When to Use
Use this for basketball work: game prep, post-game review, lineup fit, player scouting, role definition, shot-profile discussion, and weekly practice planning.
Do not use it for betting picks, medical advice, fake live stats, or American-football questions. This skill is for usable basketball decisions, not sports chatter.
Architecture
Memory lives in ~/basketball/. If ~/basketball/ does not exist, run setup.md. See memory-template.md for structure.
CODEBLOCK0
Quick Reference
Use the smallest file that resolves the blocker.
| Topic | File |
|---|
| Setup and activation behavior | INLINECODE4 |
| Memory and local file templates |
memory-template.md |
| Film-room and game-review workflow |
possession-map.md |
| Opponent scout template |
opponent-scout.md |
| Player evaluation rubric |
scouting-grid.md |
| Practice planning and drill logic |
practice-week.md |
| Role and lineup fit logic |
lineup-cards.md |
Requirements
- - No credentials required
- No extra binaries required
- Persistent notes only after the user approves local memory
- Ask which level matters: youth, high school, academy, college, rec league, semi-pro, or professional
Data Storage
Local notes in ~/basketball/ may include:
- - activation rules and the situations where basketball help should appear
- level, region, offensive style, defensive scheme, and analysis preferences
- recurring opponents, player-role notes, and roster needs
- weekly practice constraints such as court time, roster size, minutes, and schedule
Keep memory lean. Store durable context that improves future basketball work, not every game note.
Possession Map Protocol
Run the full workflow in possession-map.md. Every basketball task should first be classified into one of these lanes:
| Lane | Primary output | Anchor file |
|---|
| Game preview | plan, matchups, counters, focus possessions | INLINECODE13 |
| Post-game review |
what repeated, why, next fixes |
possession-map.md |
| Player scouting | role fit, strengths, risk, projection |
scouting-grid.md |
| Roster design | lineup balance, shot diet, role clarity |
lineup-cards.md |
| Practice week | microcycle, drill goals, constraints |
practice-week.md |
Default output should be usable in a locker room, staff meeting, film session, or workout block.
Core Rules
1. Lock the Basketball Context Before Giving Advice
- - Confirm the task is basketball, then lock level, ruleset, roster reality, schedule, and decision needed.
- Advice that ignores level, player availability, and game format sounds smart but fails in real gyms.
2. Separate Observation, Inference, and Recommendation
- - State what is known from film, stats, or user notes before jumping to conclusions.
- Label assumptions when evidence is partial, stale, or anecdotal.
3. Read the Game Possession by Possession
- - Structure previews and reviews around transition, early offense, half-court creation, defensive shell, rebounding, and special situations.
- One hot quarter, one made run, or one highlight play rarely explains the actual game.
4. Judge Players Through Roles and Lineup Context
- - Evaluate what a player must solve on offense and defense, which lineup unlocks them, and what cover they need.
- Good basketball analysis explains fit, spacing, and matchup trade-offs instead of handing out vague labels.
5. Make Practice Match the Real Game Problem
- - Every practice plan needs one clear objective, player numbers, space, timing, drill constraints, coaching cues, and a progression or regression.
- Sessions that do not map back to the next game or development need become empty reps.
6. End With Coach-Ready Outputs
- - Finish with decisions that matter now: matchup plan, lineup tweak, shot-profile priority, coverage adjustment, or next practice blueprint.
- If the answer cannot be used by a coach, analyst, scout, or player in under five minutes, tighten it.
7. Respect Basketball Boundaries
- - Do not invent live stats, injuries, or lineup certainty.
- Do not give betting picks, medical clearance, or fake precision that the evidence cannot support.
Common Traps
These are the failure patterns that most often turn basketball analysis into commentary with no coaching value.
| Trap | Why It Fails | Better Move |
|---|
| Treating every roster like a pro team | Youth and amateur groups have different spacing, shooting, and time limits | Scale the plan to real talent, court time, and teaching bandwidth |
| Confusing points scored with process quality |
Hot shooting can hide bad spacing, turnover risk, or defensive leaks | Track shot profile, turnover pressure, paint touches, and second-chance control |
| Judging players from box scores alone | Box scores hide screen quality, low-man help, spacing gravity, and decision speed | Use the role lens in
scouting-grid.md |
| Writing practices with no constraints | Good drills fail when numbers, timing, or court space do not fit | Specify players, area, timing, and scoring constraints every time |
| Fixing offense while breaking defense | More spacing or pace can expose rebounding and transition cover | State the trade-off and the cover needed |
| Using lineup names instead of functional roles | "Small ball" or "two-big" labels do not explain what actions actually work | Describe creation, spacing, rim pressure, point-of-attack defense, and rebounding jobs |
Security & Privacy
Data that leaves your machine:
- - none by default
- if the user explicitly asks for public basketball facts, only the needed searches, source fetches, or tool calls for that task
Data that stays local:
- - approved basketball notes in INLINECODE19
This skill does NOT:
- - store account credentials or betting logins
- make undeclared network requests
- present guesses as verified game data
- persist local notes without user approval
Scope
This skill ONLY:
- - structures basketball analysis, scouting, roster planning, and practice design
- turns vague basketball questions into reusable reports and gym-ready outputs
- stores lightweight local basketball notes after user approval
- stays inside basketball unless the user clearly redirects
This skill NEVER:
- - place bets, recommend stakes, or act like an odds tool
- diagnose injuries or clear return-to-play decisions
- pretend one stat line is enough evidence
- modify its own skill files
Related Skills
Install with
clawhub install <slug> if user confirms:
- -
analysis - structure trade-offs, assumptions, and decision quality. - INLINECODE22 - sharpen communication, accountability, and behavior change with players or staff.
- INLINECODE23 - handle load, conditioning, and habit work when the conversation shifts beyond tactics.
- INLINECODE24 - run source-backed league, opponent, or rules research when facts matter.
- INLINECODE25 - turn spreadsheets, tracking exports, and dashboards into clearer basketball conclusions.
Feedback
- - If useful: INLINECODE26
- Stay updated: INLINECODE27
何时使用
用于篮球相关工作:赛前准备、赛后复盘、阵容适配、球员考察、角色定义、投篮分布讨论以及每周训练计划。
请勿用于博彩预测、医疗建议、虚假实时数据或美式橄榄球相关问题。本技能服务于可执行的篮球决策,而非体育闲聊。
架构
记忆文件存储于 ~/basketball/。若 ~/basketball/ 不存在,请运行 setup.md。结构参考 memory-template.md。
text
~/basketball/
├── memory.md # 激活规则、层级、风格及长期偏好
├── possession-map.md # 近期比赛计划、复盘及回合主题
├── roster-notes.md # 阵容、角色、搭配及考察结论
├── practice-log.md # 每周节奏、限制条件及训练笔记
└── archive/ # 已归档报告及旧周期
快速参考
使用能解决当前问题的最小文件。
| 主题 | 文件 |
|---|
| 设置与激活行为 | setup.md |
| 记忆与本地文件模板 |
memory-template.md |
| 录像室与比赛复盘流程 | possession-map.md |
| 对手考察模板 | opponent-scout.md |
| 球员评估标准 | scouting-grid.md |
| 训练计划与训练逻辑 | practice-week.md |
| 角色与阵容适配逻辑 | lineup-cards.md |
要求
- - 无需凭证
- 无需额外二进制文件
- 仅在用户批准本地记忆后保存持久笔记
- 询问适用的层级:青少年、高中、青训、大学、业余联赛、半职业或职业
数据存储
~/basketball/ 中的本地笔记可包含:
- - 激活规则及应提供篮球帮助的场景
- 层级、地区、进攻风格、防守体系及分析偏好
- 常遇对手、球员角色笔记及阵容需求
- 每周训练限制条件,如场地时间、阵容人数、上场时间及赛程
保持记忆精简。存储能提升未来篮球工作质量的持久背景信息,而非每场比赛的笔记。
回合图谱协议
运行 possession-map.md 中的完整流程。每项篮球任务应首先归入以下类别之一:
| 类别 | 主要产出 | 锚定文件 |
|---|
| 赛前预览 | 计划、对位、应对策略、关键回合 | opponent-scout.md |
| 赛后复盘 |
重复出现的问题、原因、后续修正 | possession-map.md |
| 球员考察 | 角色适配、优势、风险、发展预测 | scouting-grid.md |
| 阵容设计 | 阵容平衡、投篮分布、角色清晰度 | lineup-cards.md |
| 训练周计划 | 微周期、训练目标、限制条件 | practice-week.md |
默认产出应能在更衣室、教练会议、录像分析课或训练课中直接使用。
核心规则
1. 在给出建议前锁定篮球背景
- - 确认任务属于篮球范畴,然后锁定层级、规则体系、阵容现实、赛程及所需决策。
- 忽略层级、球员可用性和比赛形式的建议听起来高明,但在真实球馆中无法奏效。
2. 区分观察、推断与建议
- - 在得出结论前,先说明从录像、数据或用户笔记中已知的信息。
- 当证据不完整、过时或为传闻时,明确标注假设。
3. 逐回合解读比赛
- - 围绕转换进攻、早期进攻、半场创造、防守阵型、篮板球及特殊局面构建预览和复盘。
- 单节爆发、一波流或一个高光回合很少能解释比赛全貌。
4. 通过角色和阵容背景评判球员
- - 评估球员在攻防两端必须解决什么问题、哪种阵容能激活他、以及他需要什么掩护。
- 优秀的篮球分析应解释适配性、空间和错位权衡,而非给出模糊标签。
5. 让训练匹配真实的比赛问题
- - 每份训练计划需包含一个明确目标、球员人数、空间、时间、训练限制条件、教练指导要点以及进阶或降阶方案。
- 与下一场比赛或发展需求脱节的训练课将成为无效重复。
6. 以教练可用的产出收尾
- - 以当下重要的决策收尾:对位方案、阵容调整、投篮分布优先级、防守调整或下一堂训练课蓝图。
- 如果答案无法在五分钟内被教练、分析师、球探或球员使用,请精简。
7. 尊重篮球边界
- - 不要编造实时数据、伤病信息或阵容确定性。
- 不要给出博彩预测、医疗许可或证据无法支持的虚假精确度。
常见陷阱
以下是将篮球分析变成无教练价值评论的最常见失败模式。
| 陷阱 | 失败原因 | 更好的做法 |
|---|
| 将每支球队都当职业队对待 | 青少年和业余球队的空间、投篮和时间限制不同 | 根据实际天赋、场地时间和教学能力调整计划 |
| 将得分等同于过程质量 |
手感火热可能掩盖糟糕的空间、失误风险或防守漏洞 | 追踪投篮分布、失误压力、禁区触球次数和二次进攻控制 |
| 仅凭数据表评判球员 | 数据表掩盖了掩护质量、弱侧协防、空间引力及决策速度 | 使用 scouting-grid.md 中的角色视角 |
| 制定无限制条件的训练计划 | 当人数、时间或场地空间不匹配时,好的训练也会失败 | 每次明确说明球员、区域、时间和得分限制条件 |
| 修复进攻却破坏防守 | 增加空间或节奏可能暴露篮板和转换防守问题 | 说明权衡取舍及所需的掩护 |
| 用阵容名称代替功能角色 | 小个阵容或双塔标签无法解释哪些战术真正有效 | 描述创造机会、空间、篮下压力、持球点防守和篮板任务 |
安全与隐私
离开您设备的数据:
- - 默认无
- 如果用户明确要求公开篮球事实,仅执行该任务所需的搜索、源获取或工具调用
保留在本地的数据:
- - 已批准的 ~/basketball/ 中的篮球笔记
本技能不会:
- - 存储账户凭证或博彩登录信息
- 发起未声明的网络请求
- 将猜测呈现为已验证的比赛数据
- 未经用户批准持久化本地笔记
范围
本技能仅:
- - 结构化篮球分析、考察、阵容规划和训练设计
- 将模糊的篮球问题转化为可复用的报告和球馆可用的产出
- 在用户批准后存储轻量级本地篮球笔记
- 除非用户明确转向,否则保持在篮球领域内
本技能绝不:
- - 下注、推荐投注金额或充当赔率工具
- 诊断伤病或决定复出许可
- 假装单条数据线足以作为证据
- 修改自身的技能文件
相关技能
若用户确认,使用 clawhub install
安装:
- - analysis - 结构化权衡、假设和决策质量
- coach - 提升与球员或教练组的沟通、问责和行为改变
- fitness - 当对话超出战术范畴时,处理负荷、体能和习惯养成
- in-depth-research - 当事实重要时,进行有来源的联赛、对手或规则研究
- data-analysis - 将电子表格、追踪导出数据和仪表盘转化为更清晰的篮球结论
反馈
- - 如有帮助:clawhub star basketball
- 保持更新:clawhub sync