after-effects

Q: How do I install after-effects?

Run npx skills add https://github.com/aedev-tools/adobe-agent-skills --skill after-effects in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/after-effects/ (personal) or .claude/skills/after-effects/ (project).

Q: Which AI agents can use after-effects?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Q: Is after-effects safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Q: Who maintains after-effects?

It is published by aedev-tools in aedev-tools/adobe-agent-skills. It has 660 recorded installs.

by aedev-toolsAI & Agents

Automate Adobe After Effects via ExtendScript. Use when the user asks to create, modify, or query anything in an After Effects project — layers, keyframes, expressions, effects, compositions, assets, rendering, batch operations. Generates and executes JSX ExtendScript via osascript on macOS.

Installs: 660
Last 24h: —
Trending rank: —
Security: Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/aedev-tools/adobe-agent-skills --skill after-effects

01
Install
Run the command in your project. The CLI asks which agents to install for.
02
Describe the task
Ask your agent for something this skill covers. It loads after-effects automatically when relevant.
03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Overview

This skill automates After Effects by generating ExtendScript (.jsx) and executing it via osascript. It reads project state through query scripts, uses rule files for domain knowledge, and wraps all mutations in undo groups.

First-Time Setup

Run scripts/runner.sh with any query script to detect the AE version
If multiple AE versions are installed, the user must choose one — runner.sh will prompt
Ensure AE Preferences > Scripting & Expressions > "Allow Scripts to Write Files and Access Network" is enabled

Workflow

For every user request:

Step 1: Gather context (auto-run, no confirmation needed)

Use --background for all query scripts — this skips ae.activate() so AE doesn't steal focus:

bash scripts/runner.sh --background scripts/active-state.jsx

Then read /tmp/ae-assistant-result.json for active comp, selected layers, CTI.

If this is the first interaction or the project context is unknown, also run:

bash scripts/runner.sh --background scripts/project-overview.jsx

This returns a summary by default: folder tree with counts, all comps listed, footage grouped by file type. NOT every individual file.

To drill into a specific folder:

bash scripts/runner.sh --background scripts/project-overview.jsx '{"mode": "folder", "folderName": "Images"}'

Only use full mode when you actually need every item listed:

bash scripts/runner.sh --background scripts/project-overview.jsx '{"mode": "full"}'

Step 2: Drill down if needed (auto-run)

If the task targets a specific comp:

bash scripts/runner.sh --background scripts/comp-detail.jsx '{"compName": "Comp Name"}'

If the task targets specific layers:

bash scripts/runner.sh --background scripts/layer-detail.jsx '{"layerNames": ["Layer 1", "Layer 2"]}'

Omit compName to use the active comp. Omit layerNames to use selected layers.

Additional query scripts

Expression errors — scan for broken expressions:

bash scripts/runner.sh --background scripts/expression-errors.jsx
bash scripts/runner.sh --background scripts/expression-errors.jsx '{"compName": "Main Comp"}'

Font inventory — list all fonts used across the project:

bash scripts/runner.sh --background scripts/font-inventory.jsx

Project audit — comprehensive health check (unused footage, missing files, expression errors, duplicate solids, font issues, empty folders):

bash scripts/runner.sh --background scripts/project-audit.jsx
bash scripts/runner.sh --background scripts/project-audit.jsx '{"checks": ["unused", "missing", "expressions"]}'

Step 3: Load domain knowledge

Read the relevant rule file from rules/. Always read rules/extendscript-fundamentals.md — it contains ES3 constraints that apply to every generated script.

Task involves	Load rule file
Layers (create, move, parent, duplicate)	rules/layer-manipulation.md
Keyframes, animation, easing	rules/keyframes-animation.md
Expressions	rules/expressions.md
Compositions (create, precompose, nest)	rules/composition-management.md
Effects and parameters	rules/effects.md
Import, footage, assets	rules/assets-footage.md
Render queue, export	rules/rendering.md
Bulk/batch operations	rules/batch-operations.md
Version-specific features	references/ae-api-versions.md

Step 4: Generate the action script

CRITICAL: Resolve the skill's real path first

Before writing or executing any action script, resolve the skill's real (non-symlinked) path. ExtendScript #include cannot follow symlinks, so you MUST use the real filesystem path.

Run this once at the start of each session:

SKILL_SCRIPTS="$(readlink -f ~/.claude/skills/after-effects-assistant/scripts 2>/dev/null || readlink ~/.claude/skills/after-effects-assistant/scripts)"
echo "$SKILL_SCRIPTS"

Use the resolved path ($SKILL_SCRIPTS) for all subsequent Write and Bash commands in this session.

Why this matters:

~/.claude/skills/ is typically a symlink — ExtendScript #include fails through symlinks
Writing to the real scripts/ directory lets #include "lib/json2.jsx" resolve correctly
The resolved path changes per machine, so never hardcode it

Every generated script MUST follow this template:

#include "lib/json2.jsx"
#include "lib/utils.jsx"

(function() {
    app.beginUndoGroup("AE Assistant: <action description>");
    try {
        var args = readArgs();
        var comp = getActiveComp();
        if (!comp) return;

        // ... action code ...

        writeResult({ success: true, message: "<what was done>" });
    } catch (e) {
        try { writeResult({ error: e.toString(), line: e.line, fileName: e.fileName }); }
        catch(e2) { writeError(e.toString(), "line:" + e.line); }
    } finally {
        app.endUndoGroup();
    }
})();

utils.jsx helpers available for generated scripts

Function	Purpose
`writeResult(obj)`	Write JSON result to `/tmp/ae-assistant-result.json`
`writeError(msg, detail)`	Last-resort error capture when JSON.stringify fails
`readArgs()`	Read args from `/tmp/ae-assistant-args.json`
`getLayerType(layer)`	Returns type string: "shape", "text", "null", "precomp", etc.
`getBlendModeName(mode)`	BlendingMode enum → string name
`getActiveComp()`	Returns active comp or writes error and returns null
`getSelectedOrAllLayers(comp)`	Selected layers array, or all layers if none selected
`hexToRGB(hex)`	`"#ff0000"` → `[1, 0, 0]`
`getCompByName(name)`	Find comp in project items by name
`walkProperties(group, leafFn, path)`	Recursive property tree walker — calls `leafFn(prop, path)` on leaves
`bubbleSort(arr, compareFn)`	ES3-compatible in-place sort
`framesToSeconds(frames, comp)`	Frame count → seconds via `comp.frameDuration`
`appendLog(message)`	Append to `~/.ae-assistant-extendscript.log`

Write the script using the Write tool, then execute with a short bash command:

Use the Write tool to write the script to $SKILL_SCRIPTS/ae-action.jsx (the resolved real path)
Execute it with bash:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/ae-action.jsx"

IMPORTANT: Do NOT use cat > file << 'SCRIPT' heredocs — they put the entire script in the bash command, cluttering the permission prompt. Always use the Write tool for the script content, then a short bash command to run it.

Step 5: Execute or confirm

Auto-run (no confirmation needed):

All read-only queries (active-state, project-overview, comp-detail, layer-detail, expression-errors, font-inventory, project-audit)
Non-destructive additions: adding a keyframe, adding an effect, creating a layer, creating a comp

Confirm before running (show the script and ask the user):

Deleting layers or comps
Removing keyframes
Replacing footage
Clearing expressions
Render queue operations
Project cleanup (removing unused items, consolidating solids)
Any operation the user might not expect

Built-in action scripts

Before generating a custom ae-action.jsx, check if a built-in script already handles the task. These are permanent, tested scripts with args-based behavior:

True Comp Duplicator — deep-clone a comp with independent sub-comps (confirm before running):

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/true-comp-duplicator.jsx" '{"compName": "Main Comp", "suffix": " COPY"}'

Font Replace — find and replace fonts across the project. Always dryRun first:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/font-replace.jsx" '{"find": "Helvetica", "replace": "Inter-Regular", "dryRun": true}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/font-replace.jsx" '{"find": "Helvetica", "replace": "Inter-Regular"}'

Project Cleanup — remove unused footage, consolidate duplicate solids, remove empty folders. Always dryRun first:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/project-cleanup.jsx" '{"dryRun": true}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/project-cleanup.jsx"

Batch Rename — rename layers, comps, or project items in bulk:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/batch-rename.jsx" '{"target": "layers", "mode": "find-replace", "find": "Layer", "replace": "Element"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/batch-rename.jsx" '{"target": "layers", "mode": "prefix", "prefix": "BG_"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/batch-rename.jsx" '{"target": "layers", "mode": "sequence", "base": "Card", "start": 1}'

Layer Stagger — offset selected layers in time for cascade animations:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/layer-stagger.jsx" '{"offset": 0.1, "unit": "seconds", "direction": "forward"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/layer-stagger.jsx" '{"offset": 2, "unit": "frames"}'

Expression Replace — find/replace text in expressions project-wide. Always dryRun first:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/expression-replace.jsx" '{"find": "comp(\"Old\")", "replace": "comp(\"New\")", "dryRun": true}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/expression-replace.jsx" '{"find": "comp(\"Old\")", "replace": "comp(\"New\")"}'

Organize Project — auto-sort project panel items into folders by type:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/organize-project.jsx" '{"structure": "by-type"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/organize-project.jsx" '{"structure": "by-extension"}'

Batch Comp Settings — change fps, resolution, duration across multiple comps:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/batch-comp-settings.jsx" '{"scope": "all", "fps": 25}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/batch-comp-settings.jsx" '{"compNames": ["Comp 1", "Comp 2"], "width": 3840, "height": 2160}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/batch-comp-settings.jsx" '{"scope": "nested", "fps": 30, "duration": 10}'

Easing Presets — apply professional easing or bounce/elastic expressions:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/easing-presets.jsx" '{"preset": "smooth"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/easing-presets.jsx" '{"preset": "snappy"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/easing-presets.jsx" '{"preset": "bounce"}'

Anchor Point Mover — reposition anchor point with visual position compensation:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/anchor-point-mover.jsx" '{"position": "center"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/anchor-point-mover.jsx" '{"position": "bottom-left"}'

Reverse Keyframes — reverse animation on selected properties:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/reverse-keyframes.jsx"

Select Layers — select layers by type, label, attribute, or name:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/select-layers.jsx" '{"type": "text"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/select-layers.jsx" '{"hasExpressions": true}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/select-layers.jsx" '{"nameContains": "BG"}'

Layer Sort — reorder layers in timeline by name, position, in-point, type, or label:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/layer-sort.jsx" '{"sortBy": "name", "order": "ascending"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/layer-sort.jsx" '{"sortBy": "position-y"}'

Smart Precompose — precompose with auto-trimmed duration:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/smart-precompose.jsx" '{"name": "My Precomp", "trimToContent": true}'

Copy Ease — copy easing from one keyframe and paste to others:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/copy-ease.jsx" '{"mode": "both"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/copy-ease.jsx" '{"sourceLayer": "Logo", "sourceProperty": "Position", "sourceKeyIndex": 2}'

Relink Footage — batch-relink missing footage from search directories. Always dryRun first:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/relink-footage.jsx" '{"searchPaths": ["/Volumes/Projects/footage"], "dryRun": true}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/relink-footage.jsx" '{"searchPaths": ["/Volumes/Projects/footage"]}'

SRT Import — create timed subtitle text layers from an SRT file:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/srt-import.jsx" '{"srtPath": "/path/to/subs.srt", "fontSize": 48}'

Text Export/Import — export all text to CSV, edit externally, reimport:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/text-export-import.jsx" '{"mode": "export", "csvPath": "/tmp/text.csv"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/text-export-import.jsx" '{"mode": "import", "csvPath": "/tmp/text.csv"}'

Batch Expression — apply, remove, enable, or disable expressions in bulk:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/batch-expression.jsx" '{"property": "opacity", "expression": "wiggle(2, 10)", "mode": "apply"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/batch-expression.jsx" '{"mode": "remove"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/batch-expression.jsx" '{"mode": "disable"}'

Randomize Properties — apply random values to transform properties:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/randomize-properties.jsx" '{"property": "rotation", "min": -15, "max": 15}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/randomize-properties.jsx" '{"property": "position", "minX": 0, "maxX": 1920, "minY": 0, "maxY": 1080}'

Un-PreCompose — extract layers from a precomp back into parent (confirm before running):

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/un-precompose.jsx" '{"precompLayerName": "Precomp 1"}'

Comp from CSV — generate comp variations from spreadsheet data (confirm before running):

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/comp-from-csv.jsx" '{"templateComp": "Lower Third", "csvPath": "/path/data.csv"}'

Render Queue Batch — add multiple comps to render queue (confirm before running):

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/render-queue-batch.jsx" '{"compNames": ["Final_16x9", "Final_9x16"], "outputPath": "~/Desktop/renders/"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/render-queue-batch.jsx" '{"scope": "folder", "folderName": "Finals"}'

Explode Shape Layer — split shape groups into individual layers:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/explode-shape-layer.jsx" '{"layerName": "AI Import"}'

Incremental Save — save project with auto-incrementing version number:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/incremental-save.jsx" '{"comment": "before revisions"}'

Purge Cache — clear memory caches, disk cache, and free resources. dryRun to check size first:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/purge-cache.jsx" '{"dryRun": true}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/purge-cache.jsx"
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/purge-cache.jsx" '{"memory": true, "disk": false}'

Trim Comp to Content — trim/extend comp duration to exactly fit layer content:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/trim-comp-to-content.jsx"
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/trim-comp-to-content.jsx" '{"padding": 0.5}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/trim-comp-to-content.jsx" '{"recursive": true}'

Null from Layers — create a null at each selected layer's position, auto-parent:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/null-from-layers.jsx"
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/null-from-layers.jsx" '{"naming": "custom", "prefix": "Driver"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/null-from-layers.jsx" '{"position": "comp-center"}'

Fit to Comp — scale selected layers to fit/fill comp dimensions:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/fit-to-comp.jsx" '{"mode": "fit"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/fit-to-comp.jsx" '{"mode": "fill"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/fit-to-comp.jsx" '{"mode": "stretch"}'

Label Layers — batch-set label colors on layers by type, name, or selection:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/label-layers.jsx" '{"label": 3, "target": "selected"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/label-layers.jsx" '{"label": 1, "target": "text"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/label-layers.jsx" '{"label": 5, "target": "all", "nameContains": "BG"}'

Blend Mode Set — set blending mode on selected layers:

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/blend-mode-set.jsx" '{"mode": "SCREEN"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/blend-mode-set.jsx" '{"mode": "MULTIPLY"}'
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/blend-mode-set.jsx" '{"mode": "ADD"}'

Split Layer — split selected layers at CTI (confirm before running — modifies layer timing):

bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/split-layer.jsx"
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/split-layer.jsx" '{"time": 2.5}'

Step 6: Execute and read result

# Execute the action script (already written to $SKILL_SCRIPTS/ae-action.jsx in Step 4)
bash "$SKILL_SCRIPTS/runner.sh" "$SKILL_SCRIPTS/ae-action.jsx" '{"arg1": "value1"}'

Read /tmp/ae-assistant-result.json for the result.

Debugging failures

If a script fails, check these in order:

~/.ae-assistant-log — runner.sh logs every execution, args, results, and errors here
/tmp/ae-assistant-error.txt — JXA-level errors (AE not responding, DoScriptFile failure)
~/.ae-assistant-extendscript.log — ExtendScript-level logs from appendLog() in utils.jsx
AE Preferences — Ensure "Allow Scripts to Write Files and Access Network" is enabled

When an error occurs, read ~/.ae-assistant-log to understand what happened, fix the script, and retry.

MUST

ALWAYS wrap mutations in app.beginUndoGroup() / app.endUndoGroup()
ALWAYS use matchNames for property access, not display names (display names are localized)
ALWAYS use 1-based indexing for layers and project items
ALWAYS write action scripts to $SKILL_SCRIPTS/ae-action.jsx (the resolved real path, NOT /tmp/)
ALWAYS use relative #include "lib/json2.jsx" and #include "lib/utils.jsx" (NOT absolute paths)
ALWAYS wrap in an IIFE to avoid global scope pollution
ALWAYS use var, never let or const (ES3)
ALWAYS write results to /tmp/ae-assistant-result.json via writeResult()
ALWAYS use getActiveComp() to get the active comp (handles the null/CompItem check and writes error)
ALWAYS use --background flag for query scripts to avoid focus-steal

FORBIDDEN

NEVER use ES5+ syntax: let, const, arrow functions, template literals, destructuring
NEVER use Array.map, Array.filter, Array.reduce, Array.forEach (not in ES3)
NEVER use JSON.parse or JSON.stringify without including json2.jsx
NEVER write action scripts to /tmp/ — ExtendScript #include can't resolve paths from there
NEVER use absolute paths in #include — they break through symlinks
NEVER hardcode layer indices — use names, selection, or iteration
NEVER run destructive operations without user confirmation
NEVER assume a comp is active without checking
NEVER use cat > file << 'SCRIPT' heredocs to write scripts — use the Write tool instead, then execute with a short bash command

FAQ

What does the after-effects skill do?

How do I install after-effects?

Run npx skills add https://github.com/aedev-tools/adobe-agent-skills --skill after-effects in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/after-effects/ (personal) or .claude/skills/after-effects/ (project).

Which AI agents can use after-effects?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is after-effects safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains after-effects?

It is published by aedev-tools in aedev-tools/adobe-agent-skills. It has 660 recorded installs.

Source

aedev-tools/adobe-agent-skills $View on skills.sh

Works with

Claude CodeCodexCursorGitHub CopilotGemini CLIWindsurfClineOpenCodeRoo CodeGooseAmpKiro

Files 53 · 382.5 KB

SKILL.md20.3 KB
references/ae-api-versions.md4.8 KB
rules/assets-footage.md12.7 KB
rules/batch-operations.md18.5 KB
rules/composition-management.md12.4 KB
rules/effects.md14.4 KB
rules/expressions.md18.4 KB
rules/extendscript-fundamentals.md25.1 KB
rules/keyframes-animation.md15.8 KB
rules/layer-manipulation.md13.0 KB
rules/rendering.md15.8 KB
scripts/active-state.jsx1.4 KB
scripts/anchor-point-mover.jsx5.3 KB
scripts/batch-comp-settings.jsx5.9 KB
scripts/batch-expression.jsx5.4 KB
scripts/batch-rename.jsx5.2 KB
scripts/blend-mode-set.jsx2.0 KB
scripts/comp-detail.jsx3.0 KB
scripts/comp-from-csv.jsx5.3 KB
scripts/copy-ease.jsx7.1 KB
scripts/easing-presets.jsx7.7 KB
scripts/explode-shape-layer.jsx3.8 KB
scripts/expression-errors.jsx3.1 KB
scripts/expression-replace.jsx4.0 KB

+29 more files

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs

after-effects

Install

Install

Describe the task

Review the result

SKILL.md

Overview

First-Time Setup

Workflow

Step 1: Gather context (auto-run, no confirmation needed)

Step 2: Drill down if needed (auto-run)

Additional query scripts

Step 3: Load domain knowledge

Step 4: Generate the action script

utils.jsx helpers available for generated scripts

Step 5: Execute or confirm

Built-in action scripts

Step 6: Execute and read result

Debugging failures

MUST

FORBIDDEN

FAQ

Popular ai & agents skills

google-agents-cli-publish

google-agents-cli-eval

skill-creator

codex-pet

full-output-enforcement

executing-plans