Skills — le catalogue de compétences de vos agents

高数题库批量出题工作流：选章→撞车排查→生成→分布校验→双维度去重→入库→复核→归档

Use when triggering or debugging XXL-JOB tasks.

Describe a DIY project, get an exact tool list, materials needed, cost estimate, and step-by-step guide filtered by your available tools. Recommends the right tool for each job, finds substitutions, and flags missing tools. Use when planning any DIY, home repair, or making project.

Parse, decode, and expand written knitting patterns. Translates abbreviations, calculates yarn requirements from gauge, tracks stitch counts across rows, and generates row-by-row instructions from condensed pattern notation. Use when a knitter needs help understanding, planning, or tracking a knitting project.

项目规划与执行管理助手。将模糊的项目想法转化为可执行的目标、WBS任务、依赖关系、优先级、时间计划、风险清单和每日行动；根据用户反馈持续更新进度、处理延期、重新排期并进行项目复盘。适用于学习作业、论文、PPT、研究、活动、工作任务、内容创作等项目。触发词包括“规划项目”“拆解项目”“项目计划”“项目进度”“今天做什么”“重新排期”“项目延期”“项目复盘”等。

基于遗忘曲线与间隔复习科学的高效学习与记忆优化计划生成器（Node.js 实现，含可视化图表，与 sleep-optimizer 同系列）。用户输入 memory-optimizer（或 /memory-optimizer）主动调用，或询问任何学习/记忆相关问题（复习计划、背书、遗忘、备考、学习计划、记忆力、考前冲刺等）时自动触发：先按问题框架收集备考阶段与任务目标，再生成含遗忘曲线图、复习调度甘特图和每日学习计划的可执行记忆优化方案

Generate a concise daily briefing by pulling together weather, calendar, recent messages, and news into one readable summary. Use when the user asks for a "daily digest", "morning briefing", or wants a quick overview of what matters today.

The master orchestrator for the OpenClaw Skill OS ecosystem. Coordinates multiple skills, manages skill interactions, and routes tasks to optimal skill combinations when the user explicitly asks to orchestrate or combine skills. Use this skill only when the user requests skill orchestration, multi-skill routing, or ecosystem-wide coordination — not for ordinary single-skill tasks.

Intelligence gathering in Structs — scouting players, planets, guilds, and the galaxy before you act. Use when assessing a raid target, checking a planet's defenses and Command Ship status, profiling an opponent, surveying the galaxy, or refreshing competitive intel. Persists findings to memory/intel/ so they survive context resets.

Gunakan saat user menghadapi task yang butuh reasoning dalam, analisis kompleks, problem-solving kreatif, sintesis long-context, atau planning multi-step. Menyediakan framework kognitif + self-correction loop untuk meningkatkan kualitas output pada task tersebut. Aktif saat user minta 'pikir lebih dalam', 'analisis mendalam', atau 'rencana multi-langkah'.

Execute implementation plans by assigning fresh subagents per independent task with reviews after each and a final branch-wide quality check.

根据客户原话、已确认事实、沟通目标和不可承诺边界，生成适合具体渠道和语言的客户回复。

判断任务边界、复用证据并路由合适的 WorkFn Skill

Maintain mid-term project state in a WORKING.md file with decisions, failed attempts, and next steps to survive context loss between sessions.

Calculate exact quantities of drinks, ice, food, glassware, and supplies for parties and events from headcount, duration, guest mix, and weather. Uses bartender-standard consumption math (drinks per guest-hour), splits beer/wine/spirits by drinker preferences, applies food-per-hour catering rules, and sizes ice in pounds. Use when planning any party, BBQ, wedding, holiday dinner, or gathering and asking how much alcohol, soda, ice, or food to buy.

Turn a person's story and occasion into original lyrics and a newly generated song. This personalized song maker and custom song generator workflow collects the recipient, relationship, occasion, memories, and must-include details, drafts the title, lyrics, section structure, genre, and mood for approval, then generates one finished original song, and reviews story accuracy, name pronunciation, hook, lyric rendering, and vocal result. Use it for custom birthday songs, wedding songs, anniversary songs, proposal songs, family tribute songs, and company or team anthems, with one approved lyric dr

For novel, fiddly, or infrastructure-sensitive work, search prior notes and solved cases for a structurally similar problem. Reuse the method as a hypothesis, verify it against current state, test the real outcome falsifiably, and record only the reusable delta.

Decode veterinary visit notes, discharge summaries, and lab panels (CBC, chemistry, urinalysis) into plain language: what each value means, which results are actually abnormal for the animal's species/breed/age, flag concerning trends across visits, and generate a question list for the next appointment. Use when the user shares vet notes or bloodwork for a pet and asks what it means, whether results are normal, or wants trends tracked over time.

Complete TODO.md items nested under the level 2 header "Current", then update documentation, CHANGELOG.md, and manifest files according to the version update each item indicates. Use when asked to automate TODO items, work through the Current section of TODO.md, apply the next version update, mainta

Use the complete official Tencent Meeting record command family to locate recordings, retrieve native smart-minutes summaries and Todos, verify evidence in transcripts, handle recording-access requests, and produce a source-labeled meeting Todo ledger.

Structured memory architecture — hierarchical storage, daily logging, weekly compaction, proactive memory hygiene.

Smart chore assignment for families and households. Assigns tasks based on skills, schedule, and fairness scoring. Tracks who did what, detects freeloaders, rotates unpleasant tasks equitably, and generates visual chore charts and fairness reports.

Manage exam anxiety with adaptive breathing exercises, evidence-based study planning, stress visualization, and motivational coaching. Use when preparing for tests or feeling overwhelmed by academic pressure.

跨引擎记忆贯通总线：让规划/记忆/验证等四引擎共享同一份结构化记忆，实现跨引擎检索 与关联，使超级智能体一次长程任务内越跑越连贯。这是「四引擎端到端自主闭环」的关键拼图。