Borrowing it
Nothing to install: this file belongs to wlsdks/ontology-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wlsdks/ontology-atlas/main/.agents/skills/design-directions/SKILL.mdgit clone --depth 1 https://github.com/wlsdks/ontology-atlasWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wlsdks/ontology-atlas/design-directions)<a href="https://agentmods.dev/skills/wlsdks/ontology-atlas/design-directions"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/design-directions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wlsdks/ontology-atlas/design-directions"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/design-directions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.01061 |
| Opus 5 | $0.00017 | $0.00531 |
| Sonnet 5 | $0.00007 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
design-directions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design directions before implementation
Two evidence lines support this step.
First, frontier models return to a persistent frontend default. Generic redirection such as “cleaner” or “not cream” replaces one default palette with another; only a concrete specification changes the structure. With sampling controls no longer exposed, generate several directions and let a person choose.
Second, Dow, Glassco, Kass, Schwarz, Schwartz, and Klemmer, “Parallel Prototyping Leads to Better Design Results, More Divergence, and Increased Self-Efficacy” (ACM TOCHI 2010), found parallel alternatives superior to serial iteration on quality, divergence, and self-efficacy.
/design-council reviews one built direction. This skill cheaply creates the
alternatives before that review when the route identifies a structural choice.
Ownership
The owner of divergence is chief, not the builder design-guardian. A builder
who authors the options biases them toward the one they want to implement and
turns the rest into straw men. chief sketches, the human owner chooses, and the
builder implements.
A direction is structural, not a palette
Atlas already fixes dark-only and tokens-on-ramps; since 2026-09-08 gradients, glow, glass and further hues are open, so a direction may spend them, but a direction is still a structure, not a coat of effects. Do not copy example colours, fonts, or assets from reference documents.
Directions differ on at least one axis:
| Axis | Structural difference |
|---|---|
| Hierarchy | what the eye reaches first |
| Layout and density | grouping, rows, and spatial ownership |
| Interaction model | modal, inline, popover, or in-place action |
| Motion information | which state change moves and what that movement explains |
Different values inside the same shape are adjustments, not directions.
When
Run only when pnpm design:route returns directions=yes: a new surface,
information architecture, primary interaction model, or primary attention
model. Do not invoke it for generic “non-trivial” work, token swaps, copy edits,
spacing/layout fixes inside a selected shape, responsive repairs, or motion
tuning.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · +1 lines a797cba318be
- 6d ago Changed · +13 lines 27eacea7b218
- 8d ago Changed · +1 lines · -2 tokens per session 64a39a768367
- 12d ago First seen · 107 lines · 36 tokens per session scan A 5c5f480d70b3
design-directions is a skill published in the GitHub repository wlsdks/ontology-atlas (104 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 1,061 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
design-brief
Parse a structured design brief written in I-Lang protocol format into a concrete design spec. Eliminates ambiguity from vague requests like "make it professional" by requiring explicit dimensions: palette, typography, layout, mood, density, and constraints. Trigger keywords: "design brief", "create a design brief"…
fs-electric-studio
OpenDesign as an enterprise design platform: a buyer-forwardable proposal for a design-org's economic buyer — pain, value, ROI, rollout. Built as a decision-grade B2B sales deck for economic buyer, design VP, procurement.
critique
Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks…
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
open-design-landing-deck
OpenDesign's brand-story deck for partners and press: why it exists, what it believes, and where design is going. Built as a decision-grade marketing & GTM deck for partners, press, community.
fs-editorial-forest
Art-directing a fashion house's annual report — the editorial system, the photography rhythm, and the data spreads. Built as a decision-grade design craft deck for brand stakeholders, exec audience.