Skills for “task”

…README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized…

…README-first deep learning repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment, checkpoint and dataset path assumptions, cache location hints, and setup notes before…

飞书日历：管理日历日程和会议室。查看/搜索日程、创建/更新日程、管理参会人、查询忙闲和推荐时段、预定会议室。当用户需要查看日程安排、创建/修改会议、查询/预定会议室时使用。不负责：查询过去的视频会议记录（走 lark-meeting）、待办任务（走 lark-task）。

…messages/reactions/chat changes, Approval status changes, Task updates, VC meeting started/joined/ended, Minutes generated, Whiteboard updated, Drive doc comment notices, etc.). Use for Lark bots, real-time message…

日程待办摘要：编排 calendar +agenda 和 task +get-my-tasks，生成指定日期的日程与未完成任务摘要。适用于了解今天/明天/本周的安排。

飞书审批：查询和处理审批待办/已办/实例，搜索可发起审批定义、查看定义详情并发起原生审批实例。当用户要处理审批任务、查看审批实例、搜索或发起审批时使用。审批待办不是飞书任务；非审批类待办走 lark-task。不负责创建审批定义；三方审批定义不走原生提单。

飞书 OKR：管理目标与关键结果。查看和编辑 OKR 周期、目标、关键结果、对齐关系、量化指标和进展记录。当用户需要查看或创建 OKR、管理目标和关键结果、查看对齐关系时使用。不负责：待办任务管理（lark-task）、日程/会议安排（lark-calendar）、绩效评估

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in…

…candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of `current_research` with auditable…

Use when you have a spec or requirements for a multi-step task, before touching code

Pick the right library for a given frontend task from a curated, opinionated list — numbers, OTP inputs, charts, command menus, virtualization, drag and drop, toasts, state, styling, and more. Only runs when explicitly…

…rather than a desktop, when automation mints a profile per task, when running several of your own accounts from one machine, or when testing how your own bot detection scores a real device. Also for 'antibrow',…

…concurrency (@concurrent, main-actor-by-default, actors, task groups), protocols and generics (some vs any), API design, performance and ARC, Swift Testing, macros, and the modern language features agents don't know…

Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.

…Turborepo repositories. Use when working with turbo.json, task pipelines, caching, Remote Cache, the turbo CLI, filtering, environment variables, package boundaries, monorepo structure, or CI…

…how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also…

Use when the task needs to summarize a local CSV, convert a file into a report, create JSON from local data, analyze local exports without uploading them and remember a recurring local reporting task. Preserves evidence…

Use for any task involving PDF files, including reading, extracting text or tables, creating, transforming, filling forms, OCR, image extraction, and security operations. Use for pdf, .pdf, PDF file, extract PDF text,…

Use when the task needs to get work done across tools, recurring task, browser and CLI and service work and remember this workflow. Preserves evidence with SkillSpec routes, forbids, dependencies, traces, and…

…the agent. HANDOFF.md holds the state of the current task (goal, status checklist, exact next step, failed attempts, open questions, branch and uncommitted files); it is written when a session ends mid-task and…