olakunlevpn
- 27 skills
- 0 followers
- 11 hours ago last updated
- ▌ Artifact CSS · olakunlevpn bundleOUTPUT IS ALWAYS A SINGLE `.html` FILE (never `.md`, never plain markdown, never a text response) styled with the artifact.css class vocabulary. Use this skill whenever producing a standalone HTML artifact that is meant to be read, reviewed, or interacted with as a document. This includes status reports, post-mortems, implementation plans, PR reviews, design systems, explainers, comparisons, slide decks, and interactive editors. Apply this skill any time the user asks for an HTML page, web page, report, dashboard, or any "show me" / "draw me" / "visualize" output that should look polished rather than developer-default. The skill provides a lightweight design system (artifact.css) with a unified color palette, typography, and component vocabulary so the artifact reads as a real document, not a rough sketch. Do not use for production apps, marketing sites, or anywhere a separate design system is already in play.
- ▌ Artifact Deck · olakunlevpn bundleOUTPUT IS ALWAYS A SINGLE `.html` FILE (never `.md`, never separate per-slide files) containing multiple slides navigated by arrow keys. Use this skill whenever the user asks for a slide deck, presentation, talk, "Friday demo", "share-out slides", "exec readout", "kickoff deck", "lightning talk", arrow-key deck, keynote-style outline, or any artifact whose primary shape is "a sequence of slides you advance through". Pair with `artifact-css` for the underlying design system. Do NOT use for single-page reports — those are `artifact-report`.
- ▌ Artifact Flow · olakunlevpn bundleOUTPUT IS ALWAYS A SINGLE `.html` FILE (never `.md`, never separate per-screen files) containing multiple screens navigated by clickable hotspots and/or a hash router. Use this skill whenever the user asks for a clickable prototype, clickable mockup, multi-screen flow, user-flow walkthrough, "click-through demo", "tap-through prototype", interactive wireframe, or any artifact whose primary shape is "a sequence of screens linked by hotspots". Pair with `artifact-css` for the underlying design system. Do NOT use for slide decks (use `artifact-deck`) or for fully-functional editors (use `artifact-editor`).
- ▌ Artifact Plan · olakunlevpn bundleOUTPUT IS ALWAYS A `.html` FILE (or a small folder of `.html` files for multi-page plans) — never `.md`, never plain markdown. The file extension on a "PLAN" deliverable is `.html`, not `.md`. Use this skill whenever the user asks for an implementation plan, technical plan, project plan, roadmap, milestone breakdown, comparison sheet, options analysis, RFC, design doc, technical proposal, "weigh three approaches", "lay out the work", "break this into phases", "compare X vs Y vs Z", or any forward-looking planning artifact that should be delivered as a polished HTML document with milestones, risk tables, open questions, and decision criteria. Pair with artifact-css for the underlying design system. Do NOT use for one-paragraph "yeah let's do that" answers or for already-decided execution checklists with no open questions left.
- ▌ Artifact Design · olakunlevpn bundleOUTPUT IS ALWAYS A SINGLE `.html` FILE (never `.md`, never Figma exports) showing design primitives next to their source code. Use this skill whenever the user asks for a design system page, design tokens reference, component variants sheet, "show all the buttons", "all states of the card component", "swatch the palette", living style guide, brand kit, or any artifact whose primary shape is "rendered components paired with their source / spec". Pair with `artifact-css` for the underlying design system. Do NOT use for one-off feature mockups (use `artifact-flow`) or for animation playgrounds (use `artifact-sandbox`).
- ▌ Artifact Editor · olakunlevpn bundleOUTPUT IS ALWAYS A `.html` FILE (never `.md`, never plain markdown) with working jQuery UI widgets and JavaScript wired up. Use this skill whenever the user asks for an interactive editor, triage board, kanban board, "thing I can drag around", feature flag panel, feature flag dashboard, prompt tuner, prompt playground, parameter panel, "let me adjust X live", "give me a UI to play with this", or any HTML artifact that the user is expected to manipulate (drag, sort, tweak sliders, toggle flags, edit and export). Pair with `artifact-css` for the underlying design system and `jQuery 4.0.0 + jQuery UI 1.14.2` for the interactivity (sortable, draggable, slider, datepicker, dialog, autocomplete widgets). Do NOT use for static dashboards that just display data — only when the user must change something and ideally export the result.
- ▌ Artifact Report · olakunlevpn bundleOUTPUT IS ALWAYS A SINGLE `.html` FILE (never `.md`, never plain markdown). Use this skill whenever the user asks for a status update, weekly report, monthly report, status report, engineering update, project update, incident report, post-mortem, retro, retrospective, PR description, or PR writeup that should be delivered as a polished HTML document. Trigger when the user wants to "summarize what shipped this week", "write up the incident", "draft a post-mortem", or any similar recurring written deliverable that benefits from a small chart, a timeline, a colored highlight, or a structured table over a flat markdown summary. Pair with artifact-css for the underlying design system. Do NOT use for casual chat summaries that the user just wants to read in the conversation - only when an HTML artifact is the deliverable.
- ▌ Artifact Review · olakunlevpn bundleOUTPUT IS ALWAYS A `.html` FILE (never `.md`, never plain markdown). Use this skill whenever the user asks for a code review writeup, PR review, annotated diff, "review this patch", "give feedback on this change", "leave inline comments on this PR", "summarize what's wrong with this code", or any reviewer-side artifact that pairs concrete diff hunks with human commentary, suggestions, and approve/request-changes verdicts as a polished HTML document. This is the reviewer-side companion to `artifact-report`'s PR writeup (which is author-side). Pair with `artifact-css` for the underlying design system. Do NOT use for casual one-line feedback or for purely conversational review chats — only when an HTML artifact with annotated diffs is the deliverable.
- ▌ Artifact Diagram · olakunlevpn bundleOUTPUT IS ALWAYS A SINGLE `.html` FILE (never `.md`, never separate image files) containing inline SVG diagrams with annotations, legends, and optional hover labels. Use this skill whenever the user asks for a flowchart, system diagram, module map, dependency graph, architecture diagram, sequence diagram, ER diagram, SVG figure sheet, "draw me a diagram of", "map the modules", "visualize the data flow", or any artifact whose primary shape is "boxes and arrows that explain a system". Pair with `artifact-css` for the underlying design system. Do NOT use Mermaid syntax or markdown — render diagrams as native inline SVG.
- ▌ Artifact Sandbox · olakunlevpn bundleOUTPUT IS ALWAYS A SINGLE `.html` FILE (never `.md`, never separate CSS/JS files) containing a live, tunable demo of one CSS/JS technique. Use this skill whenever the user asks for an animation playground, animation sandbox, "let me tune the easing", "show me different timings of X", interactive demo of one effect, CSS demo, transition tuner, or any artifact whose primary shape is "one thing animating, with sliders to tune it". Pair with `artifact-css` for the underlying design system and `jQuery 4.0.0 + jQuery UI 1.14.2` for the slider widgets. Do NOT use for full editor UIs (use `artifact-editor`) — sandbox is single-effect focused.
- ▌ Artifact Explainer · olakunlevpn bundleOUTPUT IS ALWAYS A `.html` FILE (never `.md`, never plain markdown) with real jQuery UI interactivity. Use this skill whenever the user asks for an explainer, primer, "how does X work", "explain Y", "TL;DR for Z", concept overview, feature explainer, deep dive, research summary, architecture writeup, or any pedagogical artifact that should be delivered as a polished interactive HTML document with collapsible sections, tabbed code samples, an inline glossary, and a scannable summary block at the top. Pair with `artifact-css` for the underlying design system and `jQuery 4.0.0 + jQuery UI 1.14.2` for the interactivity (accordion, tabs, tooltip widgets). Do NOT use for one-paragraph definitional answers — only when an HTML artifact with progressive disclosure is the deliverable.
- ▌ Olakunlevpn React Skills · olakunlevpn bundleUse when writing, reviewing, or refactoring React or Next.js code — components, hooks, state management, testing, performance, TypeScript patterns, server components, or project structure. Always apply these standards to all React work.
- ▌ Olakunlevpn Root Cause Skills · olakunlevpn bundleUse BEFORE changing any existing code whose behavior is wrong, broken, or not understood — bug fixes, "this isn't working", errors, regressions, "debug X", "why does Y fail", investigations. Forces the agent to prove the root cause with evidence, map every caller and consumer (blast radius), and make the smallest possible change — never a blind or speculative fix. Blocks edits until a written Evidence Ledger passes all gates and confidence is high. Pairs with olakunlevpn-meta-cognitive-verification (which runs AFTER the change). Do NOT use for greenfield code where nothing exists yet, or for pure styling/copy tweaks with no behavioral risk.
- ▌ Olakunlevpn Scaling Discipline · olakunlevpn bundleUse when architecting, reviewing, or scaling any application in any language or framework -- designing a feature, adding a dependency, optimizing a database, introducing queues or async work, structuring modules and boundaries, reusing existing code instead of duplicating it, setting up logging and observability, or deciding how a system should grow. Ten principles for building systems that stay predictable under load, plus a verification gate so "done" means proven, not assumed. Language-agnostic, so it applies to Node, Python, Go, PHP, Ruby, Java, Rust and the rest. Do NOT use for one-off scripts, throwaway prototypes, or pure styling and copy changes.
- ▌ Olakunlevpn Framework First · olakunlevpn bundleUse when writing, reviewing, or refactoring code inside an existing framework such as Laravel, XenForo, Django, Rails, WordPress, Spring, or any other. Enforces framework-first development, so the agent identifies the framework in use, follows its conventions and architecture exactly, reaches for native solutions before third-party ones, keeps code consistent with the surrounding project, and never mixes patterns borrowed from a different framework. The goal is code that reads as natural to an experienced developer of that specific framework. Do NOT use for greenfield projects with no framework chosen yet, or for pure infrastructure and scripting with no application framework involved.
- ▌ Olakunlevpn Frontend First Skills · olakunlevpn bundleUse when creating, modifying, or integrating any frontend page in React, Vue, or Inertia projects. Enforces design-first workflow where every page must originate from a pre-built design folder. Never create pages from scratch. Never assume a design does not exist without checking. Backend data is the source of truth. Always remove dummy data and wire real data.
- ▌ Olakunlevpn Git Skills · olakunlevpn bundleUse when creating git commits, writing commit messages, branching, pushing, or any git operation. Enforces concise commit messages, conventional commits, atomic changes, no AI attribution, and professional git workflow. Auto-triggers on any git activity.
- ▌ Olakunlevpn Human Writing · olakunlevpn bundleUse when writing or editing any prose that must read as human-written, not AI-generated -- blog posts, emails, docs, social posts, replies, marketing copy, landing pages, product descriptions. Strips the statistical fingerprints of AI text (em-dashes, "delve", triads, throat-clearing intros, uniform sentence length, bold-spam) so the output passes as authentic human writing. Do NOT use for code, commit messages, config, structured data, legal or medical text where hedging is required accuracy, or when the user explicitly asks for a formal corporate register.
- ▌ Olakunlevpn Laravel Skills · olakunlevpn bundleUse when writing, reviewing, or refactoring any Laravel code — models, controllers, services, actions, traits, tests, config, exceptions, service providers, or package architecture. Always apply these standards to all Laravel work.
- ▌ Olakunlevpn Local Source Of Truth · olakunlevpn bundleUse when deploying code, fixing a bug on a live server, applying a hotfix, or deciding where a permanent change should live. Enforces that the local development workspace is the single source of truth and that every permanent change flows through the normal deployment pipeline. Servers are for running and verifying, never for permanent edits. Temporary diagnostics on a server are fine, but no undocumented fix is allowed to survive there. Applies to any language, framework, or hosting setup. Do NOT use for pure local work with no server involved, or for read-only server inspection.
- ▌ Olakunlevpn Meta Cognitive Verification · olakunlevpn bundleUse after development is complete to verify a built application against its original plan. Runs 7-perspective verification (QA, Product, Project, Tech Lead, Business Analyst, DevOps, Stakeholder) with full-stack data contract auditing, execution tracing, and zero-tolerance for dummy data or silent mismatches. Never confirms completion without evidence.
- ▌ Olakunlevpn Meta Verify · olakunlevpn bundleUse after a feature or system is built and you need to prove it actually works before calling it done. Orchestrates two skills in sequence -- olakunlevpn-meta-cognitive-verification builds a checklist of everything the system is supposed to do and audits it from 7 perspectives, then olakunlevpn-root-cause-skills takes each checklist item and proves it with evidence, tracing the claim to the code that satisfies it. No item passes on assumption. No completion is declared without an evidence-backed report. Do NOT use for greenfield code that does not exist yet, or for pure styling and copy tweaks with no behavioral risk.
- ▌ Maylancer Docs Writing · olakunlevpn bundleUse when writing or structuring package documentation, README files, API references, or library guides in the Maylancer house voice. Enforces the fixed page anatomy, the one-lead-sentence rule before every code block, the depth-based tone split between intro and inner pages, the recurring phrase bank, and the inline caveat pattern so every doc reads as authored by one consistent voice.
- ▌ Olakunlevpn Blog Publishing · olakunlevpn bundleUse when writing and publishing a blog post to the olakunlevpn.github.io Jekyll site, especially a post announcing a new agent skill. A complete runbook covering the required companion skills, the repo and branch facts, the GitHub account switch, the post front-matter and voice, the humanization self-check, the commit standards, the Pages build poll, and the live verification. Follow every step so a fresh session with no prior context can reproduce the whole workflow.
- ▌ Olakunlevpn Clean Export Skills · olakunlevpn bundleUse when adding files to git, creating zip exports, or packaging a project for delivery. Ensures only actual project source files are included. Excludes agent configs, plan files, AI rules, markdown docs (except README.md), and non-project artifacts. Scans unknown files before including. Maintains a persistent .exclude file.
- ▌ Olakunlevpn Deployment Skills · olakunlevpn bundleUse when setting up deployment scripts, configuring auto-deploy, creating cron jobs, or deploying Laravel and Inertia applications to production servers. Generates deploy-pull.sh and auto-deploy.sh scripts with proper deployment sequence, logging, error handling, and cron configuration.
- ▌ Olakunlevpn Filament Skills · olakunlevpn bundleUse when writing, reviewing, or refactoring Filament PHP v5 code -- resources, forms, tables, infolists, actions, widgets, panels, relation managers, multi-tenancy, testing, or plugin development. Always apply these standards to all Filament work.