hyperb1iss

Use this skill before any creative work - new features, architecture decisions, project inception, or design exploration. Activates on mentions of brainstorm, ideate, design session, explore options, what should we build, how should we approach, let's think about, new feature, new project, architecture decision, or design exploration.

Use this skill for complex git operations including rebases, merge conflict resolution, cherry-picking, branch management, or repository archaeology. Activates on mentions of git rebase, merge conflict, cherry-pick, git history, branch cleanup, git bisect, worktree, force push, or complex git operations.

Use this skill when orchestrating multi-agent work at scale - research swarms, parallel feature builds, wave-based dispatch, build-review-fix pipelines, or any task requiring 3+ agents. Activates on mentions of swarm, parallel agents, multi-agent, orchestrate, fan-out, wave dispatch, research army, unleash, dispatch agents, or parallel work.

Use this skill when gathering knowledge at scale before making decisions - technology evaluation, SOTA analysis, codebase archaeology, competitive analysis, or any investigation requiring multiple sources. Activates on mentions of research, investigate, evaluate options, what's the best, compare alternatives, state of the art, deep dive, explore the landscape, or find out how.

Use this skill when writing or polishing a pull request description — drafting a PR body, opening a PR, rewriting a weak one, or when asked to make a PR "good" or "a banger". Produces reviewer-first descriptions that lead with why, prove every claim with evidence, name the load-bearing files and invariants, and stay honest about blast radius. Activates on mentions of write a PR, PR description, draft a PR, open a pull request, polish this PR, make this PR good, banger PR, PR body, describe these changes, or PR writeup.

Use this skill for cross-model code reviews where a different AI model reviews code written by the current model. Activates on mentions of cross-model review, peer review, second opinion, review my code, review this PR, review changes, independent review, unbiased review, different model review, cross-check code, or code review.

Use this skill for code reviews using the Codex CLI from a Claude-hosted session. Activates on mentions of codex review, code review with codex, codex check, gpt review, codex exec review, run codex, review my code, review this PR, review changes, peer review, or second opinion.

Use this skill when writing code, building features, fixing bugs, refactoring, or any multi-step implementation work. Activates on mentions of implement, build this, code this, start coding, fix this bug, refactor, make changes, develop this feature, implementation plan, coding task, write the code, or start building.

This skill should be used when working on the Hypercolor daemon, REST API, WebSocket protocol, or render pipeline. Triggers on "daemon route", "API endpoint", "WebSocket channel", "event bus", "render pipeline", "device lifecycle", "AppState", "adaptive FPS", "HypercolorBus", "backend manager", "daemon config", "MCP tool", "daemon startup", or any work in crates/hypercolor-daemon/ or crates/hypercolor-core/src/engine/.

This skill should be used when creating, modifying, or debugging RGB lighting effects for Hypercolor or LightScript-compatible engines. Triggers on "create an effect", "write a lighting effect", "design LED colors", "fix washed out colors", "port a shader to LEDs", "why does this look bad on LEDs", "color palette for RGB", "effect looks white", "colors too bright", "effect flickering", "design a palette for keyboard", "LED animation", or any work involving HTML canvas effects, LED color science, gamma correction, or the Hypercolor SDK effect pipeline.

This skill should be used when researching device protocols before implementing drivers. Triggers on "reverse engineer protocol", "research device", "find protocol docs", "USB capture", "Wireshark USB", "how does this device work", "capture USB traffic", "document wire format", "write a protocol spec", "what protocol does this use", "add support for new device", "new device driver", or any pre-implementation research for crates/hypercolor-hal/ drivers.

This skill should be used when writing, porting, or debugging device drivers in hypercolor-hal. Triggers on "add a driver", "port a driver", "implement protocol", "device not working", "wire format", "encode frame", "USB HID packet", "zerocopy struct", "CommandBuffer", "device database entry", "transport type", "frame encoding", "protocol implementation", "add device support", or any work in crates/hypercolor-hal/.

Use this skill when an agent needs to inspect or control a running Hypercolor daemon, browse or activate effects, patch live controls, adjust brightness, manage scenes or profiles, or install built HTML effects from an authoring workspace. Triggers on "hypercolor", "list effects", "apply effect", "patch controls", "install effect", "rescan effects", "brightness", "scene", "profile", or any request to control the daemon from Claude Code.

This skill should be used when working on the Hypercolor web UI in crates/hypercolor-ui/. Triggers on "UI component", "Leptos signal", "WASM build", "Trunk build", "WebSocket frame", "canvas preview", "effect card", "control panel", "device page", "SilkCircuit token", "theme switching", "sidebar", "layout builder", "Leptos context", "web-sys binding", "UI state", "optimistic update", "WebGL texture", "toast notification", "command palette", "color wheel", "device pairing", "leptoaster", or any work in crates/hypercolor-ui/.

This skill should be used when writing Rust-native effects for Hypercolor's native rendering path. Triggers on "native effect", "builtin effect", "Rust effect", "EffectRenderer", "FrameInput", "tick function", "audio reactive Rust", "canvas fill", "effect renderer trait", "write a new effect", "builtin audio pulse", "breathing effect", "color wave", or any work in crates/hypercolor-core/src/effect/builtin/.

Use for fastboot operations, flashing partitions, bootloader unlocking, recovery mode, or partition management. Triggers on "fastboot", "flash boot.img", "unlock bootloader", "recovery mode", "TWRP", "Magisk", "partition", "sideload", "A/B slots". WARNING - These operations can brick devices if done incorrectly.

Use when building Android apps (Gradle CLI) or ROMs (AOSP, LineageOS). Triggers on "gradle build", "assemble", "AOSP", "LineageOS", "lunch", "mka", "breakfast", "brunch", "compile android", "device tree", "kernel build".

Use when working with Android devices via ADB - connecting devices, running shell commands, installing apps, debugging, taking screenshots, UI automation, viewing logs, analyzing crashes, or exploring system internals. Triggers on "adb", "logcat", "install apk", "debug android", "android device", "shell command", "screenshot", "dumpsys", "crash", "ANR".

Use when working with LineageOS custom ROM development, including syncing sources, building, device trees, repopick, Gerrit contributions, or LineageOS-specific features. Triggers on "LineageOS", "lineage-sdk", "breakfast", "brunch", "repopick", "vendor/lineage", "lineage.dependencies", "mka bacon".

Persistent memory and task coordination for this project. Invoke for any prompt about past work, project state, in-progress tasks, prior decisions, gotchas, or capturing a non-obvious learning. Also covers semantic search across project knowledge and external docs.

Audit recent agent transcripts (Claude Code and Codex) to learn how a tool, system, or skill is actually being used in the wild. Surfaces failure modes, friction, success patterns, and concrete improvement candidates from real session data. Use this when you want to improve a developer-facing system that agents interact with regularly.

This skill should be used when the user asks to "configure moon", "set up moonrepo", "create moon tasks", "run moon commands", "configure moon workspace", "add moon project", "moon ci setup", "moon docker", "moon query", "migrate to moon v2", or mentions moon.yml, .moon/workspace.yml, .moon/toolchains.yml, moon run, moon ci, or moonrepo in general.

This skill should be used when the user asks to "install proto", "configure proto", "manage tool versions", "pin versions", "set up .prototools", "install node version", "install rust version", "install python version", "proto plugins", or mentions proto commands, .prototools file, or multi-language version management.

This skill should be used when the user asks to "manage UniFi devices", "configure UniFi networks", "create a VLAN", "provision an SSID", "create firewall rules", "reorder firewall policies", "create a NAT rule", "set up port forwarding", "configure masquerade NAT", "add DNS records", "manage traffic matching lists", "create DHCP reservations", "list DHCP reservations", "block a client", "kick a client", "find a client by IP or name", "adopt a device", "restart a UniFi device", "cycle a PoE port", "upgrade device firmware", "run a speed test", "stream UniFi events", "watch real-time events", "query UniFi stats", "analyze DPI traffic", "enable DPI", "generate hotspot vouchers", "show network topology", "audit firewall policies", "create a backup", "call the raw UniFi API", "check network health", or any task involving UniFi network infrastructure management via the unifly CLI. Also triggers on mentions of unifly, UniFi, Ubiquiti, UDM, UCG, USG, USW, UAP, UXG, UNVR, U6, U7, or UniFi controller operations.

Use this skill when generating commit messages, pull request descriptions, release notes, changelogs, or code reviews in a repository where git-iris is available. Activates on requests like "commit this", "write a commit message", "draft a PR", "generate release notes", "write a changelog", or "review my changes" when git-iris is on PATH.

This skill should be used when the user asks to "publish to dev.to", "hypercast", "syndicate a post", "cross-post to dev.to", "push to dev.to", or mentions publishing blog content to external platforms. Converts hyperbliss.tech blog posts to dev.to format and publishes as drafts via the Forem API.

Build, edit, verify, or present an interactive Prezzer deck — the Bun-native React presentation engine that compiles a talk into one offline HTML file. Use whenever the work involves a Prezzer deck or a repository scaffolded by `bun create prezzer`, and for any mention of slides, beats, speaker notes, presenter chrome, deck widgets, slide transitions, deck theming, deck outlines, or standalone HTML deck builds, even when prezzer is not named explicitly.

Automate Ghostty terminal sessions via MCP. Use when you need to send commands to terminals, read terminal output, capture screenshots, resize windows, open new tabs/windows, or interact with TUI apps like Neovim, htop, or any CLI tool running in Ghostty.