Information Hierarchy
Load when deciding what a reader or user sees first, what sits behind a click, and what to cut, on any surface: a UI screen, an HTML report, a doc, a reply longer than a screen.
Install
/plugin marketplace add haowjy/creative-writing-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add haowjy/creative-writing-skills --skill information-hierarchygit clone --depth 1 https://github.com/haowjy/creative-writing-skills.git /tmp/creative-writing-skills
mkdir -p ~/.claude/skills
cp -r /tmp/creative-writing-skills/plugin/claude/skills/information-hierarchy ~/.claude/skills/information-hierarchyPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Information Hierarchy The reader should get what matters to them first, find the rest when they reach for it, and never meet what changes nothing for them. Your own sense of what matters is not theirs. You know the source, so it is natural to rank by what it contains, what sounds complete, and what was at hand; the reader arrives with one question, and that ranking only weakly matches it. Decide importance from the reader. ## Rank by the Reader's Next Move Name the reader, the one question they bring to this screen or page, and what they do after looking: decide, act, check, approve, move on. The first thing they see answers that question; each section after it answers the next question they would ask, and a section that answers none goes. For each piece of information, ask what the reader would do differently for having seen it; that answer is its rank. Write the ranking down before drafting, so the cut is a choice rather than an accident of order. The data model and your own process are not readers. An ID, a timestamp, a tool call, a cost, an internal status name, the steps you took to get here: each earns a place only when the reader acts on it. Name things in the reader's words, not the system's: a user manages notifications, not webhook config. ## Layer by Rank - **First glance:** the answer, or what needs the reader's attention or action, with the action beside it. - **One reach away:** the context needed to decide, next to the thing it qualifies.
Details
- Skill name
information-hierarchy- Repository
- haowjy/creative-writing-skills
- Path
plugin/claude/skills/information-hierarchy/SKILL.md- License
- Apache-2.0
- Repo updated
- 16 November 2026
FAQ
What does the Information Hierarchy skill do?
Load when deciding what a reader or user sees first, what sits behind a click, and what to cut, on any surface: a UI screen, an HTML report, a doc, a reply longer than a screen.
How do I install the Information Hierarchy skill?
Claude Code plugin: /plugin marketplace add haowjy/creative-writing-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Information Hierarchy popular?
It lives in haowjy/creative-writing-skills, which has 593 GitHub stars and 82 forks.
Related skills
Character Sim
593haowjy/creative-writing-skills
Load to speak as a specified character from what they know, how they talk, and what they feel now: in-character conversation, voice discovery, or a relationship pressure test. Pass the character, the story moment, and their style and character-state files.
Creative Research
593haowjy/creative-writing-skills
Load when a story needs factual grounding the writer doesn't have: historical detail, cultural texture, domain accuracy, or how other authors handled similar material. Pass the question and story context; returns a sourced report the writer can draw from.
Creative Writing Craft
593haowjy/creative-writing-skills
Load when putting fiction on the page or judging how it reads there: the production modes (fresh draft, revision, bridge, alternate take, line polish), prose technique, scene mechanics, style analysis, and genre craft.
Ue Actor Component Architecture
468quodsoler/unreal-engine-skills
Use when writing or debugging AActor and UActorComponent C++: constructor vs BeginPlay, PostInitializeComponents, EndPlay cleanup, SpawnActor/SpawnActorDeferred/FinishSpawning, CreateDefaultSubobject, NewObject + RegisterComponent, SetupAttachment/AttachToComponent, tick groups, UChildActorComponent, UINTERFACE, actor pooling. Also use when the user mentions 'BeginPlay', 'Tick', 'SpawnActor', 'CreateDefaultSubobject', 'attach a component', 'root component', 'lifecycle', 'PrimaryActorTick', 'FAttachmentTransformRules'. For collision and overlaps, see ue-physics-collision; for GameMode/Pawn/Cont
Claude Design
220jiji262/claude-design-skill
Produce thoughtful, high-fidelity design artifacts in HTML — landing pages, slide decks, interactive prototypes, animated videos, posters, wireframes, and visual explorations. Use whenever the user asks to design, mock up, prototype, visualize, storyboard, or explore UI options — including phrases like "make a deck", "design a landing page", "prototype this flow", "animate this concept", "build a pitch deck", "create a poster", "visualize this idea", or "design something for a brand". Enforces fact verification (WebSearch before assuming a product exists or its version), the Core Asset Protoco
Ue Animation System
468quodsoler/unreal-engine-skills
Use when writing or debugging Unreal Engine animation C++: AnimInstance subclasses, thread-safe update, FAnimInstanceProxy, montage playback and delegates, anim notifies, animation curves, blend spaces, anim state machines, linked anim layers, root motion. Also use when the user mentions 'UAnimInstance', 'NativeUpdateAnimation', 'NativeThreadSafeUpdateAnimation', 'Montage_Play', 'OnMontageEnded', 'UAnimNotify', 'UAnimNotifyState', 'branching point', 'GetCurveValue', 'blend space', 'AnimGraph', 'LinkAnimClassLayers', 'motion matching', 'motion warping', 'root motion'. For movement and RootMotio
Browse the most popular Claude skills, all frontend & design skills, or write your own with the skills generator.