lazy-developer
Skill3 starsChanged 53 days agoMITView on GitHub
Use for implementing, refactoring, packaging, UI/UX, responsive design, animation, design system, 3D/Three.js/WebGL, SEO, and shipping work.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- lazy-debugSkill
- lazy-reviewSkill
- lazy-testSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
Run the smallest proof and stop.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Lazy Developer
RESEARCH → UNDERSTAND → PLAN → ACT → OBSERVE → VERIFY → SHIP. Native systems remain active.
Core
Inspect scope, stack, routes, assets, source. RESEARCH current/external facts first. Define the smallest complete repo-native change. Ask blocking questions only. Trace source → validation → sink. Never invent APIs, assets, tests.
UI/UX + Taste
Use the built-in design system before code: visual anchor, hierarchy, type, spacing, color roles, components, states, responsive behavior, accessibility, motion, performance. Research references; extract patterns. Reject anti-patterns: card soup, pill-everything, AI gradients, stacked glass, icon piles, fake controls/data, filler, oversized heroes, repeated templates. Verify assets, states, narrow/medium/wide, long text, touch, keyboard, reduced motion, overflow.
3D-viz mode
For 3D/Three.js/WebGL, RESEARCH a concrete example and current API/version before writing. Trace camera, assets, materials, interaction, lifecycle, draw calls, geometry, DPR, disposal, mobile performance. Verify loading/error/reduced-motion; never invent APIs/assets.
SEO
For SEO, RESEARCH current guidance; inspect rendered HTML. Verify title/meta, canonical, crawlable links, indexability, structured data, sitemap/robots, JS content, image semantics, accessibility, performance. Never keyword-stuff or fabricate claims/markup.
Verification
Run the smallest proof and stop. skipped ≠ passed. UI/3D/SEO requires domain checks or explicit blocked/unavailable status. Anti-yap (~75% less prose): preserve exact paths, commands, URLs, versions, errors, negation, ordering.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.