mattmireles
- 31 skills
- 0 followers
- 6 hours ago last updated
- ▌ Research Planning · mattmirelesPlan external research for Gemma, Hugging Face, PEFT, PyTorch MPS, multimodal processors, or training behavior when current authoritative knowledge is required.
- ▌ Research Debugging · mattmirelesDebug failures that cross Gemma Tuner and external Hugging Face, Transformers, PEFT, PyTorch MPS, dataset, or model-card boundaries.
- ▌ Audit · mattmirelesTriggered when the user’s message includes the word **audit** (primary routing hook). Findings-first review of the kokoro-coreml repo or a scoped slice (paths, diff, commits)—runs pytest (and optional lint when configured) as mechanical signals, optionally delegates readonly subagents by charter when scope or risk warrants it (**when in doubt, parallelize**), merges and dedupes findings, and assigns A–F grades for architecture, correctness risk, and complexity debt. Do not use when the user wants implementation fixes unless they explicitly ask to fix issues after the audit—for plan-phase checklists against an active plan, prefer phase-audit.
- ▌ Debug · mattmirelesSystematic debugging for kokoro-coreml: consult README/ (guides and learnings) and CLAUDE.md first, pull current library docs via Context7 MCP when coremltools/PyTorch/API behavior is uncertain, parallelize investigation with multiple subagents when stuck, prove fixes before calling success, then capture one consolidated note in README/Notes via **write-notes** as the **final** step before ending the session. For extreme cases, delegate a multi-agent audit via the Claude Code CLI. Use when the user invokes **debug**, **use debug**, asks to debug or fix a tricky bug, or work is blocked by unclear failure modes after quick local checks.
- ▌ Botnet · mattmireles bundleMaster skill for managing the owner-operated Botnet Mac fleet across gist, botnet, and kokoro-coreml. Use when checking fleet health, rolling Mac workers, debugging scrape.remote_browser, tts.kokoro_coreml, or precompute workers, handling LaunchAgents, SSH fan-out, Cloudflare control-plane health, Kokoro/Core ML runtime issues, botnet fleet env vars, or writing fleet debugging notes.
- ▌ Coreml · mattmireles bundleRoute Core ML work inside kokoro-coreml without depending on a personal ~/.cursor skill. Use for conversion, numerical parity, compute-plan profiling, ANE/GPU/CPU placement, Swift SDK behavior, TTS quality, or bakeoffs. Delegate to the repo-local child skills and checked-in guides.
- ▌ Deploy · mattmirelesClarifies what “ship” means for kokoro-coreml: there is no Cloudflare-style multi-worker deploy script. Use for tagging releases, pushing the branch, coordinating with the macOS app repo, or verifying exports before handoff. Before treating a revision as releasable, run the repo’s primary checks (see git-commit / audit). Do not use when the user only wants local experiments with no remote or release intent.
- ▌ Bakeoff · mattmirelesRun the controlled bakeoff benchmark on this machine. Prepares inputs, builds the Swift pipeline, runs the counterbalanced harness for all available configs (A, D, E, F), records results, and updates performance-notes.md. Use when the user says "run the bakeoff", "benchmark this machine", or invokes $bakeoff.
- ▌ Git Push · mattmirelesCommits any pending work via git-commit, syncs with origin (fetch, merge-oriented pull), pushes the current branch, watches GitHub Actions, and fixes root causes until CI is green—including coverage gates without lowering thresholds. Use when the user asks to push, sync and push, or ship the branch and chase CI. Requires explicit invocation or a parent workflow that authorizes push and CI remediation. Do not use without permission to write to git remote or when the user forbids automated CI fix loops.
- ▌ Markdown · mattmireles bundleWrite or repair repo markdown files. Use when the task is editing README files, guides, plans, notes, or markdown lint failures. Apply the repo's markdown rules, preserve the right template or document structure, and keep prose tight. Do not use for inline code comments or code changes that only happen to touch markdown strings.
- ▌ Git Commit · mattmirelesProduces comprehensive Git commit messages (what and why) and, when authorized, stages and commits. By default stages the entire working tree (all pending changes), including work from other agents or earlier sessions—not only files the current agent touched. After a successful commit (non-blocking), runs `pytest` at the repo root when available and a **lightweight** read of **HEAD** only (bug risks, god-module smells, needless complexity, duplication)—not a full **audit** (no lint gate, no grades, no multi-agent); for that, the user invokes the **`audit`** skill. Surfacing findings as optional heads-up, never as a reason to block or unwind the commit unless the user asks. No automatic fixes. Message-only requests use the same template without running git until commit is explicitly requested. Also use inside authorized workflows (for example execute-plan phase commits). Do not use for read-only review, hypothetical history, or when git writes are not authorized.
- ▌ Audio Judge · mattmirelesJudge generated Kokoro TTS audio clips with Gemini through llm-workflows. Use when the user asks whether synthesized speech sounds good, intelligible, whispery, corrupt, or acceptable, or when comparing PyTorch reference clips against Core ML / Swift pipeline output.
- ▌ Create Plan · mattmireles bundleCreate an implementation plan for this repo. Use when the user wants a checked-in plan under README/Plans, wants the work scoped into phases, and expects the plan to be built from repo guides and notes first, with Context7 only when current external library or framework behavior materially affects the plan. Do not use for implementing the work, informal brainstorming, or lightweight notes.
- ▌ Find Papers · mattmirelesFind and validate research papers for Kokoro CoreML's TTS, vocoder, Core ML, Apple Silicon, and on-device deployment work. Use when the user asks for a bounded, source-verified paper set or literature discovery pass; do not use for a general web guide, an implementation plan, or ingesting one named paper.
- ▌ Phase Audit · mattmireles bundleAudit a completed plan phase in this repo. Use when a phase has just been implemented and needs a findings-first review against the active plan, changed files, linked guides, and the canonical audit rubric before commit or before moving to the next phase. Do not use for implementing fixes, broad product critique, or replacing tests and CI execution.
- ▌ Write Notes · mattmireles bundleWrite or update repo notes under README/Notes. Use when the user wants debugging notes, investigation notes, audit notes, or institutional memory captured in the repo. Prefer updating the right high-level notes document over creating a fresh file for every session. Do not use for plans, README guides, or inline code comments.
- ▌ Create Guide · mattmirelesCreates technical field guides by synthesizing what the public internet says about a hard, non-obvious external domain via Gemini Deep Research Max (llm-workflows create_guide_v1). A guide is a durable “afternoon of Googling” artifact for kokoro-coreml — not dial-a-friend advice, campaign go/no-go, or product decisions. Assembles research briefs, launches long-running research, saves raw drafts locally, and hands off to guide-ingest. Use when the user invokes create-guide or wants a new README/Guides field guide on an arcane mechanism.
- ▌ Create Skill · mattmirelesGuides users through creating effective Agent Skills for Cursor. Use when you want to create, write, or author a new skill, or asks about skill structure, best practices, or SKILL.md format.
- ▌ David Ogilvy · mattmireles bundleApplies David Ogilvy–style copy discipline to reader-facing text in kokoro-coreml: README and guides, bakeoff and performance narratives, CLI and script output, error messages, integration notes, and docstrings that read as product copy. Use when the user names **Ogilvy**, **copy**, **copywriting**, **marketing** language, **user-facing** strings, **empty states**, onboarding, or wants persuasive, specific prose grounded in facts. Do not use for implementation-only work with no wording decisions, pure internals with no voice requirement, or layout-only tasks.
- ▌ Execute Plan · mattmireles bundleExecute a checked-in implementation plan for this repo phase by phase. Commits land once per completed phase locally; push and CI monitoring run once after every phase is done (not after each phase). Use when the user provides a concrete plan path and wants end-to-end implementation, phase audits, plan updates, commits, push, and CI monitoring. Do not use for creating a plan, one-off fixes without a checked-in plan, or read-only review work.
- ▌ Guide Ingest · mattmirelesIngests offline deep-research exports into README guides for kokoro-coreml: cleans markdown, corrects library/API claims with Context7 when docs contradict the draft, annotates firsthand repo contradictions without stripping useful “worth trying” external synthesis, and adds bidirectional cross-links in README/Guides and README/Notes. Use for guide-ingest, research-to-guide, or corpus linking of a new guide from Deep Research / browser export.
- ▌ Paper Ingest · mattmirelesIngest one academic paper into Kokoro CoreML's README/Papers as a faithful markdown transcription with provenance and bidirectional links to relevant repository material. Use when the user asks to ingest or import a named paper, provides a PDF, or asks to repair a raw extraction. Do not use for summaries, literature discovery, or a passing citation.
- ▌ Documentation · mattmireles bundleWrite or review inline code documentation that captures domain knowledge, non-obvious constraints, non-greppable cross-file contracts, and state lifecycle. Use when the task is adding or reviewing Python docstrings, file headers, state docs, or constant rationale. Do not use for README files, markdown docs, plan documents, or code changes where comments are incidental.
- ▌ Audit Fix Loop · mattmirelesRuns the full multi-agent audit workflow on the user's exact task scope, fixes every in-scope issue that blocks Architecture, Correctness risk, or Complexity debt from grade A, re-audits that same scope until all three are A, then commits only loop-owned changes via git-commit. Use ONLY when the user explicitly invokes audit-fix-loop, $audit-fix-loop, or "use audit-fix-loop"—not for standalone audits, plan execution, whole-repo cleanup inferred from a narrow task, or implicit routing. Does not replace phase-audit or deploy gates.
- ▌ Coreml Profile · mattmireles bundleProfile Kokoro and related Core ML packages to establish actual CPU, GPU, and Neural Engine placement, latency, and silent fallback behavior. Use for device compute plans, scheduling claims, package-shape changes, warmed timing, or hardware comparisons.
- ▌ Ilya Sutskever · mattmireles bundleAdopts the Ilya Sutskever persona and judgment for on-device ML work in kokoro-coreml: PyTorch tracing, Core ML conversion, MIL/op compatibility, ANE/GPU/CPU scheduling, precision and parity validation, and bakeoffs vs reference PyTorch. Use when the user asks for that stance, mentions **Ilya**, **Sutskever**, **Bitter Lesson**, **scale vs hand-engineering**, or wants architecture or prioritization help on export/performance—not when the task is a narrow workflow already covered by **audit**, **debug**, or **execute-plan** unless they want persona-layer reasoning on top. Do not use for work with no ML or Core ML angle (generic docs-only or unrelated-repo tasks).
- ▌ Second Opinion · mattmirelesGets two independent, read-only opinions on a concrete technical decision, diagnosis, plan, or tradeoff from GPT-5.6 Sol at xhigh reasoning and Claude Fable 5 at max effort, then reconciles agreement and disagreement without treating model consensus as proof. Use when the user asks for a second opinion, says dial-a-friend, wants outside advice, or explicitly asks what Fable and GPT think. Do not use for broad internet synthesis (create-guide), implementation, or ordinary questions answerable directly.
- ▌ Coreml Validate · mattmireles bundleValidate Kokoro Core ML exports against their frozen PyTorch/reference behavior and audio-quality gates. Use for numerical parity, input/output shape drift, export regressions, CPU-fallback signals, SDK bundles, or release-readiness evidence.
- ▌ Gemini Pipeline · mattmireles bundleOperate Kokoro's direct Gemini audio-judge workflow and diagnose Gemini API transport, response parsing, rubric, and artifact-boundary failures. Use for scripts/gemini_audio_judge_direct.py, audio quality judging, judge fixtures, or Gemini API behavior; do not use for Vertex endpoint routing, Cloudflare, or generic model-export work.
- ▌ Execute Plan Hardcore · mattmirelesExecute a checked-in implementation plan like execute-plan (phase-by-phase, commits, push, CI), then run the full audit skill on the execution scope and require Architecture, Correctness risk, and Complexity debt grades all A—fix findings and repeat until all three are A. Use when the user explicitly invokes this skill or wants the hardcore post-audit gate after plan execution. Do not use for planning-only, read-only review, or when the user wants standard execute-plan without the audit-to-A loop.
- ▌ Classification Validate · mattmireles bundleValidate Kokoro experiment and listening-decision labels, gate categories, and result manifests. Use for pass/warn/fail decision records, F0 or audio listening reviews, bakeoff classifications, or preventing invented result categories. Do not use for model export numerical parity or generic data labeling.