compare
Skill0 starsChanged 47 days agoApache-2.0View on GitHub
Build a before/after page for two videos - a project's preview and final render, a render against a variant or short, a clip against its tightened copy, or a render against a reference video to match - with a metrics table (frozen time, changes and cuts per second, moving share, static stretch, loudness), side-by-side, stacked and wipe views on one synced clock, frame stepping and per-side sound. Use when the user runs /video-studio:compare, asks to see two versions side by side, or wants to judge a change by watching it.
16 other projects use a version of this.
Adopted by
Most recently taken up by
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tooltheir own version, first seen Nov 8, 2026
- synaptiai/agent-capability-standardtheir own version, first seen Nov 1, 2026
- Hainrixz/claude-seo-aitheir own version, first seen Nov 1, 2026
- ansvisor/ansvisortheir own version, first seen Nov 1, 2026
- TakaGoto/rag-learning-academytheir own version, first seen Oct 28, 2026
- adeerkhan/vitruviustheir own version, first seen Oct 20, 2026
Used with
Projects with it also use evaluate, optimize and 5 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
NVIDIASkillevaluate
Scores existing Sports Intelligence AVLM inference outputs with avlm/evals: MCQ accuracy (run_mcq_eval.sh, INFERENCE_DIR), open-ended LLM-as-judge scores (needs CLIENT_API_KEY for the configured judge endpoint), tennis category breakdowns, run comparisons, chance-level sanity checks and triage of mcq_results.json or llm_judge_results.json. Use when the user asks to score, evaluate, benchmark or compare predictions.jsonl from inference runs, or to explain a suspicious accuracy. Not for running inference, training, quantization, data preparation, or third-party API model inference: never open, list or run anything under avlm/evals/inference_3rdparty, including when the user asks for it; it is excluded from the release.
Also in 3 projects that use this
aakash-dharSkilloptimize
Analyzes code for performance issues including slow algorithms, memory leaks, unnecessary re-renders, database query problems, and resource bottlenecks. Use when the user says "this is slow", "optimize this", "performance issue", "why is this taking so long?", or "make this faster".
Also in 4 projects that use this
OpenAISkillaudit
Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.
Also in 6 projects that use this
MicrosoftSkillreport
Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.
Also in 3 projects that use this
AnthropicSkillstart
Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.
Also in 3 projects that use this
Google CloudSkilltriage
Gather context on a change or bug and plan the implementation.
Also in 3 projects that use this
Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 16
- andrew-shwetzer/career-ops-plugin★ 501same name
- andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-★ 500same name
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool★ 432same name
- ansvisor/ansvisor★ 233same name
- Hainrixz/claude-seo-ai★ 81same name
- TakaGoto/rag-learning-academy★ 24same name
- n24q02m/wet★ 23same name
- n24q02m/wet-mcp★ 23same name
- adeerkhan/vitruvius★ 10same name
- joyehuang/skills★ 9same name
6 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository24 other files it gives its agents.
The file
Files
Compare two videos
The compare tool writes qa/compare/index.html with both videos copied
next to it (a.mp4, b.mp4). The page is one self-contained file with no
network requests, so the folder can be zipped and sent.
1. Pick the two sides
Each of a and b is one of:
{quality: "preview" | "final"}: this project's render;{project_dir, quality?}: another project's render, such as a variant or a short (absolute path);{file}: a video inside the project, relative to it, such as the originalassets/supplied/talk.mp4againstsource/assets/<asset>-tight.mp4(the filetightenwrites; its result gives the exact path);{reference}: a video to match, such as the piece the user pointed to: project-relative, or an absolute path only when the user gave it. The other side defaults to this project's latest render.
Give each side a short label when the defaults (quality, project name or
file name) would not tell the user which is which. a is the before or
reference side, and b the after side. With no sides given, the tool
compares this project's preview (a) with its final render (b). If a side is
missing, say which render or file is missing and offer the render skill.
2. Build the page
mcp__plugin_video-studio_engine__compare {project_dir, a?, b?}. It returns
each side's label, duration and resolution, notes on differing durations or
aspect ratios, and metrics[]: duration, frozen seconds and %, big changes
per second, cuts per second, moving % of frames, longest static stretch and
integrated loudness for both sides. Changes per second count sudden changes
(cuts, reveals); moving % counts every frame where the picture moves at all,
so smooth motion and crossfades show up there and not in changes/s. With a
reference, each metric has a verdict (ours meets or misses the reference);
summarise the misses in plain words and suggest the fix (more visual beats,
motion through the holds, shorter static stretches, loudness).
3. Hand it over
You can't open a browser. Give the user the absolute path of index.html
to open (on macOS: open "<path>") and tell them how to use it:
- Views: side by side, stacked, or wipe (drag the divider over the two videos laid on top of each other).
- Playback: one play button and scrubber drive both videos. Space plays and pauses, and ← and → step one frame. The shorter video holds its last frame.
- Sound: B is audible by default. Toggle each side's mute.
To say what changed rather than show it, pair this with the diff skill
(spec, lock and frame changes) or review (frames you can Read yourself).
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.

