Asset Library
1,738 video parts you can take today, and 557 more to learn from. Find one you like, then open it for the details.
Showing 121 of 2,295Show everything
In words · 121
locate.mjsFinds a point in an image by drawing numbered grids over it with ffmpeg. Its auto mode posts the image to Google if GEMINI_API_KEY is set.Tool · Apache-2.0A check on the resultverify-motion.mjsCompares the motion in a render against a reference export (Figma's own MP4) and fails under 15 dB. Described in the figma SKILL.md; the…Tool · Apache-2.0A check on the resultremotion-studioLaunching Remotion Studio to preview a video: when to let it open the browser itself and when to print the address for an in-app browser…Skill · Link onlyA check on the resultcreative/video-understand-usageUsing the local vision model on frames and clips: modes, model choice, which frames to pick.Skill · Link onlyA check on the resultmeta/checkpoint-protocolWhen and how to save a stage's state and when to stop and wait for the person. A stage marked as needing approval cannot be recorded as…Skill · Link onlyA check on the resultmeta/reviewerThe self-review an agent runs after every stage: check the file against its schema, against the stage's review points and the style rules…Skill · Link onlyA check on the resultcharacter-animation-qaReviewing local character animation: schema checks, browser previews, frame samples, final output checks.Skill · Link onlyA check on the resultvideo-understandUnderstanding a video locally with FFmpeg frame samples and Whisper transcription.Skill · Link onlyA check on the resultweb-design-guidelinesReviewing interface code against web interface guidelines.Skill · Link onlyA check on the resultaudio_probeReads the length and stream details of an audio or video file with ffprobe. Runs on the machine; needs ffprobe. Works with no keys.Tool · Link onlyA check on the resultcomposition_validatorChecks a planned composition before rendering: catches audio and picture lengths that do not match and similar plan errors. Runs on the…Tool · Link onlyA check on the resultframe_samplerPulls still frames out of a video with FFmpeg, at set times or intervals. Runs on the machine; needs ffmpeg. Works with no keys.Tool · Link onlyA check on the resultvideo_analyzerTakes a reference video apart: transcript, scenes, sampled frames and structure, written up as a brief the agent plans from. Runs on the…Tool · Link onlyA check on the resultvideo_understandDescribes frames or clips with a local vision-language model. Runs on your own GPU with model weights you download; needs transformers…Tool · Link onlyA check on the resultvisual_qaAutomatic checks on a rendered video: black frames, frozen stretches and similar faults, from sampled frames. Runs on the machine; needs…Tool · Link onlyA check on the resultcharacter_animation_reviewerChecks a character animation: rig integrity, motion and render readiness, as a report. Runs on the machine. Works with no keys.Tool · Link onlyA check on the resultBacklotA local web board that watches the projects folder and shows a production as it runs: stages, script, scene plan, generated assets as a…Tool · Link onlyA check on the result/backlotSlash command that opens the Backlot board for the current or named project. Copies for other agents sit in .cursor/commands…Skill · Link onlyA check on the resultSlideshow risk scorerScores a scene plan from 0 to 5 on six things that make a video feel like a slide deck: repetition, decorative visuals, motion without…Tool · Link onlyA check on the resultScene variation checkerChecks a scene plan for sameness before any asset is made: shot sizes, camera movement, lighting, a flagged high point, texture words…Tool · Link onlyA check on the resultDelivery promiseClassifies what a video has promised to be (for example led by motion or led by stills) at proposal time and locks it, so the render cannot…Tool · Link onlyA check on the resultCheckpoint storeWrites and reads a saved state after each stage so a run can resume, and refuses to record a gated stage as done without recorded approval.Tool · Link onlyA check on the resultSource media reviewInspects footage a user supplies (probe, sampled frames, scenes, transcript) and writes one normalized review file, so planning starts from…Tool · Link onlyA check on the resultScene pacing checkChecks that the steps of a fake terminal scene land in time with the narration cues, and fails loudly when they drift.Tool · Link onlyA check on the resultTool event logAn append-only log of tool events per project, written whenever a tool runs and read by the Backlot board.Tool · Link onlyA check on the resultatelier_snapshots.pyRenders one review still per scene of a hand-written composition so the board can show them.Tool · Link onlyA check on the resultbacklot_simulate_run.pyFakes a pipeline run on disk so the Backlot board can be watched updating; useful as a demo of the board.Tool · Link onlyA check on the resultbacklot_screenshot_stage.pyBuilds fictional projects and captures the board screenshots used in the README, with Playwright.Tool · Link onlyA check on the resultbacklot_visual_eval.pyA screenshot test for the board: captures fixed views and compares them with saved ones.Tool · Link onlyA check on the resultbacklot_watch_captures.pyCaptures a board screenshot each time a watched project changes.Tool · Link onlyA check on the resultkling_official_animated_explainer_e2e.pyAn end-to-end check of the Kling provider path; a free dry run by default, paid modes on request.Tool · Link onlyA check on the resultatlas_media_smoke.pyAn opt-in paid test run of the Atlas Cloud media tools.Tool · Link onlyA check on the resultcharacter_qa_report schemaA review of rig integrity, motion and render readiness. A JSON Schema; required fields: version, status, checks.Starter · Link onlyA check on the resultdecision_log schemaThe audit trail: every meaningful choice with the options considered and the reason, appended and never edited. A JSON Schema; required…Starter · Link onlyA check on the resultfinal_review schemaThe self-review of a finished render: a technical probe, frames looked at from four points, an audio check, whether the promise was kept…Starter · Link onlyA check on the resultreview schemaA stage review: findings each graded critical, suggestion or nitpick, with the agent's response and whether it was accepted. A JSON Schema…Starter · Link onlyA check on the resultsource_media_review schemaThe review of footage a user supplied, with what it means for planning. A JSON Schema; required fields: version, files, summary…Starter · Link onlyA check on the resultcheckpoint schemaThe resumable snapshot written after each stage. A JSON Schema; required fields: version, project_id, pipeline_type, stage, status…Starter · Link onlyA check on the resultgsap-performanceShort rules for smooth playback in a browser: animate transforms and opacity rather than width, height, top or left; will-change only on…GSAP · MITA check on the resultaesthetic-rules (review rules)29 rules written as past rulings, in five groups: rhythm (R1-R4), look, camera and composition (Q1-Q11), sound (S1-S5), copy (C1-C3)…Skill · Apache-2.0A check on the resultfinal-review (independent last check)The brief for a fresh reviewer who checks the finished film against the plan, the chosen cards, the demo source and the aesthetic rules…Skill · Apache-2.0A check on the resultGallery (static preview site)A static site that lists the 124 cards and 150 moves with search, filters and copyable names. The data is gallery/api/library.json. 54…Tool · Apache-2.0A check on the resultsmoke-render-demos.py (first-frame test of every demo)Registers every demo that exports a duration into a generated root file and renders its first frame, to catch demos that compile but crash.Tool · Apache-2.0A check on the resultshot-polish (the redesign review rig)The author's tooling and notes from the October 2026 pass that re-made all 216 demos and kept 150: per-shot notes, a keep/cut decisions…Tool · Apache-2.0A check on the resultjudgment.md (the eight judgments)The taste layer in full: eight judgments each with when, prefer, because, evidence and where it stops being true; twelve default reaches…Skill · Apache-2.0A check on the resultslop.md (the review file)The checklist run on a plan and on a render: the never-ship list, 25 ranked default patterns (N1-N25), a table of AI default against…Skill · Apache-2.0A check on the resulttaste/verdicts.md and taste/edits.mdThe author's own record of what one person said about specific films, and 18-odd before/after fixes with the reason for each. It is one…Skill · Apache-2.0A check on the resultstudies (two calibration strips)Two JPEG strips of invented brands, each pair showing a default beside a decision, drawn in different styles on purpose so they are not…Skill · Apache-2.0A check on the resultexamples/selftest (runtime regression page)A test page for the runtime itself: visibility tracks, per-word options, multi-line typing, origin claims, keyframe steps. It must print…HTML · Apache-2.0A check on the resultMotion.selfTestProves a film is seek-safe: plays every frame in order, then jumps to random frames and compares every element's style, transform and text…GSAP · Apache-2.0A check on the resultlook.pyInspects a rendered film: contact sheet, cut list, frames just before each cut, an audio audit, and gates G0 (render exists and moves), G2…Tool · Apache-2.0A check on the resultlint.mjsThe page-chrome lint, gate G5: loads the film's HTML and fails corner labels, tracked-caps labels, counters, timecodes, header or footer…Tool · Apache-2.0A check on the resultblind_review.pyBuilds a local page for choosing between two or more versions blind: random left/right, synced play, frame step, a pick and notes, with the…Tool · Apache-2.0A check on the resultshowcase comparisons (Cluely, Spotify, Wispr Flow)Three before/after films, GIFs and posters that put other companies' brands on screen to show the difference the skill makes. The NOTICE…Skill · Link onlyA check on the resultSafe mode (BLENDER_MCP_SAFE_MODE)An optional checker, off by default, that reads every script the model sends before it reaches Blender and rejects it if it imports…Tool · MITA check on the resultContext log (BLENDER_MCP_CONTEXT_LOG)An optional local log, off by default, of how many characters and estimated tokens each tool definition and tool result costs the…Tool · MITA check on the resultlookReturns one picture of the scene so the model can check its work: the user's viewport, the view through the scene camera, an auto-framed…Tool · MITA check on the resultget_scene_infoDescribes the scene in text: one header line, then one line per object with the fields asked for (location, size, whether it sits on the…Tool · MITA check on the resultget_addon_statusReports the Blender version, whether the add-on matches the server, which libraries and generators are switched on, and whether data…Tool · MITA check on the resultdisable_telemetryTurns the opt-in collection of prompts, code, screenshots and scene data off from inside a chat. It can only turn it off, and it does not…Tool · MITA check on the resultrecord_trajectory_feedbackAsks the model to file the user's reaction to a result (accept, reject, undo, or a correction in their words) into the author's training…Tool · MITA check on the resultopen_viewportShows the latest viewport picture in a panel beside the conversation.Tool · MITA check on the resultviewport_latestReturns the stored viewport picture if it is newer than the one the panel has; does not touch Blender.Tool · MITA check on the resultviewport_captureTakes a fresh viewport picture for the panel, on Refresh or by itself after the scene changes.Tool · MITA check on the resultviewport_pickFinds the object under a click on the viewport picture, so a person can point at a thing and attach it to their next message.Tool · MITA check on the resultsearch_mentionsLists scene objects, materials and collections matching a few typed letters, for @-mentions in the message box.Tool · MITA check on the resultblender:// resources (object, material, collection)Three MCP resource addresses that return one scene item's details as JSON, used by the @-mentions.Tool · MITA check on the resultViewport app (apps/viewport.html)A single HTML page the server hands to clients that support MCP Apps: a live viewport picture beside the chat with refresh and…Tool · MITA check on the resultasset-optimizationThe gate before export: an audit checklist for geometry, UVs, materials and naming, fixes for common overruns, LOD steps at 50, 25 and 10…Blender · MITA check on the resultlookdevThe loop that gets shading right: gray clay pass, base materials, a neutral three-point rig, then beauty light, a screenshot, a list of…Blender · MITA check on the resultqa-reviewA ship or no-ship review backed by screenshots: five required views, four defect levels, and a verdict template. It tells the agent never…Blender · MITA check on the resultreference-image-match (shared reference)The pack's best single page, though it is a shared reference and not one of the 94 skills: a written protocol for making a Blender scene…Blender · MITA check on the resultdream-loopThe skill itself, 2,900 characters: first get a target picture (the user's, or one made with an image generator and prompted as a real…Skill · MITA check on the resultPro workflowThe loop with a judge: build a first pass, take a screenshot, give the screenshot and the target to a fresh sub-agent that scores…Skill · MITA check on the resultfal-batch.test.mjsNine tests for the Fal helper that run against a mocked network: concurrency, resuming without paying twice, uncertain submissions never…Tool · MITA check on the resultpreview-server.pyA 46-line Python web server for the loop's screenshots: it serves the working folder on this machine only and accepts a PNG posted to…Tool · MITA check on the resultthreejs-debug-profilerHow to find why a three.js page is blank, broken or slow: reproduce first, then an ordered checklist for blank canvases (canvas size, WebGL…three.js · MITA check on the resultthreejs-qa-releaseHow to prove a three.js game works the way a player meets it: build, open in a real browser, check console errors and non-blank canvas…three.js · MITA check on the resultinspect-threejs-canvas.mjsOpens a running page in headless Chromium, checks the canvas is not blank, and measures the picture: color entropy, share of the dominant…Tool · MITA check on the resultcheck_evidence.pyChecks that the screenshots and reports a finished game claims really exist on disk, belong to the current run, are not blank and recorded…Tool · MITA check on the resultTest hooks and diagnostics contractTwo objects a page puts on window so a script can take a repeatable picture of it: diagnostics (frame count, renderer draw calls and…Tool · MITA check on the resultvisual.spec.tsA Playwright smoke test (one test, run on a desktop and a phone profile): the canvas is big enough and its pixels vary, so a blank or…Tool · MITA check on the resultvisual-regression.template.tsA Playwright screenshot-baseline template that seeds, sets a named state, freezes, hides debug UI and then compares against a stored…Tool · MITA check on the resultbot-playtest.template.tsA Playwright bot that holds keys on a script and measures whether the game really plays: frames advanced, distance moved, score gained, and…Tool · MITA check on the resultVisual scorecardA ten-category rubric for judging a real-time 3D picture from 0 to 3 (art direction, hero, obstacles, rewards, world, materials, lighting…Skill · MITA check on the resultRender budgets and material kitStarting budgets for a browser 3D scene on desktop and phone (draw calls 300 and 150, triangles 750k and 300k, textures 60 and 40, shadow…Skill · MITA check on the resultEvidence manifest formatA small JSON format that declares which viewport and state pairs one verification pass must capture, with a run id, so old screenshots…Skill · MITA check on the resultaudit.mjsProves a figure's geometry instead of trusting the eye: records each part's true shape as you draw it, ray-casts every overlapping pair to…Tool · MITA check on the resultturn-audit.mjs (3D orbit audit, beta)Checks a 3D figure at every turn angle and in every motion clip: no ordering cycles, no loose groups. Slow by the repo's own account: 15 to…Tool · MITA check on the resultcapture.mjsScreenshots a figure with headless Chrome through the browser's own debugging protocol, with no npm packages: whole card, phone width, a…Tool · MITA check on the resultdrive.mjsRuns a scripted session in headless Chrome: move, click, key, wait-until, run JavaScript in the page, slow motion (for example 0.05x) and…Tool · MITA check on the resultlines.mjsThe line-end check: on a built page, every seam, rule, rib, tick and pointer must end on a stroke, a dot or an outline. It rings the…Tool · MITA check on the resultturn-check.mjsBrowser checks for 3D figures: fidelity against the kit's own builders, a z-buffer order check, pixel pops between tiny angle steps, line…Tool · MITA check on the resultturn-bench.mjsTimes the 3D engine in Node: CPU time per kind of part.Tool · MITA check on the resultevals.jsonFive test prompts with what a good answer contains: a token bucket rate limiter, a connection pool for Next.js docs, a CDN edge cache as a…Skill · MITA check on the resultBlueprint proof harnessA small offline page that loads one kit, lights it with one sun on neutral gray with no post-processing, and stands at four distances…Tool · MITA check on the resultvalidation-report.md templateA fill-in report of what was run and seen; every row needs evidence on disk, and an unobserved frame is never written up as passing.Skill · MITA check on the resultVisual review promptsA list of judgment prompts for any rendered 3D view, each with its cheapest check, written as conditions and not as a score: a blank…Skill · MITA check on the resultFrame and interaction inspectionWhich captures a scene owes (overview, close-ups, each important interaction) and what to check on each one, looking at the rendered result…Skill · MITA check on the resultcapture.pyServes a built scene from a local port, opens it in headless Chromium, visits its named views, clicks controls you name and writes PNGs and…Tool · MITA check on the resultcapture_view_quality.pyMeasures whether a captured frame is usable at all: near-black, filled by a wall, or flat. Used by capture.py's --expect-usable.Tool · MITA check on the resultmanifest_contract.pyChecks the catalog manifest is one the helpers support before any record path is read.Tool · MITA check on the resultdirection.schema.jsonJSON Schema for one kind of catalog file (direction): required fields id, summary. Structural only; the repo's validate.py adds the checks…Skill · MITA check on the resultevidence-event.schema.jsonJSON Schema for one kind of catalog file (evidence event): required fields schema_version, event_id, change_id, timestamp, event_type…Skill · MITA check on the resultknowledge.schema.jsonJSON Schema for one kind of catalog file (reusable knowledge): required fields schema_version, id, revision, status, record_kind, title…Skill · MITA check on the resultrecipe.schema.jsonJSON Schema for one kind of catalog file (recipe): required fields schema_version, id, revision, status, record_kind, title, aliases…Skill · MITA check on the resultsource.schema.jsonJSON Schema for one kind of catalog file (source): required fields id, url, title, accessed_at, locator, scope. Structural only; the repo's…Skill · MITA check on the resultblueprint_validation.pyChecks that a blueprint record, its module and its proof captures agree. Maintainer tooling for this repo; not part of the installed skill.Tool · MITA check on the resultbuild-index.pyRegenerates the human-readable catalog pages and the coverage summary from the records; --check fails if they are stale. Maintainer tooling…Tool · MITA check on the resultcatalog_validation.pyThe catalog contract checks used by validate.py. Maintainer tooling for this repo; not part of the installed skill.Tool · MITA check on the resultcheck-docs.pyChecks links and JSON examples in the repo's Markdown. Maintainer tooling for this repo; not part of the installed skill.Tool · MITA check on the resultcheck-retrieval.pyRuns 249 authored search cases against search.py and reports which known intents find their record. Maintainer tooling for this repo; not…Tool · MITA check on the resultevidence-log.pyAppends a contract-shaped evidence event and a record snapshot to a change log. Maintainer tooling for this repo; not part of the installed…Tool · MITA check on the resultevidence_log_events.pyBuilds the event objects and snapshot paths for evidence-log.py. Maintainer tooling for this repo; not part of the installed skill.Tool · MITA check on the resultevidence_validation.pyChecks evidence links and observations for validate.py without certifying that they are true. Maintainer tooling for this repo; not part of…Tool · MITA check on the resultkit-proof.pyTurns one blueprint record into four real captures, a proof log with a hash per picture, and an evidence event. Maintainer tooling for this…Tool · MITA check on the resultkit_proof_harness.pyAssembles the offline proof page for kit-proof.py with a vendored three: no bundler, no network, no install. Maintainer tooling for this…Tool · MITA check on the resultmigrate-catalog.pyPreviews or applies the one-file-per-record layout while keeping content and search results the same. Maintainer tooling for this repo; not…Tool · MITA check on the resultpackage.pyBuilds repeatable ZIPs of the skill and the Codex plugin; never installs or publishes. Maintainer tooling for this repo; not part of the…Tool · MITA check on the resultshowcase.pyRenders the 21 showcase stills, one browser at a time, resumable, inside a time budget. Maintainer tooling for this repo; not part of the…Tool · MITA check on the resultvalidate.pyValidates the whole catalog and the public evidence with the standard library: schemas, cross-references, content hashes and proof links…Tool · MITA check on the result