Agent skill

Direction Picker

by nexu-io in nexu-io/open-design

Resolves the visual direction at the plan stage from the brief and design system, without asking the user.

Apache-2.0Auto-check: warningsFrontend & Design

Install Direction Picker

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add nexu-io/open-design --skill direction-picker -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nexu-io/open-design direction-picker --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nexu-io/open-design.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/_official/atoms/direction-picker .claude/skills/direction-picker && rm -rf skills-src

Use ~/.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/

Facts

Skill name
direction-picker
GitHub stars
100k
Token cost
~472 tokens
SKILL.md length
262 words
Files
2
Skills in repo
245
Repo updated
First seen
Licence
Apache-2.0

At a glance

Resolves the visual direction at the plan stage from the brief and design system, without asking the user.

  • Works in 3 steps: An active design system — its DESIGN.md… → A brand spec, reference URL, or… → Otherwise, infer the best-matching…
  • Tasks that involve Design systems
  • SKILL.md covers Convergence and Anti-patterns the prompt…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Direction Picker is an agent skill from nexu-io/open-design. Resolves the visual direction at the plan stage from the brief and design system, without asking the user.

Its SKILL.md is about 470 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `open-design.json`).

It sits in Frontend & Design, covering Design systems. The repository describes itself as: 🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Design systems

Example prompts

  • “Use the direction-picker skill to resolve the visual direction at the plan stage from the brief and design system, without asking the user”
  • “/direction-picker”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. An active design system — its DESIGN.md palette, typography, spacing, and
  2. A brand spec, reference URL, or screenshot the user supplied — parse that
  3. Otherwise, infer the best-matching direction yourself from the brief's

What it can do on your machine

Read from SKILL.md and the folder at commit d9dd6fe. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Direction Picker loads about 472 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 262 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~472

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.

Safety

Auto-check: warnings

The automated check found patterns that need a careful read before installing.

  • WarningTells the agent its actions are pre-authorized / not to stop for confirmationSKILL.md:3
    stage from the brief and design system, without asking the user.

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from nexu-io/open-design at commit d9dd6fe, republished under its Apache-2.0 licence (© nexu-io). 262 words, ~472 tokens.

Download SKILL.mdSave it as .claude/skills/direction-picker/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
direction-picker
description
Resolves the visual direction at the plan stage from the brief and design system, without asking the user.
od.scenario
general
od.mode
planning

Direction picker

Converging work needs one committed visual direction before the build starts. This atom owns that moment in the plan stage: decide the direction, state it in one line, and lock onto it.

Resolve the direction from what you already have, in this order:

  1. An active design system — its DESIGN.md palette, typography, spacing, and component rules are the direction. Bind its tokens and stop here.
  2. A brand spec, reference URL, or screenshot the user supplied — parse that source directly.
  3. Otherwise, infer the best-matching direction yourself from the brief's domain, audience, and tone, then bind its visual tokens. If the runtime provides only an index of direction ids and names, run "$OD_NODE_BIN" "$OD_BIN" tools directions --id <id> to retrieve the full specification — never infer colors or fonts from the name alone.

Do not ask the user to choose a visual direction. Not as a question-form, not as a markdown list of options, not as a "which of these feels right?" follow-up. The direction is yours to resolve; asking spends the user's turn on a decision they hired the agent to make.

Convergence

The atom completes when the plan states the chosen direction. The agent's next turn must build against that direction — backtracking forces a fresh devloop iteration of the plan stage.

Anti-patterns the prompt fragment forbids

  • Asking the user to pick, compare, or confirm a visual direction.
  • Locking the user into a single direction with cosmetic alternates (a stated direction must be a defensible standalone bet).
  • Inferring palette or typography from a direction's name instead of resolving its specification.

© nexu-io, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in plugins/_official/atoms/direction-picker of nexu-io/open-design.

  • SKILL.md
  • open-design.json

Open the folder on GitHubat commit d9dd6fe

Compare with similar skills

Direction Picker 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.

Direction Picker compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Direction Picker this skillnexu-io/open-design100k—~472Automated safety check: WarnApache-2.0
Impeccablebestofjs/bestofjs3.1k27 repos~2.6kAutomated safety check: PassMIT
Figma Design System Builderwarpdotdev/warp65k2 repos~4.4kAutomated safety check: PassAGPL-3.0
Figma use_figma Plugin API Ruleswarpdotdev/warp65k4 repos~4.4kAutomated safety check: PassAGPL-3.0
UI StylingOhh-889/skyroc79513 repos~2.5kAutomated safety check: PassMIT
Shadcnsupabase/evals14342 repos~4.5kAutomated safety check: PassApache-2.0

Similar skills

  • Impeccable

    bestofjs/bestofjs

    A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…

    3.1k GitHub starsUsed in 27 repos~2.6k tokens
    Frontend & DesignAuto-check passed
  • Builds or updates a design system in Figma from a codebase in ordered phases: discovery, variables and tokens, components, theming and documentation, with checkpoints.

    65k GitHub starsUsed in 2 repos~4.4k tokens
    Frontend & DesignAuto-check passed
  • Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.

    65k GitHub starsUsed in 4 repos~4.4k tokens
    Frontend & DesignAuto-check passed
  • UI Styling

    Ohh-889/skyroc

    Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs.

    795 GitHub starsUsed in 13 repos~2.5k tokens
    Frontend & DesignAuto-check passed
  • Shadcn

    supabase/evals

    Official

    Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI.

    143 GitHub starsUsed in 42 repos~4.5k tokens
    Frontend & DesignAuto-check passed
  • Design System

    Ohh-889/skyroc

    Token architecture, component specifications, and slide generation.

    795 GitHub starsUsed in 11 repos~1.7k tokens
    Frontend & DesignAuto-check passed

More from nexu-io/open-design

All 245 skills in this repo
  • Humanize PPT

    nexu-io/open-design

    Turns raw notes into a talk-ready slide outline with per-page image, diagram or video decisions, then checks the rendered deck against that outline.

    100k GitHub stars~4k tokensUpdated today
    Auto-check passed
  • Last 30 Days Trend Research

    nexu-io/open-design

    Produces a cited Markdown briefing on recent community sentiment and social reaction to a topic, labeling every source it could not actually check.

    100k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • OpenDesign Contribution Flow

    nexu-io/open-design

    Helps newcomers contribute to OpenDesign: ship a skill or design system, translate docs, fix docs or report a bug, ending in a pull request or issue.

    100k GitHub stars~3.5k tokensUpdated today
    Auto-check: notes
  • Turns a chat transcript or screenshot into a configurable animated chat clip, rendered as a Remotion bundle with optional transparency.

    100k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Team-management dashboard skill in the FlowAI aesthetic — three tabs (Team Members, Team Details, Activity Log), KPI stat row, member table, role distribution bar chart, online presence and activity…

    100k GitHub stars~865 tokensUpdated today
    Auto-check passed
  • Hatch Pet

    nexu-io/open-design

    Create, repair, validate, preview, and package Codex-compatible animated pet spritesheets from character art, screenshots, generated images, or visual references.

    100k GitHub stars~6k tokensUpdated today
    Auto-check passed

Questions about Direction Picker

What does Direction Picker do?

Resolves the visual direction at the plan stage from the brief and design system, without asking the user. Direction Picker is an agent skill from nexu-io/open-design. Resolves the visual direction at the plan stage from the brief and design system, without asking the user.

When should I use Direction Picker?

Direction Picker fits situations like: tasks that involve Design systems.

How do I install Direction Picker in Claude Code?

Run `npx skills add nexu-io/open-design --skill direction-picker -a claude-code`. Or copy the skill folder (plugins/_official/atoms/direction-picker in nexu-io/open-design) into .claude/skills/direction-picker in your project. Claude Code loads it when a task matches its description.

How do I install Direction Picker in Codex?

Run `npx skills add nexu-io/open-design --skill direction-picker -a codex`. Or copy the skill folder (plugins/_official/atoms/direction-picker in nexu-io/open-design) into .agents/skills/direction-picker in your project. Codex loads it when a task matches its description.

Can I use Direction Picker in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nexu-io/open-design --skill direction-picker -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/direction-picker, .gemini/skills/direction-picker, .github/skills/direction-picker and .opencode/skills/direction-picker in your project.

What does Direction Picker need to run?

SKILL.md names no scripts, command-line tools or credentials: Direction Picker is instructions for the agent only.

Does Direction Picker access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Direction Picker safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): tells the agent its actions are pre-authorized / not to stop for confirmation. Read the flagged lines before installing; the check is not a guarantee either way.

What licence does Direction Picker use?

Direction Picker is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Direction Picker use?

About 472 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Direction Picker?

Skills that share tags, products or a category with Direction Picker: Impeccable (bestofjs/bestofjs, 3.1k stars), Figma Design System Builder (warpdotdev/warp, 65k stars), Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars) and UI Styling (Ohh-889/skyroc, 795 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Direction Picker?

nexu-io (a GitHub organization) maintains it in nexu-io/open-design, which has 100,100 GitHub stars. The repository holds 245 skills in this directory. The repository was last updated on October 9, 2026.

Source: nexu-io/open-design on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.