PowerPoint Reader and Builder
TokenRhythm/opensquilla
Reads, edits in place, or creates PowerPoint .pptx decks, picking one of three paths based on what tools and files are available.
A skill your agent uses when animating characters or objects in Blender through Python, a bouncing ball, walk or run cycle, jump, acting shot, lip sync, eye darts or facial animation, blocking in…
$ npx skills add scenario-labs/skills --skill scenario-blender-animation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install scenario-labs/skills scenario-blender-animation --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/scenario-labs/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/dcc/blender/scenario-blender-animation .claude/skills/scenario-blender-animation && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "scenario-blender-animation" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/blender/scenario-blender-animation into .claude/skills/scenario-blender-animation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-blender-animation", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/scenario-labs/skills/tree/main/skills/dcc/blender/scenario-blender-animationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add scenario-labs/skills --skill scenario-blender-animation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install scenario-labs/skills scenario-blender-animation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scenario-labs/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/dcc/blender/scenario-blender-animation .agents/skills/scenario-blender-animation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "scenario-blender-animation" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/blender/scenario-blender-animation into .agents/skills/scenario-blender-animation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-blender-animation", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add scenario-labs/skills --skill scenario-blender-animation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install scenario-labs/skills scenario-blender-animation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scenario-labs/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/dcc/blender/scenario-blender-animation .cursor/skills/scenario-blender-animation && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "scenario-blender-animation" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/blender/scenario-blender-animation into .cursor/skills/scenario-blender-animation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-blender-animation", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/scenario-labs/skills.git --path skills/dcc/blender/scenario-blender-animation--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add scenario-labs/skills --skill scenario-blender-animation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install scenario-labs/skills scenario-blender-animation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scenario-labs/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/dcc/blender/scenario-blender-animation .gemini/skills/scenario-blender-animation && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "scenario-blender-animation" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/blender/scenario-blender-animation into .gemini/skills/scenario-blender-animation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-blender-animation", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install scenario-labs/skills scenario-blender-animationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add scenario-labs/skills --skill scenario-blender-animation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/scenario-labs/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/dcc/blender/scenario-blender-animation .github/skills/scenario-blender-animation && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "scenario-blender-animation" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/blender/scenario-blender-animation into .github/skills/scenario-blender-animation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-blender-animation", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add scenario-labs/skills --skill scenario-blender-animation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install scenario-labs/skills scenario-blender-animation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scenario-labs/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/dcc/blender/scenario-blender-animation .opencode/skills/scenario-blender-animation && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "scenario-blender-animation" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/blender/scenario-blender-animation into .opencode/skills/scenario-blender-animation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-blender-animation", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
scenario-blender-animationA skill your agent uses when animating characters or objects in Blender through Python, a bouncing ball, walk or run cycle, jump, acting shot, lip sync, eye darts or facial animation, blocking in…
Scenario Blender Animation is an agent skill from scenario-labs/skills. Use when animating characters or objects in Blender through Python, a bouncing ball, walk or run cycle, jump, acting shot, lip sync, eye darts or facial animation, blocking in stepped keys, splining, polish, timing and spacing, arcs, overlap, squash and stretch, graph editor handles, slotted actions or NLA layers, staging a playblast, or when animation looks floaty, stiff, slides, pops, chatters, the subject is too small in frame, or a knee pops and needs an expert review.
Its SKILL.md is about 5.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `references/critique.md`, `references/expert-notes.md` and `references/procedures.md`).
It sits in Documents & Office, covering Slides and decks. It works with Blender and Python. The repository describes itself as: Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through… The licence is MIT.
8 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit f6f8ab7. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
npxFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Scenario Blender Animation loads about 5.1k tokens when it runs, and up to ~32k if it reads all its reference files. Until then it costs about 126 tokens; SKILL.md has 2,054 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from scenario-labs/skills at commit f6f8ab7, republished under its MIT licence (© scenario-labs). 2,054 words, ~5,072 tokens.
.claude/skills/scenario-blender-animation/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.Expert animation means every frame on screen is a choice: key poses the audience reads, holds and snaps placed by hand, spacing designed, arcs checked. The Blender Studio stance is to block stepped, spline late and in parts, and judge from the shot camera at real speed. An agent cannot scrub, so it measures instead: per-frame positions, spacing charts, arc checks, framing, an onion-skin image, a curve plot, and a playblast it actually looks at. If a sibling skill named here is missing from your available skills, ask the user to install it (npx skills add scenario-labs/skills --skill <name>); unattended, proceed from tool schemas and flag the gap.
REQUIRED BACKGROUND: scenario-blender-expert (execution channel, review loop, 5.2 API changes). Shot planning, cameras and animatics belong to scenario-blender-previs-storyboard; building the rig to scenario-blender-rigging.
Toolkit: scripts/bx_anim.py (keying, blocking-to-spline, curve checks, measurement, staging, playblast light, knee-pop, flip and balance checks, onion-skin and curve images, one-object bouncing_ball; API in procedures.md, tested on 5.2.1) and bx_review.playblast.
| Input | Why it changes the plan | Default when silent |
|---|---|---|
| Medium, fps | Film 24 (Hjalti); games often 30 with fixed hit or release frames (Picaut) | 24 fps |
| Camera | Locked acting shot: judge only through the camera (Rik). Moving, re-framable or gameplay camera: poses work from every direction (Leo Silly-Pelissier, Picaut) | locked camera |
| Style | Stepped on twos and never splined (Sprite Fright shots, Rik) vs splined; stylized vs naturalistic (Leo) | splined, stylized |
| Rig | Control names, IK/FK, rotation modes. Generated Rigify [verified]: torso, hips, chest, head, foot_ik.L, upper_arm_fk.L, jaw_master; ["IK_FK"] on upper_arm_parent.L (0 IK, 1 FK); legs have IK_Stretch 1.0; rest legs are 99.6% straight; main controls QUATERNION | FK arms when arcs matter, IK when hands touch things (Joey, Tony Garcia) |
| Named object | A brief that names the animated object expects every channel on it | one object, bouncing_ball(obj=...) |
| Audio, transcript | Beats, accents, phoneme preparation | beats from the brief |
| Reference | Timing and beats, never a trace (Hjalti) | none: write a beat list |
| Budget | Rik: about 3 s a week in big studios, 5 to 6 s on his acting shot; Flow: 2 s per animator per day | state what the budget buys |
audio_envelope + accent_frames; hit a pose just before its audio peak (Alex). Start mid-action (Rik). GATE: beat table written.staging_report(subject, frames) with the real render size: subject height, how much of the frame the action covers, entry, final pose margin. Playblast look: playblast_lighting(key_dir=(0, 0, 1)) (overhead key converted to Workbench's camera space: the shadow sits under the subject, the gap is its height, contact is where they meet), floor_slab, rotation_texture on anything that rolls. GATE: flags empty; shadow_frames visible in the air and touching at a contact; camera stills looked at.world_pose (rig axes are arbitrary), key with key_pose(..., keytype='EXTREME'), CONSTANT, all main controls. GATE: pose strip onion_skin(frames=keys, spread=...) shows clear silhouettes and contrast; balance_report margin >= 0 on held poses.breakdown at the middle frame with per-part factors (COG dips, extremities delayed at 0.2 to 0.3, directed part favored late; after a take-off the body is ballistic, about 2/3 of the rise in 3 of 7 frames, and the feet must follow); ease_inbetweens for 20/80 (Pablo); overshoots and settles; overlap offsets; key types as a confidence map (Hjalti). GATE: stepped playblast approved; notes on intent stopped (Leo: none after Block B).blocking_to_spline(rig, body_bones, transition=3, interpolate={...}): big moves and continuous contacts in interpolate; VECTOR on foot contacts and take-offs. GATE: hold_drift < 1e-5, overshoots only wanted settles, face still CONSTANT, motion_report without unintended constant spacing, ballistic_fit on the airborne COG with g_ratio near 1.0 and a small residual, limb_extension never above 1.0.offset_keys 1 to 2 frames per chain link (Dillon), head lag 2 to 3 frames in cycles (Joey), contacts that slide rather than glue (Rik). Fingers: little overlap, no bounce. GATE: arcs clean in camera pixels (to_camera(..., res=(w, h)), motion_report(dims=2)).transitions meets those counts; accents clearly fewer than syllables.foot_slip under 1 mm, lowest_point for penetration, rotation_flips empty (fix_rotation_flips), limb_extension under 0.99 wherever the leg should stay bent, smears 1 frame (Pablo), burst spacing only now (Raymond), subdivision on. GATE: critique.md rubric passes on the final playblast, onion skin and graph image.Variants. Bouncing ball (P16, P18): bouncing_ball(obj=ANIM_ball, first_apex=-3, fit=False, ...) keys ONE object: exact parabolas under one gravity through whole-frame contacts, odd or even flights so small hops keep their height, squash on the contact frame and stretch along the velocity through a world-aligned squash modifier (the roll is never twisted), roll = distance / radius, constant-deceleration roll, a 6-frame hold. first_apex before start throws it in from off-screen. Weight mapping is [added]: tune by render. Walk (Joey, 30 fps): contact 0, down 5, passing 10, up 15, 40-frame cycle; heel curve straight during contact, root linear with REPEAT_OFFSET (P5). Jump: tests/code/blender-animation/test_rigify_jump.py is the worked example (Rigify human, blocking to spline).
| Item | Value | Source |
|---|---|---|
| Snappy pose change | 2 to 3 frames after the hold | Rik |
| Aggressive change | 4 frames instead of 8 | Alex |
| Hold to read an idea | 6 frames | Alex |
| Settle | 1 to 2 frames, 4 soft | Alex |
| Reaction after stimulus | about 6 frames | Rik |
| Eye dart / brow change | 1 to 2 / 3 to 10 frames | Rik |
| Ease rule | 80% of the remaining way per in-between (slow-in); mirror 20% | Pablo |
| Smear | 1 frame, sometimes 2 | Pablo |
| Micro-anticipation | last 1 to 2 frames before hit or release pushed to an extreme | Picaut |
| Head lag in a cycle / foot offset | 2 to 3 frames / 1 frame | Joey / Rik |
| Real gravity at 24 fps | acceleration 0.01703 m/frame^2; a quadratic fit's leading coefficient is half (-0.00852). gravity() | physics [added] |
| Subject size in frame | 12% of frame height minimum, 15% or more for a single subject | [added] E3: both runs measured 10% |
| IK leg extension | under 0.99 of full length while meant bent; above 1.0 = IK stretch | [added] |
| Pinwheel on a rolling object | roll per frame under 360 / sectors degrees | [added] wagon-wheel |
Measurable: slot named after the character; key poses CONSTANT and typed before approval; hold_drift ~0; overshoots only on settles; foot_slip < 1 mm; lowest_point never below the floor (sample sub-frames); transitions for darts, brows, snaps, plosives; ballistic_fit g_ratio near 1 at real scale; motion_report: sharp turns only at contacts, no arc wobble or start-stops inside a move; staging_report flags empty with shadow frames visible; limb_extension, rotation_flips, balance_report as above; roll_aliasing ok.
Visual (open every image): pose strip, onion skin through the shot camera with tracks, graph_image, playblast frame sheets (subject size, entry, shadow gap closing at contacts, spin readable), orbit views when the camera is not locked.
| Mistake | What it looks like | Fix |
|---|---|---|
| Whole blocking to Bezier | "floaty spaghetti" | blocking_to_spline with pillars, body only |
| Pillar on a continuous contact | body brakes before impact | put that frame in interpolate; VECTOR on the foot |
| AUTO handles on a hold | hold drifts past the pose | AUTO_CLAMPED; AUTO only for a settle |
| Heel curve eased during contact | foot slides (5.8 cm per step measured) | VECTOR or zero-length FREE handles |
| Jaw open on every syllable | chattering mouth | big opens on accent_frames only |
| BOUNCE easing for a ball | no squash frame ever shows | bouncing_ball or keyed whole-frame contacts |
| Squash on a parent that also aims | pattern twists on stretch frames (55 degrees measured on the old rig) | squash_modifier (world axes) on the object itself |
| Flights rounded to even frames | hops lose or gain height, gravity changes per bounce (0.98 to 1.31 measured) | whole-frame contacts, odd flights allowed, one gravity |
| Framing the whole set | subject 10% of frame, top 40% empty | move in or shorten the travel until staging_report is clean |
display.light_direction read as world | shadow hidden behind the subject (0 px) | playblast_lighting(key_dir=...) |
| Arcs checked in normalized camera coords | false sharp turns at apexes (aspect squeezes x) | to_camera(..., res=(w, h)) |
| Legs straight at stand or push-off | IK stretch lengthens the leg (18% in the first jump draft) | soft knees, feet breakdown after take-off, VECTOR take-off |
action.fcurves is gone: channelbags via bpy_extras.anim_utils (bx_anim.channelbag). Assigning an action animates only if a slot matches; otherwise set ad.action_slot.layers.new raises); layer with the NLA plus an ADD or COMBINE action (push_layer).keyframe_points.insert gives BEZIER AUTO_CLAMPED; a Keyframe reference dies at the next insert on that curve.anim.keyframe_insert fails; pose.breakdown and pose.blend_to_neighbor need explicit prev_frame/next_frame; render.opengl refuses, so playblasts are Workbench renders.scene.display.light_direction is camera-relative; matrix_world is stale until view_layer.update(), so convert after it.modifiers["X"].properties.inputs.Socket_n.value.render.ffmpeg.audio_codec = 'AAC'.references/expert-notes.md: principles, numbers and disagreements by expert, with timestamps; load when choosing between approaches or writing notes.references/procedures.md: full tested code for every procedure (setup, blocking, spline, walk, lip sync, facial timing, contact pin, slots, layers, pose library, playblast, measurement, ball, staging, knee/flip/balance); load before writing code.references/critique.md: the review rubric per stage, staging thresholds and their calibration, how these animators phrase notes; load at every gate.references/sources.md: the 14 source videos, what each is best for, best timestamps.© scenario-labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 5 other files (scripts, references) in skills/dcc/blender/scenario-blender-animation of scenario-labs/skills.
Open the folder on GitHubat commit f6f8ab7
Scenario Blender Animation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Scenario Blender Animation this skillscenario-labs/skills | 946 | — | ~5.1k | Automated safety check: Pass | MIT | |
| PowerPoint Reader and BuilderTokenRhythm/opensquilla | 7.1k | — | ~3.8k | Automated safety check: Notes | Apache-2.0 | |
| PPTXAgentTeam-TaichuAI/ScienceClaw | 671 | — | ~2.5k | Automated safety check: Pass | Proprietary | |
| Native Enhance PPTXbyungjunjang/slide-master | 280 | — | ~330 | Automated safety check: Pass | MIT | |
| Office PPTXsingula-ai/alego | 109 | 1 repos | ~1.7k | Automated safety check: Pass | MIT | |
| PresentationsPinelliaChill/Operant | 243 | — | ~195 | Automated safety check: Pass | Custom licence |
TokenRhythm/opensquilla
Reads, edits in place, or creates PowerPoint .pptx decks, picking one of three paths based on what tools and files are available.
AgentTeam-TaichuAI/ScienceClaw
Use this skill any time a .pptx file is involved — as input, output, or both.
byungjunjang/slide-master
Enhance a finished PPTX while keeping visible content and layout stable.
singula-ai/alego
Create, read, edit, and check PowerPoint presentations (.pptx), including slide text, tables, images, and charts.
PinelliaChill/Operant
Create a PowerPoint deck from user content and verify its slide structure.
K-Dense-AI/scientific-agent-skills
Supports local computational pathology research with PathML: slide loading and tiling, preprocessing and QC, h5path storage, multiplex quantification, spatial graphs, and bounded model inference.
scenario-labs/skills
A skill your agent uses when drawing or animating with Grease Pencil in Blender 5.x from Python: 2D or 2.5D illustration, frame-by-frame animation, a cutout or part-based 2D character, strokes with…
scenario-labs/skills
A skill your agent uses when grooming hair or fur in Blender with hair curves, such as a character hairstyle, animal fur, procedural fur in geometry nodes, or hair cards and mesh hair for games.
scenario-labs/skills
A skill your agent uses when lighting, rendering or compositing in Blender: light a character, product or hero shot, interior at dusk or night, three-point or motivated lighting, sun and sky, HDRI…
scenario-labs/skills
A skill your agent uses when creating a ChatGPT pet or Codex pet with Scenario: hatching an animated companion from a text idea, a character, mascot or brand cue, or reference photos and art; making…
scenario-labs/skills
A skill your agent uses when animating characters or scenes in Godot 4.7: AnimationPlayer clips and RESET, AnimationTree state machines and blend spaces built in code, Mixamo or glTF import, loop…
scenario-labs/skills
A skill your agent uses when adding or fixing sound in Godot 4.7: audio buses and effects, volume sliders, 'too many sounds', combat audio with hundreds of enemies, sounds clipping or distorting, 3D…
Categories
A skill your agent uses when animating characters or objects in Blender through Python, a bouncing ball, walk or run cycle, jump, acting shot, lip sync, eye darts or facial animation, blocking in…. Scenario Blender Animation is an agent skill from scenario-labs/skills. Use when animating characters or objects in Blender through Python, a bouncing ball, walk or run cycle, jump, acting shot, lip sync, eye darts or facial animation, blocking in stepped keys, splining, polish, timing and spacing, arcs, overlap, squash and stretch, graph editor handles, slotted actions or NLA layers, staging a playblast, or when animation looks floaty, stiff, slides, pops, chatters, the subject is too small in frame, or a knee pops and needs an expert review.
Scenario Blender Animation fits situations like: animating characters; objects in Blender through Python; A bouncing ball; facial animation.
Run `npx skills add scenario-labs/skills --skill scenario-blender-animation -a claude-code`. Or copy the skill folder (skills/dcc/blender/scenario-blender-animation in scenario-labs/skills) into .claude/skills/scenario-blender-animation in your project. Claude Code loads it when a task matches its description.
Run `npx skills add scenario-labs/skills --skill scenario-blender-animation -a codex`. Or copy the skill folder (skills/dcc/blender/scenario-blender-animation in scenario-labs/skills) into .agents/skills/scenario-blender-animation in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add scenario-labs/skills --skill scenario-blender-animation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scenario-blender-animation, .gemini/skills/scenario-blender-animation, .github/skills/scenario-blender-animation and .opencode/skills/scenario-blender-animation in your project.
Going by SKILL.md and its folder, Scenario Blender Animation needs Python for the scripts in its folder and the command-line tools its instructions call (npx). Our summary lists: Python 3; Node.js.
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Scenario Blender Animation is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.1k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 27k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Scenario Blender Animation: PowerPoint Reader and Builder (TokenRhythm/opensquilla, 7.1k stars), PPTX (AgentTeam-TaichuAI/ScienceClaw, 671 stars), Native Enhance PPTX (byungjunjang/slide-master, 280 stars) and Office PPTX (singula-ai/alego, 109 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
scenario-labs (a GitHub organization) maintains it in scenario-labs/skills, which has 946 GitHub stars. The repository holds 146 skills in this directory. The repository was last updated on October 10, 2026.
Source: scenario-labs/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.