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 Dragoon0x/taste-skills --skill learning-by-makinggit clone --depth 1 https://github.com/Dragoon0x/taste-skillsWrote 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/dragoon0x/taste-skills/learning-by-making)<a href="https://agentmods.dev/skills/dragoon0x/taste-skills/learning-by-making"><img src="https://agentmods.dev/badge/skills/dragoon0x/taste-skills/learning-by-making/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/dragoon0x/taste-skills/learning-by-making"><img src="https://agentmods.dev/badge/skills/dragoon0x/taste-skills/learning-by-making.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00056 | $0.00706 |
| Opus 5 | $0.00028 | $0.00353 |
| Sonnet 5 | $0.00011 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
learning-by-making 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 10d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning by Making
Taste is sharpened by making, failing, and making again. Not by watching.
How to use
/learning-by-makingApply making-as-practice constraints to creative development in this conversation.
Constraints
The Volume Principle
- MUST prioritize quantity of finished work over quality of any single piece
- A designer who ships 50 projects in a year learns more than one who perfects 3
- MUST finish things. Unfinished work teaches you how to start. Finished work teaches you how to decide.
- NEVER let "it's not ready" become permanent. Set a deadline. Ship it. Learn from the gap between what you shipped and what you wished you'd shipped.
Deliberate Practice Formats
- Speed rounds (15-30 min): Redesign a real product screen. No research. No moodboard. Just instinct. What comes out reveals your current taste baseline.
- Style copies (60 min): Recreate someone else's design decision-for-decision. Not pixel-copying. Understanding why every choice was made by making it yourself.
- Constraint challenges (45 min): One typeface, one color. 320px width only. Zero images. 10 words max per screen. Constraints strip away crutches and expose your actual judgment.
- Fake briefs (2-4 hours): Invent a product. Design it end-to-end. Landing page, onboarding, core screen, settings. The act of making complete decisions across a whole product builds holistic taste.
- Remix exercises (30 min): Take something you made last month. Redesign it from scratch without looking at the original. Compare the two. The delta is your growth.
Rules of Making
- MUST make things even when they're bad. Especially when they're bad. Bad work with reflection teaches more than good work by accident.
- MUST reflect after making. "What worked? What didn't? What would I change with 2 more hours?" Without reflection, volume is just busywork.
- MUST vary the format. If you only design landing pages, your taste is landing-page-shaped. Design dashboards, mobile apps, emails, posters, packaging, signage.
- SHOULD share work publicly. The vulnerability of showing imperfect work accelerates growth because it forces you to articulate your decisions.
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.
- 10d ago First seen · 46 lines · 56 tokens per session scan A 008f49b85cc3
learning-by-making is a skill published in the GitHub repository Dragoon0x/taste-skills (4 stars, last pushed 6mo ago), licensed MIT. It adds 56 tokens to every session and 706 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
threejs-interaction
Three.js interaction - raycasting, controls, mouse/touch input, object selection. Use when handling user input, implementing click detection, adding camera controls, or creating interactive 3D experiences.
create-video-seedance-2-fal
Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills…
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
seedance-2-5
Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…
threejs-shaders
Three.js shaders - GLSL, ShaderMaterial, uniforms, custom effects. Use when creating custom visual effects, modifying vertices, writing fragment shaders, or extending built-in materials.
create-workflow-diagram
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.