adobe-illustrator-operator
Use when working with Adobe Illustrator files, .ai brand assets, artboards, layers, vector exports, SVG/PDF/PNG rendering, Illustrator scripting…
Skill by TheAngryPit
Chalk Labs
Need help deploying adobe-illustrator-operator?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/theangrypit-adobe-illustrator-operator
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, design
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/adobe-illustrator-operator
What's inside
- Skill name
adobe-illustrator-operator- Description
- Use when working with Adobe Illustrator files, .ai brand assets, artboards, layers, vector exports, SVG/PDF/PNG rendering, Illustrator scripting, Illustrator-to-Penpot 1:1 reconstruction, Flue Illustrator bridges, or computer-use fallback for Adobe UI workflows.
- License
- MIT
- Instructions
- 116 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (6)
- SKILL.md
- openai.yaml · agents/
- file-level-recipes.md · references/
- illustrator-control-map.md · references/
- penpot-1to1-reconstruction.md · references/
- probe_illustrator_asset.py · scripts/
SKILL.md (first lines)
# Adobe Illustrator operator Use this skill to operate Illustrator work safely, starting with the least fragile path that can prove the result. ## Operating rule Do not open or mutate Illustrator by reflex. Pick the lowest-risk lane that satisfies the task. 1. Inspect the asset and requested output. 2. Use file-level tools when the `.ai` file is PDF-compatible and the task is render, contact sheet, preview, page count, or basic extraction. 3. Use Illustrator scripting only when the task needs real Illustrator document state, artboards, layers, paths, swatches, text, or native export behavior. 4. Use Flue only as an optional bridge when installed and reviewed. Treat it as a runtime, not authority. 5. Use browser/computer-use only for UI-only flows, dialogs, plugin installs, visual confirmation, or workflows the scripting lane cannot reach. 6. Never save, close, overwrite, package, relink, or destructive-export unless the user explicitly asks. 7. Verify with a file readback or visual review before claiming completion. ## Lane selection | Task | Default lane | Proof | |---|---|---| | Preview `.ai`, make PNGs, count pages | File-level tools | `file`, `pdfinfo`, rendered output | | Export PDF-compatible `.ai` to PNG/SVG/PDF | File-level tools first | output files plus visual check | | Inspect artboards, layers, swatches, selected objects | Illustrator scripting | JSON from Illustrator runtime | | Native Illustrator export, outline text, package assets | Illustrator scripting | exported file plus readback | | Dialogs, plugins, font UI, manual import screens | Computer-use | screenshot or visible app state | | Experimental bridge automation | Flue optional | smoke test and JSON response | ## Illustrator to Penpot 1:1 reconstruction When the task is to recreate an Illustrator file, brandbook, logo sheet, or layered brand asset in Penpot, Illustrator is the canonical source for both visuals and structure. Read `references/penpot-1to1-reconstruction.md` before acting. Non-negotiable rules: 1. Work one Illustrator document at a time. 2. Snapshot the source file before touching it. 3. Read the full Illustrator artboard and layer tree before exporting or importing. 4. Import or recreate in Illustrator tree order, not by fastest export convenience. 5. Preserve native text as text wherever technically possible. 6. Preserve source names where available. 7. Replace generic imported names with semantic names tied to the source tree. 8. Verify each artboard visually and structurally before advancing. 9. Verify the original Illustrator file stayed unchanged before reporting completion. ## Required first probe For local assets, run the bundled probe before choosing a heavier lane: ```bash python3 <skill>/scripts/probe_illustrator_asset.py /path/to/file.ai ``` The probe reports whether Illustrator appears installed, whether the file is PDF-compatible, page count when available, and which lane is recommended. ## Illustrator scripting lane Use this lane only after confirming Illustrator is installed and the user wants Illustrator-level behavior. On macOS, Illustrator scripting normally runs through AppleScript/JXA calling JavaScript in Illustrator. Keep scripts small and return JSON text. Safe first script goal: - list document name - list artboards - list layer names - do not edit - do not save If the script needs API details, use Adobe Illustrator scripting docs or local app introspection before guessing. Read `references/illustrator-control-map.md` before running scripting or Flue. ## Flue lane Flue can be useful, but it is optional and alpha-quality until locally proven. Use Flue only if all are true: - the user approved using it for this session - `flue` is installed and version is known - Illustrator is installed and open - a read-only smoke test succeeds Do not install `flue`, run `flue setup`, or change agent configs without explicit user approval. ## Computer-use lane Use computer-use or Chrome/browser control when the task depends on UI state that scripting cannot reach. Examples: plugin installation, font upload UI, save/export dialogs, or visual checks inside Illustrator. Before acting through UI: - state the exact intended click or menu action - avoid destructive choices - prefer screenshots before and after - stop if a modal asks for account, license, overwrite, cloud sync, or payment decisions ## File-level fallback Many `.ai` files are PDF-compatible. For brand assets, this is often enough and safer than launching Illustrator. Read `references/file-level-recipes.md` for `pdftocairo`, `pdfinfo`, page rendering, and contact-sheet workflows. ## Completion report Report: - lane used: file-level, Illustrator scripting, Flue, or computer-use - files read or created - whether Illustrator was actually used - strongest proof level - limitations, especially if text/vector editability was not proved Do not say an asset is editable in Illustrator unless Illustrator or a real vector import path proved it.
From TheAngryPit/TheAngrySkills, MIT.
More from TheAngryPit/TheAngrySkills
- 0.570score
openclaw-debugging
TheAngryPit
Use when diagnosing OpenClaw provider, tool-surface, code-mode, streaming, transcript, worker or package-runtime failures.
SkillAFreshness: AClaude Code +9 - 0.570score
openclaw-node-connect
TheAngryPit
Use when explicitly asked to repair one exact OpenClaw browser or native-node connection, including auth, Tailscale routing or pairing.
SkillAFreshness: AClaude Code +9 - 0.570score
model-capability-router
TheAngryPit
Use when the operator explicitly asks for native Codex model or reasoning-effort routing, including an active standing request.
SkillAFreshness: AClaude Code +9 - 0.570score
openclaw-control-ui-e2e
TheAngryPit
Use when changing or proving OpenClaw Control UI behavior with deterministic Gateway fixtures, browser flows, rendered evidence or interaction profiling.
SkillAFreshness: AClaude Code +9 - 0.569score
openclaw-node-inspect-debugger
TheAngryPit
Use when debugging Node.js breakpoints, async hangs, hidden locals, heap retention or CPU hot paths with the inspector.
SkillAFreshness: AClaude Code +9 - 0.569score
openclaw-diagnose-gateway
TheAngryPit
Use when diagnosing OpenClaw Gateway, config, channel, model, SecretRef or listener failures without changing state.
SkillAFreshness: AClaude Code +9 - 0.559score
model-routing-preset-builder
TheAngryPit
Use when the operator explicitly wants to customise the native Codex model-capability-router policy.
SkillAFreshness: AClaude Code +9 - 0.533score
ask-pit
TheAngryPit
Ask which skill or flow fits your situation.
SkillAFreshness: AClaude Code +9 - 0.529score
continuity-handoff
TheAngryPit
Create a compact fresh-task continuity packet that preserves goals, decisions, proof, protected state, and a bounded read-only handle to legacy Codex history.
SkillBFreshness: BClaude Code +9 - 0.479score
karpathy-agentic-guidelines-q8
TheAngryPit
Compact q8 Karpathy-inspired agentic coding guidance.
SkillCFreshness: CClaude Code +9 - 0.479score
penpot-mcp-operator
TheAngryPit
Use when working with Penpot through MCP, including remote or local Penpot MCP setup, reading or modifying active Penpot design files, creating pages, boards…
SkillCFreshness: CClaude Code +9 - 0.474score
aegis-communication-discipline
TheAngryPit
Use when project execution is drifting into noisy chat.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Jul 3, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/TheAngryPit/TheAngrySkills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from TheAngryPit
- 0.570score
model-capability-router
TheAngryPit
Use when the operator explicitly asks for native Codex model or reasoning-effort routing, including an active standing request.
SkillAFreshness: AClaude Code +9 - 0.570score
openclaw-control-ui-e2e
TheAngryPit
Use when changing or proving OpenClaw Control UI behavior with deterministic Gateway fixtures, browser flows, rendered evidence or interaction profiling.
SkillAFreshness: AClaude Code +9 - 0.570score
openclaw-debugging
TheAngryPit
Use when diagnosing OpenClaw provider, tool-surface, code-mode, streaming, transcript, worker or package-runtime failures.
SkillAFreshness: AClaude Code +9 - 0.570score
openclaw-node-connect
TheAngryPit
Use when explicitly asked to repair one exact OpenClaw browser or native-node connection, including auth, Tailscale routing or pairing.
SkillAFreshness: AClaude Code +9 - 0.569score
openclaw-diagnose-gateway
TheAngryPit
Use when diagnosing OpenClaw Gateway, config, channel, model, SecretRef or listener failures without changing state.
SkillAFreshness: AClaude Code +9 - 0.569score
openclaw-node-inspect-debugger
TheAngryPit
Use when debugging Node.js breakpoints, async hangs, hidden locals, heap retention or CPU hot paths with the inspector.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get adobe-illustrator-operator running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
adobe-illustrator-operator skill. Agent Mart. https://agentmart.dev/skills/theangrypit-adobe-illustrator-operator (last updated 2026-10-24)