Showing 53581–53597 of 53597 skills
Add a feature to an app you vibe-coded without breaking the three things that already worked -- read the existing patterns first, extend them instead of inventing a second way to do the same thing. Use when adding any new screen, flow, or capability to an existing codebase.
OneWave-AI/open-agent-stack
Plan and capture the demo or launch video for the app you just shipped -- the beat sheet, the clean capture setup, and the narration -- so it shows the product working instead of narrating a tour. Use after shipping, when the app needs a video for a landing page, launch post, or client handoff.
OneWave-AI/open-agent-stack
GSAP in a React or Next.js app without the leaks -- timelines over stacked tweens, useGSAP and context for cleanup, ScrollTrigger set up so it survives route changes and layout shifts. Use when building GSAP animations in a component-based app.
OneWave-AI/open-agent-stack
Make a vibe-coded app survivable by someone else -- an honest README, the decisions written down, the shortcuts listed, and a setup path a new developer can follow without you. Use before handing an app to a client, a contractor, a teammate, or your own future self.
OneWave-AI/open-agent-stack
Turn the demo into a product -- replace hardcoded arrays with a real database, stubbed sign-in with real auth, and the fake form with one that actually delivers. Use when an app looks finished but nothing it shows is true.
OneWave-AI/open-agent-stack
The small motion that makes an app feel built rather than generated -- hover, press, focus, toggles, loading, and state changes done as a consistent system in plain CSS. Use when UI feels static or lifeless, or when hover effects are scattered and inconsistent.
OneWave-AI/open-agent-stack
Find and fix animation jank -- the layout thrash, paint storms, and layer explosions that make motion stutter on real devices even when it is smooth on your laptop. Use when animations feel choppy, scroll stutters, or before shipping any animation-heavy page.
OneWave-AI/open-agent-stack
Define the app's motion language before animating anything -- a small set of durations, easings, and named moves that every animation draws from, so the app feels designed instead of decorated. Use before writing the first animation in a project, or when existing motion feels scattered.
OneWave-AI/open-agent-stack
Scaffold a new app from one sentence -- Next.js + TypeScript + Tailwind with a real design-token theme applied from the first commit, opinionated structure, and honest slots for auth and data. Use when starting any new project, prototype, or client build.
OneWave-AI/open-agent-stack
The de-AI pass -- audit a vibe-coded app for template smell in design and copy, then fix it with editorial layout, purposeful motion, and human-sounding words. Use after any build session, before anyone else sees it.
OneWave-AI/open-agent-stack
Build scroll-driven sections that feel authored rather than twitchy -- pinned scenes, scrubbed timelines, reveals, and parallax with the timing and cleanup that make them work on a phone. Use for landing pages, product tours, and any section where scrolling advances a narrative.
OneWave-AI/open-agent-stack
Pre-flight and deploy -- catch the classic day-one embarrassments (exposed keys, missing env vars, broken build, open endpoints), then ship to Vercel with domains and analytics wired. Use when the app is ready for other humans.
OneWave-AI/open-agent-stack
Build a marketing website that converts and ranks -- page inventory, copy before layout, one honest conversion path, real SEO and OG metadata, forms that actually deliver. Use for landing pages, company sites, product sites, and portfolios, as opposed to apps with accounts and data.
OneWave-AI/open-agent-stack
The app broke and you did not write the code -- find the actual cause instead of guessing at fixes, and stop the loop where every attempted fix adds a new bug. Use when something worked yesterday, the build fails, the deploy is white, or the same error keeps coming back.
OneWave-AI/open-agent-stack
Create teaching-quality STEM animations using ManimGL. Generates narrative-driven animations as 15-second chunks merged into a final video. Configurable topic, duration, and model name. Works with Claude Code and opencode across any model. Invoke: /test-manim "topic" [--duration 30|60|90|120] [--model name] Default duration: 30s. Primary goal: great storytelling + visual clarity.
shihabshahrier/manim-coding-skill
GEPA-style measured evolution of a learned skill under ~/.config/opencode/skills. Use this skill when the `evolution_status` tool or `optimize_skill` tool returns a skill with high use_count AND non-zero failure rate, OR when the user asks to evolve/improve/optimize/refine a specific skill, OR when the self-improving-skills plugin's `optimize_skill` tool was called (it returns the procedure pointer; this skill provides the actual reasoning). This is the companion axis to `skill-distiller` — distiller ACQUIRES skills, this skill IMPROVES them by reflective mutation grounded in failure traces.
okdk7788/opencode-self-improving-skills
Distills reusable techniques from a finished work session into a learned skill under ~/.config/opencode/skills — patching an existing skill when one fits, creating a new class-level skill only as a last resort. Use this skill whenever the agent has just completed complex work (substantial debugging, multi-file refactoring, new library/API integration, non-obvious workaround discovery), OR when the self-improving-skills plugin's system-prompt advisory fires ("자기개선 트리거" / "도구 호출 N회 누적"), OR when the user explicitly asks to capture/distill/learn/save a technique. This is the review-and-capture stage of the self-improvement loop modeled on Nous Research's Hermes Agent.
okdk7788/opencode-self-improving-skills