shawnxxxqazwsx
- 23 skills
- 0 followers
- 3 hours ago last updated
- ▌ Hatch Pet · shawnxxxqazwsx bundleCreate, repair, validate, visually QA, and package Codex-compatible v2 animated pets from character art, generated images, company or prospect brand cues, or visual references. Use for any new Codex pet, custom mascot, non-pixel pet style, brand-inspired pet, existing-pet repair, or 8x11 spritesheet workflow requiring all 9 standard animation rows, 16 look directions, deterministic assembly, QA artifacts, and spriteVersionNumber 2 packaging.
- ▌ Max Synth · shawnxxxqazwsx bundleBuild synthesizers in Cycling '74 Max / Max 9 with Max (event) and MSP (audio) objects: oscillators, filters, envelopes, MIDI, poly~, MC wrapping, gen~, and Max 9 ABL DSP. Use when the user asks to patch a synth in Max, MaxMSP, MSP, Max for Live, or mentions cycle~, saw~, adsr~, poly~, dac~, subtractive/FM/wavetable synthesis, or the MaxMSPMCP tools. Do not use for JUCE/VST C++ synths, generic DAW mixing, or Jitter-only visuals.
- ▌ Unity Dev · shawnxxxqazwsx bundleDevelop, debug, refactor, and verify Unity projects in C#, including MonoBehaviour, ScriptableObject, scenes, prefabs, assembly definitions, shaders, Editor tooling, and Unity tests. Use when the request explicitly concerns Unity or the repository is identifiable as a Unity project from Assets/ plus ProjectSettings/ProjectVersion.txt. Do not use for non-Unity repositories that merely contain an Assets directory, or for Codex/AGENTS.md bootstrap-only requests handled by unity-init.
- ▌ Goal Guard · shawnxxxqazwsx bundleApply evidence and progress guards to an active Codex Goal without replacing its lifecycle. Use when the user explicitly asks to guard a goal, prevent false-green checks or empty goal turns, audit completion evidence, coordinate parallel goal work, or diagnose repeated goal turns and blockers.
- ▌ Mc Patcher · shawnxxxqazwsx bundleDevelop, diagnose, build, review, and verify the mc-patcher C++/JUCE repository. Use only when the current repository is identifiable as mc-patcher or the user explicitly asks to work on or apply mc-patcher; do not trigger for generic JUCE, VST3, or audio-product research. Covers MC Host, MC Bridge, multichannel routing, shared-memory IPC, Q-Link, wet return, latency, VST3/WaveShell hosting, realtime safety, targeted validation, explicit deployment, and honest reporting of untested DAW paths.
- ▌ Unity Init · shawnxxxqazwsx bundleBootstrap or repair Codex guidance for an existing Unity repository by inspecting its Unity version, packages, render pipeline, layout, and validation commands, then creating or carefully merging a root AGENTS.md. Use when the user asks to initialize, bootstrap, or configure Codex for a Unity project. Do not trigger merely because AGENTS.md is absent.
- ▌ Daw Control · shawnxxxqazwsx bundleSafely inspect, operate, troubleshoot, and verify common DAWs, especially REAPER and Nuendo/Cubase. Use for project, track, routing, plug-in, transport, rendering, and DAW-based validation tasks; not for changing source code or modeling hardware DSP by itself.
- ▌ Save Tokens · shawnxxxqazwsx bundleReduce context and tool-token cost in Codex while preserving correctness and required verification. Use when the user explicitly asks to minimize tokens, cost, context growth, tool output, or repeated exploration on a coding, research, review, or migration task.
- ▌ Orchestrator · shawnxxxqazwsx bundleCoordinate complex multi-model development work when independent evidence, implementation, verification, or review packages can improve the outcome. Use for cross-module work, shared-resource risk, uncertain diagnosis, or an explicit request to split, self-check, or coordinate parallel work. Do not use for simple local changes or explanations.
- ▌ Utility Chat · shawnxxxqazwsx bundleA user-invoked mode for non-product-coding utility work such as Codex skills, plugins, configuration, AI tooling explanations, local setup audits, and source-backed research synthesis. Use only when the user explicitly invokes $utility-chat or says utility/杂活 mode. Route work to the relevant installed skill instead of duplicating its workflow. Do not trigger merely because a request is miscellaneous, and do not use as a substitute for a repository's domain skill during substantial implementation.
- ▌ Web Research · shawnxxxqazwsx bundleProfessional multi-source web research with verified live URLs and papers (fetch before cite). Auto-apply for technical docs, APIs, papers, product compare, market pricing, policy tables, obscure-entity/media hunts, or when the user attaches @web-research / says 调研 / 全面调研 / look up sources. For OpenAI and Codex product questions, use the official-source `openai-docs` workflow instead.
- ▌ Midi To Score · shawnxxxqazwsx bundleInterpret performed MIDI and write a musician-readable score with AI-authored rhythm, voices, spelling, expression, transposition, and layout, producing a score plan and MusicXML instead of trusting a DAW's automatic notation. Use for Studio One or other DAW MIDI-to-score work; do not use for audio-only transcription unless reliable note data is first derived.
- ▌ Vst Plugin UI · shawnxxxqazwsx bundleDesign, review, and implement user interfaces for audio plug-ins and standalone audio hosts — VST3/AU/CLAP editors, JUCE LookAndFeel, WebView/WebUI (HTML/CSS/JS, React, Rive, Spline), faceplates, knobs, faders, meters, plug-in browsers, mixer or Q-Link consoles, complex material/graphic systems, resizable HiDPI layouts, accessibility, palettes, and processing visualizers. Use when a request concerns an audio-plugin or audio-host GUI, WebUI/WebView surface, MC Host skinning, references the UI, interaction, or visual language of products such as FabFilter, Valhalla, or Baby Audio, or asks to turn an audio-product brief into a wireframe, mockup, critique, or JUCE/Web implementation. Do not use for DSP-only work or generic marketing websites.
- ▌ Immersive Audio · shawnxxxqazwsx bundleAnalyze and plan spatial-audio formats, conventions, recording, rendering, evaluation, delivery, standards, papers, and datasets across channel-, object-, scene-, and sound-field-based systems. Use when a request has a spatial or immersive audio component; do not trigger for generic audio work or general paper searches.
- ▌ Session Handoff · shawnxxxqazwsx bundleCreate or resume a continuation brief for moving work to a new Codex task or continuing later. Use when the user asks for a handoff, 交接, continuation summary, saved state, fresh-task context, a new task that preserves current progress, or resuming work from a saved handoff.
- ▌ Task Brief Refiner · shawnxxxqazwsx bundleClarify what the user wants through a focused conversation, then synthesize the settled requirements into an accurate, self-contained instruction for an AI. Use when the user asks to work out their requirements, refine or audit a vague idea or prompt, be interviewed about a task, or summarize a discussion into a final instruction across planning, creative, research, administrative, and technical work. Do not trigger merely because an ordinary request could be more detailed, and do not execute the resulting instruction unless the user also asks for execution.
- ▌ Skill Retrospective · shawnxxxqazwsx bundleAutomatically review Codex task history when the user says a skill, workflow, verification step, or agent failed to activate or behaved incorrectly; when the user re-reports a problem that the active workflow previously claimed fixed or verified; when an active user-owned workflow reaches an evidence- backed learning gate; or when the user asks to audit or improve skills. Also recover durable lessons after visible compaction. Update the narrowest user- owned skill, or create one only when no existing skill fits. Do not trigger for a first ordinary bug, a one-off correction, task length alone, or a mere milestone, and never modify system- or plugin-owned skills.
- ▌ Audio Render Forensics · shawnxxxqazwsx bundleCompare same-program Original, Target, and Current audio renders with alignment, normalized residual, dynamics, spectral, stereo, loudness, plots, and machine-readable evidence. Use for forensic evaluation of mastering or DSP renders. For spatial audio, first freeze conventions with immersive-audio. This skill does not prove DAW routing, deployed binary identity, or live plug-in acceptance.
- ▌ Pigora Eq Audit · shawnxxxqazwsx bundleAudit deployed Pigora EQ plug-ins with a detailed, reproducible control and response matrix. Use for post-deployment verification, comprehensive module audits, or targeted rechecks of user-reported curve defects. Covers Bell, shelves, HPF/LPF, native modes, interpolation, automation and installed audio. Do not use for routine fitting, automatic full audits after every build, or GUI-only review.
- ▌ Varimu Neural Training · shawnxxxqazwsx bundlePlan, coordinate, execute, audit, package, and publish neural or hybrid training for the captured Manley Variable Mu data. Use when preparing a training-ready batch, selecting a causal model and losses, coordinating multiple machines through GitHub claims, monitoring for new capture batches, validating each usable model with Original/Target/Current audio-render forensics, or sealing a completed model/data/annotation bundle. Do not use to grant dataset eligibility, to mix primary and comparison-only targets, or to claim hardware equivalence without independent withheld evidence.
- ▌ Hardware Audio Emulation · shawnxxxqazwsx bundleResearch, design, implement, review, and validate hardware-inspired or hardware-matched audio DSP in mc-patcher: EQ and tone stacks, colour stages, dynamics, tape, transformers, amplifiers, cabinets, analog delay/modulation, electromechanical reverb, converters, and synth circuits. Use for measured-response, source-constrained, behavioral, circuit-informed, gray-box, or neural virtual-analog work. Do not use for clean utility DSP, hosting/IPC/routing, GUI-only work, or generic audio research without a hardware-emulation target.
- ▌ Pigora Public Fit Training · shawnxxxqazwsx bundleResearch, fit, and validate Pigora hardware-EQ magnitude responses against frozen public evidence or owner-authorized inference targets. Use for target extraction/completion, coefficient or control-law fitting, and response acceptance. Keeps public-fit, inference engineering, and product readiness separate. Do not use for GUI-only work or private-capture training.
- ▌ Hardware Compressor Capture · shawnxxxqazwsx bundlePlan, run, audit, and package calibrated input-output captures of physical analog compressors, limiters, and levelers for measured-response, gray-box, or neural plug-in modeling. Use for converter calibration, stimulus and parameter design, long-memory and stereo-link identification, dataset QA, repeatability, and model handoff. Do not use for ordinary compressor mixing advice, software-only preset matching, or DSP implementation after an accepted capture set already exists.