latias94
- 31 skills
- 0 followers
- 9 hours ago last updated
- ▌ Ch Imagegen 2 · latias94 bundleGenerate or edit raster images through a running local codex-helper or OpenAI-compatible relay, including text-to-image, image-to-image, multi-image edits, masks/inpainting, streaming image responses, batch generation, 2K/4K gpt-image-2 sizing, and sub2api/NewAPI-compatible JSON or multipart OpenAI Images API requests. Use when the user asks for ch-imagegen, codex-helper image generation, local proxy image generation, OpenAI Images API generation or edits, gpt-image-2 images, image-to-image, or generated bitmap assets through the user's relay/provider chain.
- ▌ Lspi · latias94 bundleUse lspi (an MCP server) to give Codex LSP-powered semantic navigation and safe refactoring. Use this when you need symbol-level understanding (hover/definition/references/implementation/typeDefinition), or when doing a rename across a real codebase and you want a preview-first workflow.
- ▌ Upgrade Dear Imgui Stack · latias94 bundleUse when a user asks to upgrade Dear ImGui, cimgui, ImPlot, ImPlot3D, ImNodes, ImGuizmo, Dear ImGui Test Engine, or related bindings in this repository. Refresh submodules, regenerate pregenerated native/WASM bindings, audit safe Rust API and backend shim changes, update examples/docs/changelog/versioning, and validate release readiness.
- ▌ Wow Pve Spec Coach · latias94 bundle通用《魔兽世界》PvE 职业专精导师 skill。用于任意职业/专精的循环教学、天赋理解、技能与被动机制拆解、属性与装备思路、团本 Boss 处理、大秘境打法、Warcraft Logs 复盘、SimC/Raidbots 解释、高分玩家视角答疑;尤其适合用户问“这个专精怎么打”“为什么攻略这么循环”“我当前天赋该怎么理解”“日志哪里有问题”“大米/团本怎么提升”。不用于 Voidforge/R 币/宏伟宝库路线决策,那类问题交给 wow-voidforge-roll-planner。
- ▌ Wow Voidforge Roll Planner · latias94 bundle规划《魔兽世界》12.0.5 晦暗虚空核心 / Voidforge bonus roll、宏伟宝库 6 代币和本周装备获取路线。用于“这周 R 币投哪个 M+ / Boss”“低保拿装备还是换核心”“是否继续追同一去重池”“用哪个拾取专精 roll”“Hero talents / 套装 / 制作装是否改变 roll 路线”等决策;BIS、属性、WCL / Mythicstats 只作为决策依据,不输出通用职业攻略。
- ▌ Ch Imagegen · latias94 bundleGenerate or reference-edit raster images through a running local codex-helper proxy using its OpenAI-compatible `/v1/images/generations` and JSON `/v1/images/edits` bridges. Use when Codex should create bitmap images via the user's local relay/provider chain, when the built-in imagegen tool is unstable with the relay, or when the user asks for `ch-imagegen`, codex-helper image generation, OpenAI Images API generation, reference image generation, gpt-image-2 images, 2K/4K image outputs, or local proxy image generation.
- ▌ Codex Session Diagnostics · latias94 bundleDiagnoses codex-helper and Codex failures from a Codex session key by correlating helper logs, helper configuration/state, and Codex session JSONL files. Use when the user provides a Codex session id/key or asks why Codex is waiting, stuck, disconnected, failed to resume, lost continuity, or behaved differently through codex-helper.
- ▌ Merman Release · latias94 bundleMerman release operator workflow. Use when preparing a new Merman or independently versioned support-crate release, updating changelog or release notes, bumping package versions, running release preflight, creating or verifying a tag release, dispatching platform publish workflows, recovering failed release CI, or checking published registry and GitHub Release state.
- ▌ Contribute Merman Pr · latias94 bundlePrepare and validate a focused Merman pull request with change-scoped Rust, FFI, feature/dependency, generated-license, workflow, platform, and performance checks. Use when opening, updating, reviewing, or repairing a PR, deciding whether a CI gate is redundant, or handing off a branch for review.
- ▌ Writing Great Skills · latias94 bundleBuild evidence-backed, user-facing Merman release reports by comparing a configurable base release tag and target revision. Use for alpha/beta/stable release analysis, changelog-ready summaries, dependency and Cargo feature comparisons, native/WASM/Web/Node artifact sizes, Rust/Mermaid.js/mermaid-rs-renderer benchmarks, diagram-family support matrices, migration guidance, and scenario-based crate/package recommendations.
- ▌ Align Mermaid Release · latias94 bundleAlign Merman to a selected Mermaid release and its companion behavior graph. Use when changing the pinned Mermaid baseline, evaluating compatible or latest companion packages, admitting added or removed diagrams and layouts, porting upstream parser/semantic/editor/LSP/render behavior, updating Playground or reference CLI integration, or deciding whether release dependencies justify a Cargo feature split.
- ▌ Optimize Merman Performance · latias94 bundleDiagnose and improve Merman latency, throughput, memory use, input-amplification complexity, dependency closure, or artifact size with evidence matched to the claim and semantics-preserving implementation. Use when investigating a performance regression, profiling a Rust render stage, removing superlinear or attacker-controlled work, optimizing parser/layout/SVG/text paths, comparing Node N-API with Node-WASM, tuning browser WASM or CLI/native artifacts, or deciding whether a proposed fast path, cache, or refactor is a real improvement.
- ▌ Fret UI Review · latias94This skill should be used when the user asks to "review a Fret UI", "polish UX", "audit focus/overlays", or "check token drift and `test_id` stability". Provides a framework-aligned audit workflow (tokens, focus-visible, overlays, commands gating) with outcome-first findings, recommended regression gates, and evidence anchors.
- ▌ Fret Crate Audits · latias94This skill should be used when the user asks to "audit a crate", "review contract surfaces", "assess refactor hazards", or "produce a crate audit note". Provides a crate-by-crate audit workflow (purpose/exports/deps/hazards) plus a small gate set to turn findings into landable steps.
- ▌ Fret Diag Workflow · latias94 bundleRuns and triages Fret UI diagnostics via `fretboard-dev diag` (scripts, bundles, shareable artifacts, compare/triage, perf gates). Use when user asks to reproduce a flaky UI bug, write a diag script, capture/share a diagnostics bundle, triage/compare bundles, or add a perf gate.
- ▌ Fret App UI Builder · latias94 bundleThis skill should be used when the user asks to "build a Fret app UI", "refactor an existing Fret UI", "pick a theme/tokens baseline", or "compose shadcn-style recipes". Provides a product-oriented workflow (style → recipes → UX polish → gates) to ship a cohesive, usable UI with early regression protection.
- ▌ Fret Boundary Checks · latias94This skill should be used when the user asks to "run layering checks", "verify crate boundaries", "prevent winit/wgpu leakage", or "refactor across crates safely". Provides a guardrail workflow (layering checks, forbidden-dep spot checks, drift reports) to keep contract crates portable during refactors.
- ▌ Fret Skill Evolution · latias94 bundleThis skill should be used when the user asks to "turn a fix into a skill", "capture reusable learnings", "write/refresh a Fret skill", or "add a regression gate + evidence". Provides a workflow to convert tricky fixes into repeatable skills with tests/diag scripts and evidence anchors.
- ▌ Fret Skills Playbook · latias94 bundleThis skill should be used when the user asks to "write or update a skill", "define regression gates", "add a diag script", or "standardize `test_id` conventions". Provides shared conventions for execution-mode selection, goal-backward verification, layering decisions (mechanism vs policy), regression gate types, diag scripts, and evidence discipline.
- ▌ Fret Repo Orientation · latias94This skill should be used when the user asks to "find the right crate/layer", "locate entry points", "choose the smallest runnable target", or "get oriented in the Fret repo". Provides a navigation workflow to map an intent to the correct layer and pick the fastest runnable demo/harness to iterate.
- ▌ Fret External App Mode · latias94This skill should be used when the user asks to "use Fret from an external app repo", "run Fret mono-repo tooling from another project", or "keep evidence anchors clickable". Provides a workflow for applying Fret skills outside the mono-repo, including what works without `tools/`/`fretboard` and how to bridge when needed.
- ▌ Fret Perf Optimization · latias94This skill should be used when the user asks to "optimize UI performance", "investigate jank", "create a perf baseline", or "attribute worst-frame hitches". Provides a perf workflow (tail vs typical, suite normalization, worst-bundle attribution) to land reversible optimizations with evidence and gates.
- ▌ Fret Perf Tracy Bridge · latias94This skill should be used when the user asks to capture Tracy traces, profile a worst-frame hitch, or correlate `diag perf` bundle evidence with a timeline. Bridges Fret's perf gates (diag perf + bundles) with Tracy profiling: reproduce worst bundles, capture traces, map spans to bundle stats, and add low-overhead instrumentation safely.
- ▌ Fret Workstream Lifecycle · latias94 bundleThis skill should be used when the user asks to "start a new workstream", "resume a fearless refactor lane", "record workstream progress", "split a narrow follow-on", or "close out a lane". Provides a lightweight workstream lifecycle for Fret: scaffold the right docs, keep lane state explicit, resume existing lanes with an assumptions-first evidence pass, attach repro/gate/evidence to each slice, and leave closeout notes without reopening scope by accident.
- ▌ Fret Shadcn Source Alignment · latias94 bundleAlign shadcn/ui v4 + Radix behavior and composition to Fret. Default visual parity targets the current `new-york-v4` registry source unless the user names another style; semantics still follow Radix/Base UI. Use when user says "align shadcn", "parity mismatch", "match Radix", "port shadcn v4", or reports issues like "items-stretch", "w-full", "hit box too big", or layout/interaction drift. Maps fixes to the correct layer (mechanism vs policy vs recipe) and locks outcomes with goal-backward proof notes, focused tests, and `fretboard diag` scripts.
- ▌ Fret Fixture Driven Harnesses · latias94 bundleThis skill should be used when the user asks to "convert a large test matrix", "reduce god test files", "add fixture-driven conformance", or "make repetitive scenarios reviewable". Provides a workflow for JSON fixtures + thin Rust runners (shadcn/Radix conformance, overlay placement matrices) to reduce merge conflicts and keep behavior reviewable.
- ▌ Fret Framework Consumer Audit · latias94 bundleThis skill should be used when the user asks to "find problems from a Fret user's perspective", "audit developer experience", "build real examples to expose framework friction", or "review onboarding/examples/scaffolds/API ergonomics". Provides a task-driven workflow that simulates framework consumers shipping a small app slice, records friction by owner layer, and turns the top issues into gates, docs/example fixes, or refactor lanes.
- ▌ Fret Mobile Real Device Debug · latias94This skill should be used when the user asks to "debug on real mobile devices", "run the smallest Android/iOS target", "verify Vulkan/Metal constraints", or "capture mobile diagnostics evidence". Provides a real-device workflow (Android + iOS) to reproduce issues, capture bundles, and archive evidence for ADRs/workstreams.
- ▌ Fret Material Source Alignment · latias94 bundleThis skill should be used when the user asks to "align Material 3 components", "port Material 3 (Expressive)", "match MUI/Compose Material behavior", or "build a Material design-system layer" for Fret. It provides a source-of-truth workflow that treats Material spec + MUI + Compose Material3 + Base UI as parallel references with explicit axis-based precedence, prefers local `repo-ref/` mirrors when available, and maps changes to the correct Fret layer with goal-backward proof notes, targeted tests, and `fretboard diag` scripted repros.
- ▌ Fret Release Check And Publish · latias94 bundleThis skill should be used when the user asks to "prepare a release", "publish crates", "debug release-plz failures", or "validate release-plz config/workflows". Provides a release readiness and publish workflow for Fret using `release-plz` + crates.io (scope selection, dry runs, CI troubleshooting).
- ▌ Fret Framework Maintainer Guide · latias94 bundleThis skill should be used when the user asks to "land a framework change", "change a hard contract", "update/add an ADR", "add diagnostics/perf gates", or "do upstream parity work". Provides a contract-first maintainer playbook for safe evolution (ADRs, boundaries, goal-backward verification, diag/perf, shadcn/Radix/Base UI alignment, evidence discipline).