Openpencil Design Orchestrator

Orchestrate Pencil/OpenPencil design work through MCP using a staged workflow: preflight, planning, skeleton, section content, refinement, and safe fallback. Use when working with Pencil/OpenPencil, .fig/.pen design files, MCP-based design editing, or when Claude Code, Codex, Cursor, or Windsurf needs reliable prompt patterns, client setup guidance, and risk controls for AI-assisted design changes.

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ziiinian/openpencil-design-orchestrator --skill openpencil-design-orchestrator
Manual install
git clone --depth 1 https://github.com/ziiinian/openpencil-design-orchestrator.git /tmp/openpencil-design-orchestrator
mkdir -p ~/.claude/skills
cp -r /tmp/openpencil-design-orchestrator/. ~/.claude/skills/openpencil-design-orchestrator

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# OpenPencil Design Orchestrator

Use this skill to turn vague Pencil/OpenPencil requests into a controlled multi-step workflow.
Default to MCP-first execution. Prefer small, verifiable edits over one-shot generation.

## Quick Start

1. Run `scripts/preflight-check.sh` when the environment or MCP connectivity is unknown.
2. Read `references/prompt-framework.md` before drafting or executing prompts.
3. Read `references/client-adapters.md` when the user mentions Claude Code, Codex, Cursor, or Windsurf setup.
4. Read `references/risk-matrix.md` when debugging failures or choosing guardrails.
5. Read `references/fallback-mode.md` when MCP is unavailable or unstable.

## Workflow

### Step 1 - Preflight

- Confirm Pencil/OpenPencil is running if the workflow depends on desktop-hosted MCP.
- Confirm whether transport is `stdio` or `HTTP`.
- Confirm `openpencil-mcp` is installed when using MCP.
- Read the current file/page tree before proposing mutations.
- Refuse giant blind edits when the current structure is unknown.

### Step 2 - Planning

- Translate the request into pages, sections, components, tokens, and execution order.
- Resolve ambiguity before editing.
- Ask for confirmation only when ambiguity materially changes layout or scope.
- Prefer explicit checkpoints over creative guessing.

### Step 3 - Skeleton

- Create only structural scaffolding: pages, frames, sections, containers, autolayout, naming.
- Avoid visual polish and long-form copy generation in this phase.
Read the full skill on GitHub

Details

Skill name
openpencil-design-orchestrator
License
MIT
Repo updated
22 March 2026

FAQ

What does the Openpencil Design Orchestrator skill do?

Orchestrate Pencil/OpenPencil design work through MCP using a staged workflow: preflight, planning, skeleton, section content, refinement, and safe fallback. Use when working with Pencil/OpenPencil, .fig/.pen design files, MCP-based design editing, or when Claude Code, Codex, Cursor, or Windsurf needs reliable prompt patterns, client setup guidance, and risk controls for AI-assisted design changes.

How do I install the Openpencil Design Orchestrator skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ziiinian/openpencil-design-orchestrator --skill openpencil-design-orchestrator. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Openpencil Design Orchestrator popular?

It lives in ziiinian/openpencil-design-orchestrator, which has 5 GitHub stars and 0 forks.

Related skills

Phd Application Advisor

5

alex-yimingyang/phd-application-advisor

大龄非科班转AI申请海外PhD的全流程顾问。覆盖RA申请、选方向选校、套磁、文书、面试、推荐信、时间规划等所有环节,专门针对30+在职、非CS背景、想转AI方向申博的人群提供策略建议。 当用户提到以下任何场景时使用此skill:大龄读博、非科班申博、转行申PhD、30+申博、在职申博、工作后读博、非传统背景申请PhD、AI方向博士申请、美国博士申请、海外PhD、申博规划、申博咨询,或任何涉及"工作几年后想读博不知道怎么开始"的问题。即使用户没有明确说"非科班",只要描述了类似背景(非CS本科、工作多年、想转AI/ML方向读博),也应触发此skill。

AI, LLMs & Agents

Omi

5

CzzzzzzJ/omi

Omi3.0 小红书图文笔记生产线。输入内容素材 + IP形象,自动产出分镜脚本JSON + 图片生成指令,适用于 Claude Code、OpenClaw、Codex、扣子等任何具备本地图片生成能力的 Agent 平台。触发词:omi、小红书笔记生成、omi笔记

AI, LLMs & Agents

Prism V2

5

Ronkupper/PRISM

PRISM — structured multi-session, multi-vendor LLM-orchestrated audit and research framework. Trigger this skill whenever the user invokes PRISM mechanics by name or by recognizable construct: PRISM audit, PRISM v2, begin a PRISM audit, Master file, any filename matching *_master_p*.md, Prompt Strategy, Lens Library, Vendor Selection, Vendor Triangulation, Setup probes or any of P1-P7 by number, Monitor M* or any of M1-M12 by number, Standing Principle SP-*, Execution Envelope, Execution Self-check, Execution Output, Dispatch register, Dispatch shape (equivalence/split/limitation-named), the W

AI, LLMs & Agents

Oeconomia

5

vincitamore/oeconomia

Delegation economy for a session whose own context window is the scarce resource. REFLEX: name the model wherever the dispatch primitive accepts one (an unset model can inherit the session model and silently spend the budget you protect); delegate bulk early (multi-file reads, protocol-driven review sweeps, build/test runs, scripted edits) so freight never lands in the compounding window; keep judgment and every required orientation read; floor: one known-file read, one grep, a two-line edit, or any read near session end stays home; a same-provider subagent relieves the window, never the accou

AI, LLMs & Agents

Prompt Constraints

5

q253595422/prompt-constraints

生图 / 视频提示词约束引擎。把模糊需求、关键词、粗糙草稿或参考图,转成受约束、可校验、可直接投喂的生图(t2i / i2i)与视频(t2v / i2v / 多镜头)提示词。 用于:写/优化/扩写生图提示词,写/优化视频提示词,从参考图反推提示词(图画文 / img2prompt),锁定角色·场景·风格一致性(character sheet / 角色三视图 / 身份锚点),写负面约束与回避清单,按模型适配(Nano Banana Pro、即梦 Seedream、GPT Image、Midjourney、FLUX、Seedance、可灵 Kling、Veo、Sora、Hailuo、MiniMax、LTX、Wan)。 当用户提到「生图提示词 / 视频提示词 / prompt / 提示词 / 反推提示词 / 图画文 / 一致性 / 首帧图 / 分镜 / 运镜」时使用。

AI, LLMs & Agents

No AI Tone

5

mckenizemanfull5678-ctrl/no-ai-tone

中文长文写作五步管线:把杂乱素材整理成一篇读起来「不像 AI 写的」文章。当用户要写 公众号 / 知乎 / 博客等中文长文,要把素材·笔记·链接整理成稿,抱怨 AI 写的东西有 「AI 腔 / AI 味」,或想给一篇已有文章去 AI 腔、提炼金句、规划配图时使用。主线五步写作 + 配图落地:选题研判 → 内容线设计 → 大纲打磨 → 风格化初稿 → 双重精修(去 AI 腔 + 金句提炼) → 配图落地(信息图为主、配图也去 AI 味)。核心心法是「人决策、AI 执行」——每一步产出后 停下来等用户拍板,绝不一口气跑完。

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.