffmpeg -ss 00:45:00 -i source.mkv -frames:v 1 frame3.png
58```
59
60### Step 3: Visual Comparison
61
62**Using SlowPics** (https://slow.pics):
631. Upload comparison frames from each source
642. Uncheck "Show border" and "Smooth scaling"
653. Use clicker mode (not slider)
664. Press number keys (1/2/3) to switch rapidly between sources
67
68**What to look for**:
69
70| Area | Better Source Shows |
71|------|---------------------|
72| Dark gradients | Smoother transitions, less banding |
73| Edges | Clean edges, no haloing/ringing |
74| Textures | Preserved grain/detail, not smeared |
75| Colors | Natural, not oversaturated or shifted |
76| Compression | Less blocking, less mosquito noise |
77
78### Step 4: Check for Filtering
79
80**Signs of harmful filtering**:
81
82**Lowpassing (blur)**:
83- Soft, smeared appearance
84- Fine details less defined than other source
85- Some Blu-ray authoring studios apply this
86
87**Sharpening**:
88- Haloing around edges (bright/dark outlines)
89- Unnatural crispness
90- Line warping on straight edges
91
92**Color manipulation**:
93- Oversaturated colors
94- Crushed blacks or blown highlights
95- Different color grading than other source
96
97**Upscaling**:
98- Details too sharp for claimed resolution
99- AI hallucinations (invented details)
100- Native resolution lower than file resolution
101
102## Common Scenarios
103
104### Blu-ray vs Web
105
106**Blu-ray usually better when**:
107- Same master, Blu-ray has more bitrate
108- No filtering applied during authoring
109- Proper color space handling
110
111**Web can be better when**:
112- Blu-ray has lowpass filter applied
113- Web has newer/better master
114- Blu-ray is poor upscale from SD source
115- Web version has better color grading
116
117### Multiple Blu-ray Releases
118
119Different authoring studios, regions, or editions can have different quality:
120- Check authoring studio (some are known for lowpassing)
121- Compare frame-by-frame for filtering
122- Look for remastered vs original master
123
124### SD vs HD
125
126**HD version better when**:
127- Truly native HD content
128- Good upscale from clean SD master
129
130**SD version better when**:
131- HD is poorly upscaled from SD source
132- HD has additional filtering damage
133- SD is closer to original DVD master
134
135## Red Flags
136
137**Higher bitrate source might be worse if**:
138- Encoded with inferior encoder (NVENC vs x264)
139- Has filtering applied (sharpening, lowpass)
140- Is upscaled from lower resolution
141- Has wrong color space applied
142
143**Higher resolution source might be worse if**:
144- Upscaled from lower resolution original
145- Has AI upscaling artifacts
146- Native production resolution was lower
147
148## Quick Decision Guide
149
150| Comparison | Check First | Likely Winner |
151|------------|-------------|---------------|
152| Blu-ray vs Web | Filtering, authoring | Depends on studio |
153| 4K vs 1080p | Native resolution | If native, 4K |
154| HEVC vs AVC | Encoder, settings | Neither inherently |
155| High vs low bitrate | Encoder efficiency | Higher if same encoder |
156| HDR vs SDR | HDR legitimacy | SDR if HDR is fake |
157
158## Tools Reference
159
160- **SlowPics** (slow.pics) - Frame comparison hosting
161- **vs-preview** - VapourSynth comparison tool
162- **mpv** - Frame extraction, playback comparison
163- **MediaInfo** - Metadata comparison
164
165## Additional Resources
166
167- **JET Guide**: https://jaded-encoding-thaumaturgy.github.io/JET-guide/
168- **${CLAUDE_PLUGIN_ROOT}/references/quality-myths.md** - Why specs don't equal quality
169- **${CLAUDE_PLUGIN_ROOT}/references/artifacts.md** - What quality issues look like
170
In the file
SKILL.md769 words
Files1
Licence
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈80
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
1,195
on trigger
The instruction body, read only when the skill fires.
0.64%
of a 200k window
Ten skills this size would take about 6% of the window before you open a file.
050k100k150k200k context window

1.3k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

Adoption
Installsnone yet
Ratingno reviews yet

The procedure it runs

The procedure has not been published here. It is in the skill’s own SKILL.md, which its author has not sent to the marketplace yet.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It writes no files and reaches no network. All it changes is how the model reasons and writes.

What it asks for
Writes filesno
Network accessno

Read from the allowed-tools line of this skill’s own SKILL.md. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 5.1 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md5.1 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Video Source Comparison · 1.3k tokens when loaded npx mcprush@latest skill add robbyt/video-source-comparison

Writes to .claude/skills/video-source-comparison/ in the current project. Add --global to put it in your home directory instead, for every project.

Which clients pick it up on their own

A skill is a folder of text. A client with a skills folder reads it without being told; everywhere else the same text works, it is just handed to the model rather than found.

Claude Code.claude/skills/
Claude Desktop
ChatGPT
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok.grok/skills/
Zed.agents/skills/
Windsurf.windsurf/skills/
Agent SDK.claude/skills/
HTTP / API
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencerobbyt/video-source-comparison

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v
  • No earlier releases have been published to the marketplace.
Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

no reviews yet · no installs yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Who can post

Only accounts that have had the skill installed for fourteen days, so a review is written after living with it rather than after reading it. Publishers may reply once.

Who wrote it

RO
robbyt

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill