byronwall
- 22 skills
- 0 followers
- 3 hours ago last updated
- ▌ Impeccable · byronwall bundleUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
- ▌ Propose Fixes · byronwall bundleDevelop, compare, and recommend among multiple plausible fixes for a problem. Use only when the user explicitly invokes $propose-fixes or asks to use the propose-fixes skill for a bug, architecture issue, UX problem, performance concern, process failure, tooling limitation, or other general-purpose problem where several viable approaches may exist. Inspect supplied context and relevant files, but ask before running diagnostics. Present 3-5 meaningfully distinct options, score them on problem-specific dimensions, recommend one option or a deliberate hybrid, and wait for the user's decision before taking action.
- ▌ Pnpm 11 Upgrade · byronwall bundleUpgrade JavaScript and TypeScript repositories to pnpm 11 compatibility. Use when a repo is moving to pnpm 11, pnpm reports that package.json#pnpm settings are ignored, patchedDependencies stop applying, ERR_PNPM_IGNORED_BUILDS appears, build-script approvals are needed, Corepack/Docker pins are stale, or a reusable pnpm 11 migration checklist is requested.
- ▌ Orchestrate Work · byronwall bundleCoordinate substantial work from one persistent orchestrator with narrowly scoped GPT-5.6 Luna collaboration subagents. Use when Byron says `$orchestrate-work`, asks Codex to be an orchestrator, requests parallel implementation or investigation, asks to split coding from verification, or wants a coordinated feedback loop. Create a dedicated Codex task only for a new orchestrator, an explicit request for a separate task, or a wholly new scope that needs independent ownership and history.
- ▌ Agents Doc Update · byronwall bundleUpdate AGENTS.md and related documentation after implementation work. Use when the user asks to capture patterns, lessons, conventions, or reusable workflows from an extended discussion, bugfix session, refactor, or feature delivery.
- ▌ Consider Contrast · byronwall bundleCompare multiple viable approaches before an agent makes a meaningful decision. Score the options from 0 to 10 only on dimensions that are specific and relevant to the task domain, then select the best option or design a stronger hybrid. Use when the user invokes `$consider-contrast`, asks to consider and contrast alternatives, wants to avoid tunnel vision, or wants a decision checkpoint inside a larger investigation, plan, design, or implementation task. Keep this as a proportional inline step unless the user asks for a full decision report.
- ▌ Portfolio Content · byronwall bundleAdd or update project entries, blog posts, placeholders, and related images for Byron Wall's personal portfolio site at /Users/byronwall/Projects/wall-portfolio. Use when asked to create portfolio content, post a project, draft a blog page, add a placeholder page, or prepare portfolio content for auto-publishing.
- ▌ Write Byron Voice · byronwall bundleDraft, revise, or review text authored as Byron Wall in his voice. Use when Byron asks for text "in my voice" or when producing prose meant to be published, posted, sent, or attributed to him, including blog posts, project updates, essays, explanations, emails, messages, bios, and captions. Also use when converting his notes or transcripts into prose, cleaning up AI-generated text without inheriting its style, or checking a draft for fidelity to his transcript-derived language, reasoning, and technical point of view. Do not use for ordinary assistant replies, neutral documentation, code comments, or text attributed to someone else unless Byron explicitly requests his voice.
- ▌ Search Transcripts · byronwall bundleRefresh, search, review, and synthesize Byron's living v2c transcript archive without asking him to run commands or identify files. Use when Byron says "refresh transcripts", "load new transcripts", "process my voice memos", "run speech to text", "run the transcript LLM processing", "review the transcripts about...", "find the relevant ideas in...", "what did I say about...", asks whether a topic or project appears in his transcripts, or wants themes, decisions, requirements, opportunities, or changes of thinking recovered from voice memos.
- ▌ Debug UI Event Flow · byronwall bundleDiagnose and repair browser interaction regressions where pointer, click, drag, focus, selection, URL state, or visual emphasis disagree. Use for click-versus-drag bugs, pointer-capture retargeting, delegated-event ordering, background clicks that swallow target clicks, selection outlines without downstream display changes, stale click suppression, or UI behavior that passes scripted checks but fails through real mouse input.
- ▌ Token Use Diagnosis · byronwall bundleDiagnose recent local Codex or agent-thread token use by querying llmly's usage explorer, grouping results by raw tool and session, and explaining token hotspots, tool overhead, and practical process changes. Use when asked why a recent task used many tokens, to review the last hour or day of agent work, or to compare sessions without exposing full prompts or tool results.
- ▌ Product Grid Context · byronwall bundleUse when working in or around a Product Grid Management project and you need project, node, image, or graph context through the pgm CLI. This skill helps agents query context from a running Product Grid server without scraping the UI.
- ▌ Analyze Codex Threads · byronwall bundleSearch and synthesize Codex task/thread history to recover meaning, recurring goals, effectiveness, friction, repeated user steering, common errors, reusable commands or one-off scripts, missing tools, workflow gaps, and practical next steps. Use when the user asks to review, audit, mine, compare, or learn from recent Codex tasks in the current project, named projects, a date range, or across projects; asks what keeps going wrong or what they repeatedly request; wants opportunities for scripts, skills, tooling, documentation, or process improvements; or wants an evidence-based retrospective of agent work.
- ▌ Create Calendar Entry · byronwall bundleCreate and verify macOS Calendar events for Byron Wall. Use when the user asks to add, schedule, put, or create an event, appointment, meeting, activity, or reminder-like item on Byron's personal calendar or the ByronAnne joint calendar, including when event details come from a selected email, screenshot, webpage, or pasted text.
- ▌ Review Data Structures · byronwall bundleReview application data structures, fixtures, schemas, TypeScript types, persistence models, API contracts, and UI projections. Use when deciding whether current shapes are clear, durable, database-ready, easy to extend, or burdened by duplicate types and transformations. Produces direct but motivating improvements. Do not use for query-performance tuning or database operations unless data-model design is also in scope.
- ▌
- ▌ Solid Ssr Change Safety · byronwall bundlePrevent SolidJS SSR hydration mismatches during frontend edits. Use when changing components that render on both server and client, especially markdown renderers, conditional JSX, list rendering, and DOM-structure-heavy UI.
- ▌ Decompose Transcript Jobs · byronwall bundleDecompose long transcripts, dictations, voice-memo exports, brainstorming notes, and exploratory conversations into traceable jobs to be done, themes, product scope, decisions, open questions, opportunity backlogs, capability gaps, and implementation-ready planning artifacts. Use when Codex is asked to process a large transcript or memo; capture unique jobs or desired outcomes; group ideas into themes or work streams; separate committed changes from speculative ideas; map transcript goals to an existing product or repository; preserve side ideas without bloating the immediate plan; or turn loosely ordered commentary into a consistent Markdown document set.
- ▌ Test Opengraph Contact Sheets · byronwall bundleRender, collect, compare, and visually verify representative OpenGraph or social-card image variants as a labeled contact sheet. Use when creating or changing OG image routes, metadata-image templates, dynamic social previews, `ImageResponse` output, or branded share cards in any web repository, especially when several content types, fallback states, titles, descriptions, or source-image ratios must remain coherent.
- ▌ Prepare Chatgpt Pro Repo Prompt · byronwall bundleCreate copy-ready, repository-grounded prompts for ChatGPT Pro to review, research, evaluate, or plan work in a software repository. Use when a user wants to hand a GitHub repository to ChatGPT Pro, Deep Research, or ChatGPT agent. Do not use when the user wants Codex to do the repository work directly.
- ▌ Review Plan With Product Questions · byronwall bundleReview technical, architectural, migration, implementation, or refactoring plans by first asking product-level questions that resolve technical choices, then identifying the weakest, least-clear, and most failure-prone parts. Use when a user wants plan feedback grounded in product priorities rather than architecture preferences, asks what an implementation is most likely to get wrong, or wants product questions that guide engineering decisions.
- ▌ Solid Ssr Hydration Debug Playbook · byronwall bundleTroubleshoot and resolve SolidJS hydration mismatches using a comment-out and re-enable playbook. Use when seeing hydration errors, template crashes, or server/client DOM mismatch behavior.