编码规范、框架、重构、代码审查（1.8万 个）
This skill should be used when the user asks to "dev-navigate", "どこから始めれば", "何を使えばいい", "スキルを選んで", "ナビ", "navigate", "which skill", "how to start", "開発の進め方", "何から始める". 開発者がやりたいことをヒアリングし、最適なtsumikiスキルとその実行順序をナビゲーションする。
中文简介正在准备中。当前显示原文说明。
通过先编写测试、确认失败，再添加使测试通过的代码来实现开发任务。支持按计划实施和小型修复，并检查代码质量，记录设计决策依据及需要人工确认的部分。
MG 动态图颗粒铺轨器——成片 SOP 第 ⑤ 步（**最后叠上**），在 B-roll 底轨三源（影视素材 / 本地素材 / AI 情景片段）全部铺齐、且 ④ 全局抽帧检查构图通过之后，把栏目的 html-particle 动态图颗粒（透明叠加 / 满屏底层）叠铺到已定稿的底轨之上。先由栏目 MG 生产 skill 按派单各槽位产颗粒，再驱动 `gtrk mg` 命令 lint + 铺进 `.gtrk` 工程的 beat_track。当用户想「铺 MG 颗粒 / 上动态图 / 铺动效 / 给这段配动画铺进工程 / 把 MG 派单铺轨 / 消费 dispatch.mg」时使用本 skill。凡涉及把 MG 动态图颗粒铺进已剪好的成片工程，优先用本 skill 驱动 gtrk CLI，别让用户自己去终端敲 `gtrk mg`。
中文简介正在准备中。当前显示原文说明。
视觉拆分派单器——把一条已剪好的口播工程（gtrk + transcript）拆成 beat 级「视觉拆分稿」，为每个连续文稿段指定唯一主层（A_ROLL 真人出镜 / MG 动态图 / AI_DRAMA 再现 / FILM_BROLL 影视素材）+ 辅助层，产机器可消费的派单清单（MG 槽位 / B-roll 检索队列 / AI 动画队列）驱动后续铺轨。当用户想「文稿视觉化拆分 / 视觉拆分稿 / beat 时间线 / 派分镜 / A-roll B-roll 分配 / 哪些段做动态图·哪些做 AI 情景动画·哪些用影视素材 / 给这条口播派单」时使用本 skill。凡涉及把口播成片拆成分镜派工，优先用本 skill 驱动 gtrk CLI 的 `split` 命令，绝不手写时码、绝不抄原文定位。
中文简介正在准备中。当前显示原文说明。
Vlog 纪实类一站式成片图纸——纪实 Vlog 是散文的载体：用有限的素材，把一个故事、或一个几个思想，串联起来（形散神不散）。表达形态上是「现场同期声 × 后期旁白」双声道交替，区别于纯口播链（单一对镜说）与纯配音链（全片旁白配 B-roll）：同期声片段是内容本体不是配画，旁白只做定调层。当用户想「做一条纪实 vlog / 我拍了一堆素材想做成有深度的 vlog / 探店探险探厂记录 / 日常生活流做成片 / 旅途记录 / 野采野钓记录 / 城市漫游 citywalk / 圣地巡礼 / 取景地探访 / 挑战企划记录」时使用本 skill。凡涉及把带同期声的现场素材做成纪实成片，优先用本 skill 编排 gtrk CLI 全链，不要手搓单命令、别让用户逐步驱动。
中文简介正在准备中。当前显示原文说明。
Reference for the dpella/mcp Haskell library — types, handler shape, transports, and the conventions Emanote uses. Load this before adding MCP resources/tools/subscriptions so you don't re-discover the API by WebFetch.
中文简介正在准备中。当前显示原文说明。
Review code for quality, simplicity, and common mistakes before declaring work complete.
中文简介正在准备中。当前显示原文说明。
Run /be's review gauntlet SERIALLY — /lens-debate (lowy ⇄ hickey), then /codex-debate, then /simplify, then code-police, each editing and committing on the live branch in turn. Use from /be §4, or when the user asks to "run the review gauntlet". Requires Claude Code's Skill tool.
中文简介正在准备中。当前显示原文说明。
Run an automated codex⇄Claude debate to consensus — no round cap, no deadlock exit. Two explicit subcommands. `review` (also the bare/back-compat default) — codex (reviewer) critiques the current diff and a Claude subagent (author) fixes/disputes, looping until they agree. `answer` — Claude and codex each answer a freeform prompt in parallel, then cross-check until they agree, and a unified answer is returned. Use when the user types `/codex-debate`, asks to "have codex review this", "run the codex debate", "review this PR with codex", "argue this with codex until you agree", or passes a question to "have Claude and codex debate/answer until they agree".
中文简介正在准备中。当前显示原文说明。
chrome-devtools-mcp launcher — a single bash script that resolves Playwright's bundled Chrome-for-Testing and Node.js directly through Nix. See repo README for usage, override mechanisms, and version compatibility.
中文简介正在准备中。当前显示原文说明。
How a downstream app consumes the shared @kolu/surface stack (@kolu/surface · surface-app · surface-nix-host · surface-mcp) — declaring a typed reactive surface, serving it, consuming it (SolidJS hooks or a CLI), and mirroring a remote surface over ssh. Grounded in the real consumers: kolu, pulam-web, drishti, odu, and the TUIs. Load when wiring a surface server/client/mirror, or reaching for getHostSession / a link / the `.use()` hooks. CHANGING the framework is gated separately — `.claude/rules/surface.md` (a paired, CI-green drishti PR pinned to final kolu HEAD).
中文简介正在准备中。当前显示原文说明。
Write engaging PR titles and descriptions for any forge (GitHub today; Bitbucket planned). Use when creating or updating PRs. Leads with narrative paragraphs and reaches for lists, tables, and diagrams when content is genuinely structured.
中文简介正在准备中。当前显示原文说明。
odu MCP server launcher — drive CI from a coding agent. `bin/serve` resolves odu via Nix and runs `odu mcp` in the cwd. See the repo README for the tools/resources and override knobs.
中文简介正在准备中。当前显示原文说明。
Create, inspect, and safely update project-scoped ReachAI Agents; edit and publish Supervisor config drafts; discover published bindable Skills; and attach or detach exact Skill versions through the Agent AI Coding REST API. Use when an AI coding tool is asked to add an Agent, configure its model or prompt, bind a Skill, remove a Skill binding, or attach a published Workflow as a Tool.
中文简介正在准备中。当前显示原文说明。
Get current weather and forecasts (no API key required).
中文简介正在准备中。当前显示原文说明。
Create a skill or bring an existing one up to the same standard (validate + asm eval fix loop); run evals, tune triggering. Use when authoring, fixing, or retrofitting a skill. Don't use for invoking skills, writing prose, or Python scaffolds.
中文简介正在准备中。当前显示原文说明。
Improve an open-source GitHub skill and open a friendly suggestion PR upstream: fork, run skill-creator's retrofit, attach asm eval before/after metrics. Don't use for local-only skills, authoring from scratch, bulk repos, or registry publish.
中文简介正在准备中。当前显示原文说明。
Refactor a too-long SKILL.md by progressive disclosure: measure token cost, classify every section KEEP/CUT/MOVE, shorten the body into references/ and scripts/, verify nothing was lost. Don't use for authoring new skills, eval retrofits, or prose.
中文简介正在准备中。当前显示原文说明。
Use when implementing any new feature or fixing any bug in this project — both Rust (src-tauri) and TypeScript/Svelte 5 (src). Triggers on phrases like "add X", "fix Y", "implement Z", "change how W works".
中文简介正在准备中。当前显示原文说明。
Cavekit specification-driven development methodology — the Hunt lifecycle (Draft → Architect → Build → Inspect → Monitor) and how to apply it. Use when starting a Cavekit project, structuring an existing codebase as kits/plans, or routing between sub-skills.
中文简介正在准备中。当前显示原文说明。
Configure or diagnose access to a requested source using available host tools. Use for source MCP setup; source configuration needs no engagement record and credentials stay with the host.
中文简介正在准备中。当前显示原文说明。
Plan how to earn customer trust and appropriate access. Use when credibility, permissions or AI policy constrain the engagement.
中文简介正在准备中。当前显示原文说明。
Triage an outage, loss of stakeholder trust or a failing engagement direction. Use for urgent recovery; distinguish diagnosis from authorized production mitigation.
中文简介正在准备中。当前显示原文说明。
Investigate a failure, regression or incorrect result in an integration or application, even before it can be reproduced. Use for diagnosis and repair; follow incident authority for live mitigation.
中文简介正在准备中。当前显示原文说明。