← all publishers

PresidenteOG

@presidenteog source repo

Report this profile Claim this profile

• 39 skills
• 0 followers
• 4 hours ago last updated

1. ▌
   Persistent File Planner · presidenteog

   Use for genuinely large or multi-session work — a build spanning many phases, a migration, anything likely to survive a /clear or a context compaction — where the plan needs to live on disk rather than in the conversation. Not for ordinary tasks; a quick fix or single-session job doesn't need this.
   0 installs
2. ▌
   Verifying Agent Reports · presidenteog

   Use when a subagent, delegated task, or earlier session's write-up states a count, a file's contents, how a tool behaves, or that something was committed or verified — before acting on it or repeating it to the user.
   0 installs
3. ▌
   Agent Cost Observability · presidenteog

   Use when deciding which model tier a task should run on, investigating why a session or subagent burned more tokens than expected, or doing a periodic check that spend hasn't quietly drifted — grounded in what's actually observable here (session transcripts, /caveman-stats, Model Policy tiers), not a hypothetical enterprise dashboard.
   0 installs
4. ▌
   Web Interface Guidelines · presidenteog

   Use when building or reviewing a web UI and you need concrete interface-quality rules — interaction, state, accessibility, forms, feedback, motion, responsive layout, performance and copy. A practical checklist of web interface best practices to apply or audit against.
   0 installs
5. ▌
   Cognitive Externalization · presidenteog

   Use when designing or reviewing an agent or skill system and deciding what should live in the prompt versus be pushed out to durable memory, a reusable skill, a typed protocol, or the harness (hooks/permissions) — especially before adding "just one more instruction" to an already-long system prompt or CLAUDE.md.
   0 installs
6. ▌
   Compose State And Effects · presidenteog bundle

   Use when writing or reviewing Jetpack Compose state ownership, remember state, state hoisting, screen state holders, LaunchedEffect, DisposableEffect, SideEffect, Flow collection, navigation, snackbar, analytics, or focus requests.
   0 installs
7. ▌
   Windows Powershell Safety · presidenteog

   Use when driving PowerShell on this machine — before trusting a failed exit status, before combining a heredoc with a deletion in one call, or when writing a file another tool will parse.
   0 installs
8. ▌
   Negotiating Visual Changes · presidenteog

   Use when about to redesign or restyle a UI surface the user has already seen, or when one pass bundles two or more separable visual changes.
   0 installs
9. ▌
   Threejs Materials Lighting · presidenteog bundle

   Light and shade a three.js scene: choose materials (MeshStandardMaterial PBR vs unlit MeshBasicMaterial), add ambient/hemisphere/directional/point/spot lights, turn on shadow maps, and use an environment map (IBL) for realistic reflections. Use when a three.js model looks black, flat, or wrong — when the user mentions three.js materials, MeshStandardMaterial, lights, shadows, envMap, or PBR. For renderer/loop setup use threejs-scene-setup; for loading models use threejs-gltf-loading.
   0 installs
10. ▌
    Kotlin Concurrency And Flow · presidenteog bundle

    Use when writing or reviewing Kotlin coroutine scope ownership, init launches, non-suspending launch APIs, runBlocking, cancellation, StateFlow, SharedFlow, Channel, stateIn, SharingStarted, state updates, or one-shot events.
    0 installs
11. ▌
    Customer Research · presidenteog

    Use when a product idea or feature needs real user evidence instead of opinions — before writing a survey, when a persona is guessed rather than researched, or when raw interview notes need synthesizing into opportunity areas.
    0 installs
12. ▌
    Tech Debt Auditor · presidenteog

    Use when asked to audit a codebase or module for technical debt and produce a findings report — architectural decay, consistency drift, type/test/dependency gaps, security hygiene. Read-only, cites file:line for every finding, ranks by severity against effort, and never recommends a rewrite. Not for making the fix — pair with a builder agent for that.
    0 installs
13. ▌
    Better Prompt Text · presidenteog

    Use when the user invokes /better-prompt-text or wants a rough prompt (Spanish or English) turned into a polished, precise English prompt to copy and use elsewhere — text delivery only, no execution, no files.
    0 installs
14. ▌
    Design System Spec · presidenteog

    Use when authoring or updating a DESIGN.md design-system specification — defining color/type/spacing tokens with rationale, component state variants, and WCAG-safe palettes for a codebase or agent to consume. Trigger when a project has no design system file yet, or an existing DESIGN.md needs new components or a dark-mode variant.
    0 installs
15. ▌
    Agent Eval Designer · presidenteog

    Use when asked to design an evaluation for an AI agent or skill's real-world reliability — across repeated runs, under noisy tools and environments, against realistic tasks — rather than to verify a single change worked once. Distinct from a one-off QA pass; produces a repeatable eval suite with metrics, noise controls, and human-review gates for high-risk cases.
    0 installs
16. ▌
    Compose Performance · presidenteog bundle

    Use when investigating Jetpack Compose recomposition cost, compiler stability reports, skippability, unstable parameters, frame-rate State reads, cross-phase snapshot back-writing, or @ReadOnlyComposable contracts.
    0 installs
17. ▌
    Sequential Thinking · presidenteog

    Use when a problem's answer depends on a chain of prior conclusions and jumping straight to one risks skipping a step — before answering, when it's unclear where to start, or when an earlier reasoning error needs to surface at the step that caused it.
    0 installs
18. ▌
    Threejs Scene Setup · presidenteog bundle

    Stand up a three.js scene: import maps and the three/addons path, the Scene/PerspectiveCamera/WebGLRenderer trio, the setAnimationLoop render loop, responsive resize, and OrbitControls. Use when starting or debugging a three.js app — when the user mentions three.js, THREE.Scene, WebGLRenderer, PerspectiveCamera, the render loop, resizing, or OrbitControls. For models use threejs-gltf-loading; for materials/lights use threejs-materials-lighting.
    0 installs
19. ▌
    Clarification Timing · presidenteog

    Use when mid-task and unsure whether to interrupt the user with a question right now, defer it, or just proceed on a reasonable assumption — especially once meaningfully into a multi-step delegated task, where asking late can be worse than not asking at all.
    0 installs
20. ▌
    Influence Psychology · presidenteog

    Use when copy or a UX flow isn't converting and needs a persuasion audit — missing social proof, no clear authority signal, no reciprocity or scarcity, or urgency that reads as manufactured rather than genuine.
    0 installs
21. ▌
    Storybrand Messaging · presidenteog

    Use when a brand message, landing page or pitch is unclear or isn't converting — the copy talks about the brand instead of the customer, or there's no one-sentence answer yet to what the business actually does for someone.
    0 installs
22. ▌
    Threejs Gltf Loading · presidenteog bundle

    Load glTF/GLB models in three.js with GLTFLoader and play their skinned animations with AnimationMixer, including DRACO/Meshopt-compressed meshes and KTX2 textures. Use when importing 3D models into three.js — when the user mentions glTF, GLB, GLTFLoader, AnimationMixer, animation clips, DRACOLoader, or "load a 3D model". For scene/camera/renderer setup use threejs-scene-setup; for materials and lights use threejs-materials-lighting.
    0 installs
23. ▌
    Agent Topology Selector · presidenteog

    Use when deciding how to split a task across the crew roster — whether it needs one agent, several running in parallel, a sequential handoff, or a crew-lead-planned hierarchy — before dispatching, especially when a task looks like it could go to more than one crew-* agent.
    0 installs
24. ▌
    Frontend Taste Engineer · presidenteog

    Use before generating new UI/frontend code — components, landing pages, dashboards — to override the model's default drift toward generic, templated-looking interfaces. Applies measurable dials (layout variance, motion intensity, visual density) and a banned-pattern list instead of vague taste calls. Trigger on "make this look premium/distinctive", "avoid generic AI UI", or any fresh component/page generation.
    0 installs
25. ▌
    Humanizer · presidenteog

    Use when written text reads like AI output and needs to sound human — removing the tells (overused transitions, hedging, inflated vocabulary like "delve/robust/comprehensive", uniform sentence rhythm, em-dash overuse, empty summaries) while keeping the meaning. For blog posts, captions, emails, docs, scripts.
    0 installs
26. ▌
    Image Dna · presidenteog bundle

    Capture a look from references and reuse it instead of describing it from memory. Use the moment reference images, screenshots or style sets enter the conversation, before writing any prompt, render brief, CSS or token spec from them, because the usual failure is glancing at the refs and generating from impression, which drops the one detail that made the style work. Three modes. Extract (references in, structured DNA profile out). Learn (file a handed-over style into the Design library with provenance). Compose (several captured profiles plus a target asset type, conflicts resolved explicitly, one resolved token set out). Covers renders, GFX character art, thumbnails, VFX, logos, packaging, UI and HUD surfaces, button sets and full web-page designs. Triggers on match this reference, make it look like these, extract the style, design tokens from this screenshot, capture the visual DNA, saca el estilo de estas imagenes, que se vea igual que esta referencia, analiza este diseno.
    0 installs
27. ▌
    Test Seams · presidenteog

    The reference that makes a red-green loop produce tests worth keeping, what a good test is, confirming the seams under test before writing any, and the three anti-patterns that make tests break on refactors or pass by construction. Use when writing or reviewing tests, doing red-green-refactor, or deciding what to test. Complements the loop itself (superpowers:test-driven-development drives red-green); this is the quality gate on what it produces.
    0 installs
28. ▌
    Deep Modules · presidenteog

    Design vocabulary for deep modules, a lot of behaviour behind a small interface placed at a clean seam and testable through that interface. Use when designing or reshaping a module's public interface, deciding where a boundary goes, judging whether an abstraction earns its keep, or when another skill needs the module / interface / depth / seam terms. A reference to consult, not a session to run.
    0 installs
29. ▌
    Image Handoff · presidenteog

    Hand an image prompt to the user as copy-pasteable text instead of sending it through the Antigravity bridge — for pasting into gemini.google.com (Gemini 3.1 Pro image generation), ChatGPT, Midjourney, or any web image tool. Use this when the user says to give them the prompt, wants to run it themselves, mentions the Gemini website or another web UI, when the Antigravity image quota is exhausted, or when they want to see the prompt text before it gets generated. Outputs the prompt in a copy-ready block plus a manifest of which reference images to attach and which docs the prompt draws on.
    0 installs
30. ▌
    UI UX Pro Max · presidenteog

    Senior UX audit across 5 layers — first impression, task flows, visual consistency, trust signals, and business alignment
    0 installs
31. ▌
    Awesome Design · presidenteog

    Bootstrap a project's visual identity using DESIGN.md files — plain-text brand design systems that AI agents read to generate consistent UI. Pick a reference from the awesome-design-md collection or generate a custom one from scratch.
    0 installs
32. ▌
    Lm Studio Tier · presidenteog

    Use for mechanical, non-interactive work that can run on a local model instead of burning subscription tokens — bulk classification, mechanical code edits, screenshot/UI description, long-text summarization. Not for anything needing MCP servers, subagents, vault memory, or judgment calls; the local tier has none of that and is slow (seconds to minutes per call, not real-time).
    0 installs
33. ▌
    Refactoring UI · presidenteog

    Use when a UI looks amateurish or cluttered but doesn't need a redesign — spacing, hierarchy, color or type feel off and the fix should be a handful of targeted CSS/Tailwind changes, not starting over.
    0 installs
34. ▌
    Reference Hunt · presidenteog

    Use whenever the deliverable is *found* material rather than *generated* material — real examples, reference images, prior art, competitor work, source collections. Visual references first (GFX, UI, thumbnails, brand, packaging, web layout), then code/implementation examples and written sources. Gives the multi-angle query fan-out, per-source-type phrasing, the reject list, the verification rule, and where findings land. Use it on "find examples of X", "get me references for X", "who does X well", "show me how others do it", "busca referencias de X" — and use it even when the request looks like one quick web search, because firing a single query and reporting whatever ranks first is exactly the failure this prevents. Do not answer these from memory.
    0 installs
35. ▌
    Game Design Doc · presidenteog

    Use when writing or updating a Game Design Document — defining the core gameplay loop, mechanics, onboarding, and progression from a concept, or documenting an existing game's systems for a team. Trigger when a project has no GDD yet, or when a new mechanic needs a formal spec before implementation.
    0 installs
36. ▌
    Antigravity Tier · presidenteog

    Use for self-contained work that needs real reasoning capability but none of Claude Code's own tooling — research, long summaries, first drafts — where routing to Antigravity's free Gemini/Claude quota via `agy -p` costs nothing instead of burning subscription tokens. Not for anything needing MCP servers, subagents, or vault memory; agy has none of that context.
    0 installs
37. ▌
    Context Glossary · presidenteog

    Build and maintain a per-repo CONTEXT.md, a short prose dictionary of the project's domain terms the agent reads to decode jargon and name things consistently. Use when project terminology is being discussed or disputed, when naming feels inconsistent, when a hard-to-explain concept keeps needing a paragraph, or when writing or editing a CONTEXT.md or an ADR.
    0 installs
38. ▌
    Grill · presidenteog

    Relentless multi-round interview that resolves every open decision in a plan or design before building starts. Use when the user says "grill me", wants their thinking stress-tested, wants to align before implementing, or is about to start a build from a vague brief. Distinct from loose ideation and from a single clarifying question.
    0 installs
39. ▌
    Graphify · presidenteog bundle

    any input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report. Use when user asks any question about a codebase, project content, architecture, or file relationships — especially if graphify-out/ exists. Provides persistent graph with god nodes, community detection, and BFS/DFS query tools.
    0 installs