visual-studio
Skill0 starsChanged 2 months agoMITView on GitHub
Produce photoreal product stills, reusable identity packs, UGC/ad videos, cinematic VFX shots, and video thumbnails with native image_gen, image_edit, image_to_video, and reference_to_video. Use when: product photo, studio shot, lifestyle, Pinterest pin, hero banner, carousel, ad pack, virtual try-on, UGC, unboxing, product review, TV spot, cinematic video, VFX, character sheet, size-ref, face-lock, YouTube thumbnail, Shorts cover, or the user runs /visual-studio. Load native image tools if present, else DEGRADED before any generate/edit/video call. Not for UI/frontend (use impeccable), game sprites or tiles (use game-asset-core), or UI motion (use emil-design-eng).
1 other project uses a version of this.
Adopted by
Most recently taken up by
- G1Joshi/Agent-Skillstheir own version, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- G1Joshi/Agent-Skills★ 15same name
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 repository47 other files it gives its agents.
- templates/AGENTS.mdAGENTS.md
- academicSkill
- adhdSkill
- agent-architecture-auditSkill
- api-designSkill
- automation-audit-opsSkill
- browser-actSkill
- chrome-devtools-axiSkill
- click-path-auditSkill
- codebase-designSkill
- code-tourSkill
- contract-firstSkill
- cost-aware-llm-pipelineSkill
- diagnosing-bugsSkill
- diagram-designSkill
- domain-modelingSkill
- emil-design-engSkill
- eval-harnessSkill
- found-this-designSkill
- full-audit-keamananSkill
- full-performance-auditSkill
- gh-axiSkill
- grill-with-docsSkill
- humanizerSkill
- hyperframesSkill
- id-demo-videoSkill
- img2threejsSkill
- impeccableSkill
- install-anti-slopSkill
- markitdownSkill
- matt-code-reviewSkill
- mongodb-opsSkill
- playwright-qaSkill
- prompt-optimizerSkill
- prototypeSkill
- researchSkill
- scroll-craftSkill
- scroll-worldSkill
- skill-stocktakeSkill
- smartbook-ingestSkill
- smartdocSkill
- supabase-opsSkill
- tddSkill
- to-specSkill
- to-ticketsSkill
- vercel-opsSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
Before any image_gen, image_edit, image_to_video, or reference_to_video call, load native image tools if the session exposes them.
- Distinctive: line 23
Use only native image/video tools.
- Distinctive: line 25
Do not invent tool parameters.
- Very specific: line 32
If PRODUCT.md, DESIGN.md, or an Impeccable pin exists, copy its hex, logo path, type, and forbidden treatments into the pack lock.
- Distinctive: line 35
Ask at most four labeled questions, and only for blockers the brief does not already answer.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Visual Studio
Production director for photoreal stills and short videos. The image and video tools already own generation. This skill owns the production order, identity, modes, and VFX method.
Load first
Before any image_gen, image_edit, image_to_video, or
reference_to_video call, load native image tools if the session exposes them; otherwise write prompt files and mark DEGRADED. Tool choice, prompt
length, real-people references, exact text, shot length, and ffmpeg concat
live there. Do not restate them here.
Hard rules
- Use only native image/video tools. Do not call an external image/video API, CLI, or MCP.
- Do not invent tool parameters. If a capability is missing (video-to-video, 15s one-take, trained identity models), use the fallback in the matching reference.
- Match the user's language. Mode names stay English.
- Recurring people, products, creatures, and wardrobes come from an
identity pack (pipeline.md). Never a fresh
image_genof "the same" subject. - If
PRODUCT.md,DESIGN.md, or an Impeccable pin exists, copy its hex, logo path, type, and forbidden treatments into the pack lock. Do not invent brand facts. - Ask at most four labeled questions, and only for blockers the brief does not already answer.
Handoff
| Request | Skill |
| UI, landing, dashboard, design system | impeccable |
| Scroll-led storytelling / scrollytelling | scroll-craft |
| Scroll-scrub fly-through, diorama, 3D-world landing | scroll-world |
| Website/app whose UI needs designed photos or videos | impeccable leads the surface; this skill produces the media |
| Game sprites, tiles, icon sets, animation sheets | game-asset-core |
| Deterministic HTML composition rendered to video | hyperframes |
| UI motion / interaction feel | emil-design-eng after Impeccable |
| Photoreal stills, ads, cinematic, identity, thumbnails (no UI) | this skill |
| Photoreal person/creature inside a world page | scroll-world owns the chain + page; this skill cinematic for those stills/clips |
Route
Pick one lane from the brief. Load only that reference.
| Lane | User wants | Load |
| identity | character sheet, digital twin, face-lock, reusable person/creature | pipeline.md |
| still | product photo, studio, lifestyle, pin, hero, carousel, try-on, restyle | modes.md stills |
| ad-video | UGC, how-to, unboxing, review, TV spot, try-on video | modes.md ads |
| cinematic | VFX, plate, creature, jump, flyby, location cinematic | cinematic-vfx.md |
| thumbnail | YouTube thumbnail, Shorts/Reels cover | modes.md thumbnails |
A campaign that needs a person plus product plus video: identity pack first, then stills, then ads or cinematic. Do not start at video.
Run
- Route the lane. Load
imagineplus the one reference. - Reuse or build the identity pack before any scene that repeats a subject.
- Stills first. Approve or self-check the still against the lock. Then animate.
- One shot, one beat. Shot length and concat live in
imagine. - Deliver the files with short labels (mode, ratio, what is locked). Do not dump prompts, retries, or tool names unless the user asks.
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.