Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Owl-Listener/designpowers --skill taste-feedbackgit clone --depth 1 https://github.com/Owl-Listener/designpowersWrote 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/owl-listener/designpowers/taste-feedback)<a href="https://agentmods.dev/skills/owl-listener/designpowers/taste-feedback"><img src="https://agentmods.dev/badge/skills/owl-listener/designpowers/taste-feedback.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 164 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00042 | $0.01828 |
| Opus 5 | $0.00021 | $0.00914 |
| Sonnet 5 | $0.00008 | $0.00366 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
taste-feedback 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 8d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Live Taste Feedback
The standard Designpowers pipeline catches taste mismatches at critique — after the full build is done. That's expensive. A wrong colour palette discovered after 8 components are built means rebuilding all 8. This skill interrupts the build at strategic moments to show intermediate output and ask: "Is this heading in the right direction?"
When to Use
- During
design-builderexecution, at natural visual checkpoints - When the build involves subjective aesthetic decisions (colour, typography, spacing, tone)
- When this project's taste direction (
design-taste) is ambiguous on the decision at hand - When the project is new and there's little explicit direction yet for this decision
- When the design-lead's direction was based on interpretation, not explicit user instruction
Do Not Use When
- The user is in auto mode and hasn't opted into taste checks
- The build is purely structural (data models, API integration, routing)
- This project's
design-tastedirection already settles this decision clearly - The user has explicitly said "just build it, I'll review at the end"
Process
Step 1: Identify Checkpoints
Before the build begins, identify 2-4 moments where taste feedback is most valuable. More than 4 interruptions becomes annoying. Choose wisely.
High-value checkpoints:
| Checkpoint | Why It Matters | When to Show |
|---|---|---|
| Colour and typography applied | The foundational visual layer — everything else builds on this | After the first component is styled |
| Layout structure visible | Spatial relationships, density, whitespace | After the primary screen scaffold is built |
| First interaction implemented | How the interface moves and responds | After the first stateful component works |
| Content integrated | How real words look in the design | After content-writer's copy is in place |
Low-value checkpoints (avoid):
| Checkpoint | Why It's Low Value |
|---|---|
| Unstyled HTML structure | Nothing to react to aesthetically |
| Individual component in isolation | Context-free judgement is unreliable |
| After every small change | Interruption fatigue kills the creative flow |
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.
- 8d ago First seen · 166 lines · 42 tokens per session scan A 14f808c2aade
taste-feedback is a skill published in the GitHub repository Owl-Listener/designpowers (243 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 1,828 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
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.
veo-generator
Render a scripted video project into mp4 clips with the Google Veo 3.1 API. Reads a project's shot package (shots/.md), one clip per camera cut, reusing each shot's prompt and sketch — world anchor only with --with-reference, seed unless --no-seed. Use on "render the Veo video for ", "generate the videos from the shot…
video-transcription
Transcribe video and audio files to SRT subtitles with speaker diarization using the Soniox (default) or AssemblyAI API. Use when the user wants to transcribe meetings, videos, or audio files. Supports MKV, MP4, MOV, M4A, MP3. Triggers on "/transcribe", "transcribe my meetings", "transcribe videos in /Movies", or any…
tailwind-shadcn
Tailwind CSS utility patterns with shadcn/ui component usage, theming via CSS variables, and responsive design. Use when styling components, installing shadcn components, implementing dark mode, or creating consistent design systems.
nano-banana-imagegen
Generate and edit images using Google Gemini image models via the nano-banana CLI. Use when the user asks to create, generate, make, or edit images with AI. Supports text-to-image, image editing, style transfer, and multi-image composition. Trigger on requests like "create an image", "generate a picture", "make me a…
anti-slop-frontend
A mechanical, countable anti-slop checklist for AI-generated frontend. Catches the specific signatures an undirected model defaults to: AI-purple glows, Inter-everywhere, em-dashes, div-based fake screenshots, eyebrow-on-every-section, beige+brass "premium" palettes, generic Jane Doe / Acme data. Advisory layer that…