ARS-Codex research, academic writing, manuscript review, and experiment planning. Use for deep research, literature or systematic reviews, meta-analysis, research questions, paper drafts, revisions, revision roadmaps, abstracts, citations, integrity checks, peer review, and research-to-paper workflows. Citation triggers: check citations, look over the refs, 檢查引用, 檢查參考文獻, 인용 확인, 인용 형식 검사. Korean: 논문 심사, 논문 수정, 초록 작성, 체계적 문헌고찰, 연구부터 논문까지. Español: revisión de literatura, revisar artículo, enmendar mi artículo, escribir resumen, investigación a artículo. Also use for ARS aliases: /ars-plan, /ars-outline, /ars-abstract, /ars-lit-review, /ars-citation-check, /ars-disclosure, /ars-format-convert, /ars-3w, /ars-revision-coach, /ars-revision, /ars-reviewer, /ars-mark-read, /ars-unmark-read, /ars-cache-invalidate, /ars-rebuttal-audit, /ars-full. Role prompts, references, templates, and handoff schemas live under ars/.

Batch several `/gsd-quick`-shaped tasks together — planned, dispatched, and merged as one run

Port a Retool app's functionality into a page in apps/moderator. Use when given a Retool JSON export (or asked to migrate/replace a Retool moderation tool) and a page needs to be built in the moderator app. Decodes the export, inventories its queries, and builds the page with shadcn + Tailwind under the Retool nav group.

Take a new model from nothing to mod-testable in the live generator, then hand off for launch. Orchestrates the child skills in order — add-ecosystem, write-model-description, official-model-admin, generation-coverage, generation-gate-rules, add-generation-support, add-prompt-enhancement-guide and generator-launch — and stops at each deploy. Use when onboarding a new generator model, or a new version of an official one.

Create a Draft CivitaiOfficial model and version through the API, work out whether the version is API-only or needs hosted model files (and either import those from Hugging Face or walk the user through uploading them), update an existing model's description, or transfer a model to CivitaiOfficial. Every description write requires the user's approval of the exact text, enforced by an approval hash. Use when setting up an official model or version for review before publishing, or when an official model's description needs to change. Called by onboard-generator-model; usable on its own.

Port a moderator page from the main Next.js app (src/pages/moderator/**) into apps/moderator. Use when asked to migrate, move or cut over a /moderator/* page to the spoke, or to port its tRPC procedures and Prisma services to SvelteKit loads/actions and Kysely.

Add, remove or inspect a model version's "EcosystemCheckpoints" row — the coverage override that makes a version generatable regardless of publish status — and bust the version cache so the generator sees the change. Use to make a Draft official version testable by moderators, or to drop the override after launch. Called by onboard-generator-model; usable on its own.

Reference for using the Plannotator CLI: plan review, code review, annotating files, URLs, folders, and running local apps, annotating the last assistant message, browsing archived plan decisions, and exporting or sharing Guided Reviews. Invoke when asked to use Plannotator for anything not covered by a more specific plannotator-* skill.

Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.

Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.

Interacts with live Hunk diff review sessions via CLI. Inspects review focus, navigates files, hunks, and exact lines, reloads session contents, adds inline review comments, and paints attention marks on character ranges. Use when the user has a Hunk session running or wants to review diffs interactively.

Maps the `hunkdiff/extension` authoring surface for Hunk, the terminal diff viewer — hiding or reordering reviewed files, docked panes, alternate file views, commands and key bindings, dialogs, workspace writes, themes, syntax languages, VCS backends, lifecycle events. Use when writing, debugging, or installing a Hunk extension, or when a request asks Hunk itself to behave differently. Not for reviewing a diff in a live session — that is hunk-review.

Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, profile management, policy iteration, settings, service exposure, BYOC workflows, and attached-provider inference. Covers basic through advanced multi-step workflows. Trigger keywords - openshell, sandbox create, sandbox exec, sandbox connect, logs, provider create, profile list, profile describe, provider refresh, policy set, policy get, settings, service expose, forward, port forward, BYOC, bring your own container, inference, use openshell, run openshell, CLI usage, manage sandbox, manage provider, gateway add, gateway select.

Generate sandbox security policies from plain-language requirements and optional REST API documentation. Produces L4 or fine-grained L7 network policies and ordered network middleware configuration. Use for API access rules, middleware host selection, failure behavior, or built-in and operator-run middleware attachment. Trigger keywords - generate policy, create policy, update policy, change policy, sandbox policy, network policy, API policy, security policy, allow API, restrict API, network middleware, supervisor middleware.

Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes. Use for gateway health failures, Docker/Podman runtime issues, Helm failures, Kubernetes scheduling, TLS or auth, gateway interceptors, supervisor middleware startup or runtime failures, external compute-driver sockets, VM drivers, or sandbox startup. Trigger keywords - debug gateway, gateway failing, deployment failing, helm install failing, cluster health, gateway health, gateway not starting, health check failed, sandbox pending, docker driver, podman driver, kubernetes driver, external driver, compute driver socket, gateway interceptor, supervisor middleware, middleware failed, vm driver.

Debug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM. Use for provider attachment, endpoint policy, credential substitution, topology, and migration from the removed managed inference endpoint. Trigger keywords - debug inference, managed inference endpoint, local inference, ollama, lm studio, vllm, sglang, trtllm, NIM, inference failing, model server unreachable, credential_endpoint_mismatch, host.openshell.internal.

Maintain and validate OpenShell's build-only Windows MSVC lane for x64 and ARM64. Use when working on Windows compilation, `windows:*` mise tasks, unsupported Windows compute-driver contracts, or Windows build reports. This skill does not implement Docker, Kubernetes, Podman, VM, MXC driver, policy translation, MSI, service, or supervisor runtime support on Windows.

长文任意语言互译、术语一致性、分段续跑与章节审校方法。Used by InkOS translation workers.

按题材、目标读者和用户标准审稿，展示具体问题并协作修订。Use for chapter or manuscript review with transparent criteria.

导入已有小说、逆向重建设定与续写工程，并区分母本参考。Use for importing manuscripts or attaching external canon safely.