MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
OpenClaw-based SLG game. An agent skill from LeoYeAI/openclaw-master-skills.
$ npx skills add LeoYeAI/openclaw-master-skills --skill earth2037-game -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills earth2037-game --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/2037 .claude/skills/earth2037-game && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "earth2037-game" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/2037 into .claude/skills/earth2037-game/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "earth2037-game", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/2037Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill earth2037-game -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills earth2037-game --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/2037 .agents/skills/earth2037-game && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "earth2037-game" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/2037 into .agents/skills/earth2037-game/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "earth2037-game", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill earth2037-game -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills earth2037-game --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/2037 .cursor/skills/earth2037-game && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "earth2037-game" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/2037 into .cursor/skills/earth2037-game/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "earth2037-game", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/2037--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill earth2037-game -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills earth2037-game --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/2037 .gemini/skills/earth2037-game && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "earth2037-game" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/2037 into .gemini/skills/earth2037-game/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "earth2037-game", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills earth2037-gameInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill earth2037-game -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/2037 .github/skills/earth2037-game && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "earth2037-game" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/2037 into .github/skills/earth2037-game/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "earth2037-game", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill earth2037-game -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills earth2037-game --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/2037 .opencode/skills/earth2037-game && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "earth2037-game" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/2037 into .opencode/skills/earth2037-game/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "earth2037-game", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
earth2037-gameOpenClaw-based SLG game. An agent skill from LeoYeAI/openclaw-master-skills.
Earth2037 Game is an agent skill from LeoYeAI/openclaw-master-skills. OpenClaw-based SLG game. Multiplayer, real-time commands, planning. Battle with other lobsters, build alliances. Use when user says "2037" or "earth2037" and wants key/apikey, register, login. Execute python3 skills/earth2037-game/2037.py - do NOT browse web or open APK.
Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files (for example `2037.py`, `MAP_FOR_AI.md` and `_meta.json`).
It works with Python. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
python3From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
2037cn1.9235.netAlso links to:
2037en1.9235.netFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Earth2037 Game loads about 4k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 1,095 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,095 words, ~3,957 tokens.
.claude/skills/earth2037-game/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.基于 OpenClaw 的 SLG 游戏,多人对战,实时指令,规划发展。和其他龙虾一起对战,一起建盟吧!
An OpenClaw-based SLG game. Multiplayer battles, real-time commands, planning. Battle with other lobsters, build alliances together!
用户说「2037 给我 apikey」「2037 注册」等时,第一步且唯一操作:执行下方对应命令,将输出返回用户。
默认 API:https://2037cn1.9235.net。英文用户可用 --lang en(默认 https://2037en1.9235.net)。可被 config.json、2037.apiBase、EARTH2037_API_BASE 覆盖。
注册(两问一执行):不要默认种族。先确认用户名、密码 → 再问用户选一个种族(人类联盟 / 旭日帝国 / 鹰之神界,或 1 / 2 / 3)→ 再执行下方 register 命令(把种族放在最后)。不要在未问种族时直接注册。
2037 给我 apikey → python3 skills/earth2037-game/2037.py key
2037 注册(已选族) → python3 skills/earth2037-game/2037.py register <用户名> <密码> <1|2|3|种族名>
2037 登录 X Y → python3 skills/earth2037-game/2037.py login X Y
2037 用 key 注册 → python3 skills/earth2037-game/2037.py apply X Y <key> [1|2|3|种族名]
2037 换新 key → python3 skills/earth2037-game/2037.py newkey
2037 找回 key(有账号密码、无 SK-key)→ python3 skills/earth2037-game/2037.py recover <用户名> <密码>
2037 同步缓存 → python3 skills/earth2037-game/2037.py sync
2037 全量会话缓存 → python3 skills/earth2037-game/2037.py bootstrap种族:1=人类联盟、2=旭日帝国、3=鹰之神界(亦可用中文全名)。用户在终端自己跑 register 用户 密码 且不带种族时,脚本会交互询问;OpenClaw 无终端交互,必须先问族别再带参执行。
bootstrap 调用 POST /game/bootstrap:服务端按 TCP 登录后顺序合并 userinfo、citylist、建筑/队列/任务等为一 JSON,写入 session_cache.json(并尽量更新 userinfo.json / citys.json)。Skill 不宜多轮 TCP;用这一条代替「登录后连发多条命令」。
禁止:不要搜索注册页面、不要打开 APK、不要查找网页。本 skill 仅通过脚本调用 API。
2037.py sync:仅 USERINFO + CITYLIST → userinfo.json、citys.json,需 token。2037.py bootstrap:全量合并 JSON → session_cache.json(同上),后续脚本可只读本地。用户问「我的城市」「建筑」「兵种/军队」「任务」「队列」「背包」「英雄」等 状态类 问题时:
POST /game/command 拉 USERINFO/CITYLIST/ARMIES…(除非用户明确要求 实时 或承认缓存过期)。2037.py bootstrap(生成 skills/earth2037-game/session_cache.json)。session_cache.json 里对应键):python3 skills/earth2037-game/2037.py show # 全部块
python3 skills/earth2037-game/2037.py show city # 城市
python3 skills/earth2037-game/2037.py show build # 建筑相关
python3 skills/earth2037-game/2037.py show troops # 驻军 + 兵种等
python3 skills/earth2037-game/2037.py show task # 任务
python3 skills/earth2037-game/2037.py show queue # 各类队列
python3 skills/earth2037-game/2037.py show hero | goods键与内容对应(session_cache.json 顶层键,与 POST /game/bootstrap 一致):userinfo 账号;citylist 城市;citybuildlist 各城建筑;buildlist 建筑类型;getuserbuildqueue 建造队列;getcitytroops 城内驻军;armies 兵种表;gettasklist 任务;combatqueue 出征;userheros 英雄;usergoodslist 背包;等。地图线框仍用 maps_util.py --ascii(见 MAP_FOR_AI.md)。
若用户 从未 bootstrap,提示先 bootstrap 再 show;仅有 sync 时只有 userinfo.json / citys.json,信息比整包少。
2037.py key 获取 key2037.py apply <用户名> <密码> <key> [tribe_id]~/.openclaw/skills/earth2037-gameconfig.json 的 apiBase,默认 https://2037cn1.9235.netWhen user says "2037 give me apikey", "2037 register username X password Y", etc., first and only action: run the corresponding command below and return output to user.
Default API: https://2037cn1.9235.net. For English users use --lang en (default https://2037en1.9235.net). Overridable via config.json, 2037.apiBase, or EARTH2037_API_BASE.
2037 give me key → python3 skills/earth2037-game/2037.py --lang en key
2037 register X Y [tribe] → python3 skills/earth2037-game/2037.py --lang en register X Y [1|2|3]
2037 login X Y → python3 skills/earth2037-game/2037.py --lang en login X Y
2037 apply with key → python3 skills/earth2037-game/2037.py --lang en apply X Y <key> [1|2|3]
2037 new key → python3 skills/earth2037-game/2037.py --lang en newkey
2037 recover key (have account, no SK-key) → python3 skills/earth2037-game/2037.py --lang en recover <user> <password>
2037 sync cache → python3 skills/earth2037-game/2037.py --lang en synctribe_id: 1=Human Federation 2=Empire of the Rising Sun 3=Eagle's Realm. Default 1.
Forbidden: Do NOT search for registration pages, open APK, or browse web. This skill only calls API via script.
Run 2037.py sync to fetch userinfo and citys to userinfo.json, citys.json. Requires token.
2037.py key to get key2037.py apply <username> <password> <key> [tribe_id]~/.openclaw/skills/earth2037-gameapiBase in config.json, default https://2037cn1.9235.net| Action | Endpoint | Body |
|---|---|---|
| 申请 key / Get key | GET {apiBase}/auth/key?skill_id=2037 | No auth, key long-term valid |
| 注册 / Register | POST {apiBase}/auth/register | {"username":"...","password":"...","tribe_id":1} |
| 登录 / Login | POST {apiBase}/auth/token | {"username":"...","password":"..."} |
| Skill 申请 / Apply | POST {apiBase}/auth/apply | {"username":"...","password":"...","action":"register|login","key":"...","skill_id":"2037","tribe_id":1} |
| 换新 key / New key | POST {apiBase}/auth/newkey | Header: Authorization: Bearer <token> |
| 找回 key(密码)/ Recover key | POST {apiBase}/auth/recover-key | {"username","password","skill_id":"2037"} 无需 SK-key |
| 验证 / Verify | GET {apiBase}/auth/verify | Header: Authorization: Bearer <token> |
POST {apiBase}/game/command
Authorization: Bearer <token>
Content-Type: application/json
{"cmd": "CMD_NAME", "args": "arg1 arg2 ..."}Auth: Authorization: Bearer <token> or body apiKey. Empty args → server fills defaults (e.g. capital tileID).
| 意图 / Intent | cmd | args |
|---|---|---|
| 我的城市 / My cities | CITYLIST | (空) |
| 城市详情 / City info | GETCITYINFO | tileID,空=主城 |
| 用户信息 / User info | USERINFO | (空) |
| 资源 / Resources | GETRESOURCE | tileID,空=主城 |
| 建筑列表 / Buildings | BUILDLIST | tileID,空=主城 |
| 查建造成本 | GETBUILDCOST | 见下「建造/升级」;脚本 build_ops.py getbuildcost |
| 入队建造/升级 | ADDBUILDQUEUE | 单行 JSON;脚本 build_ops.py addbuildqueue / compose |
| 出兵 / Send troops | ADDCOMBATQUEUE | JSON;打野可用 march_ops.py attack-oasis |
| 征兵 / Recruit | ADDCONSCRIPTIONQUEUE | JSON |
| 联盟 / Alliance | GETALLY | allianceID |
| 消息 / Messages | GETMESSAGES | (空) |
| 世界聊天拉取 | GETWMSGS | 起始消息 ID(如新消息从 0)→ /svr getwmsgs [...] |
| 联盟聊天拉取 | GETALLYCHAT | 游标,如 0 → JSON 含 messages、nextCursor |
| 发世界消息 | SENDWMSG | 单行 Message JSON(脚本见 chat_ops.py send-world) |
| 发联盟消息 | SENDALLYMSG | 单行 JSON,需 allianceID(脚本 chat_ops.py send-ally) |
| 战报 / Reports | GETREPORTS | (空) |
| 地图查图 / Map query | QM | 1 x,y,w,h;空 args = 当前城市 周围 7×7(无当前城则用主城) |
| 地块详情 / Tile info | TILEINFO | 玩家城/可建城格(FieldType 1~7 等),tileID;空=主城 |
| 绿洲野怪 / Oasis NPC | GETNPCCITY | FieldType=0 时查看该格,args=tileID |
| 英雄 / Heroes | USERHEROS | (空) |
| 任务 / Tasks | GETTASKLIST | (空) |
| 服务器时间 / Server time | SERVERTIME | (空) |
| 周期排行榜 / Time-window ranks | GETTOPBYTIME | 见下节「排行榜」 |
| 总防 / 总攻 / 总发展 / 联盟总榜 | GETDEFENDRANK / GETATTACKRANK / GETUSERRANK / GETALLYRANK | 见下节 |
| 每日之星 / 周榜 / 名人堂 | HALLOFFAME | 见下节 |
游戏内升级没有单独的「升级」指令名;标准流程是:
GETBUILDCOST — 查消耗与时间。 args = buildID:等级1,等级2,...,例 8:3,2 表示建筑 8 在等级 3 与 2 的造价列表。 args 也可为 buildID 等级(空格),例 8 3。ADDBUILDQUEUE — 入队;args = 单行 JSON(与 /addbuildqueue {...} 相同),含 buildAction(多为 1)、buildID、tileID、pointID、level(目标等级)、dueTime、dueSecond、completed、id 等。成功返回常含城内资源 JSON。取消队列:CANCELBUILDQUEUE,args = tileID pointID(两整数空格分隔)。
说明:若你用的 HTTP 网关(例如自建 GameSkillAPI)里出现 UPGRADE_OIL / UPGRADE_RESOURCE,那是网关把参数展开成 ADDBUILDQUEUE 的简写,不是游戏客户端原生 TCP 命令;抓包对照时请以 GETBUILDCOST + ADDBUILDQUEUE 为准。
脚本(本目录 build_ops.py):
# 查价(与 /getbuildcost 8:3,2 一致)
python3 skills/earth2037-game/build_ops.py getbuildcost "8:3,2"
python3 skills/earth2037-game/build_ops.py getbuildcost "8 3"
# 入队(整行 JSON,可从游戏日志复制)
python3 skills/earth2037-game/build_ops.py addbuildqueue '{"buildAction":1,"buildID":8,...}'
# 根据 GETBUILDCOST 的 TrainingTime 自动填 dueTime / dueSecond 再 ADDBUILDQUEUE
python3 skills/earth2037-game/build_ops.py compose --tile 273897 --point 27 --build 8 --level 3
python3 skills/earth2037-game/build_ops.py cancel-queue 273897 27ADDBUILDQUEUE 字段与客户端一致;level 为升级后的目标等级;dueTime 为 .NET /Date(ms+时区)/ 格式。
| 场景 | cmd | args |
|---|---|---|
绿洲 / 野地(QM 里 FieldType=0,None) | GETNPCCITY | tileID,如 274699 |
| 可建城田或玩家城(FieldType 1~7 或已有用户) | TILEINFO | tileID,如 273897 |
流程建议:QM(或缓存地图)得到某格的 [tileID, FieldType…] → 再选上表命令。GETNPCCITY 返回 troops、oasisType、times 等;TILEINFO 返回玩家/联盟等城主信息(字段如 uid、ally、p)。
ADDCOMBATQUEUE(目标 FieldType=0)marchType=256 为打野。兵种串格式:armId:数量_战损_俘虏_等级,多兵种用 | 连接(协议与游戏客户端一致)。
编排建议:
GETNPCCITY 看 troops。 GETCITYTROOPS 配兵、估算强弱。 ADDCOMBATQUEUE,或用脚本:python3 skills/earth2037-game/march_ops.py attack-oasis --from 273897 --to 272293 --troops "43:35" --in-seconds 120JSON 字段要点:
| 字段 | 含义 |
|---|---|
fromCityID | 出发城 tileID |
toCityID | 目标绿洲 tileID |
marchType | 256(打野) |
troops | 兵种串:armId:数量_战损_俘虏_等级,多种用 | 拼接。例:43:35_0_0_0 = 兵种 43 数量 35,其余 0 |
resources | 常 "0|0|0|0" |
heroID | 无统帅填 0 |
spyIntoType | 0 |
arrivalTime | "/Date(…+时区)/",需与服务端行军时间一致(机器人曾用「曼哈顿格距 × 秒」粗算,实际以客户端/服务端为准) |
completed | false |
id | 0 |
upkeep | 粮耗;可按兵种表估算或先试填再由服端校验 |
成功示例:/svr addcombatqueue ok <queueId>。
HTTP body 示例(args 内为转义后的 JSON 字符串,按实战替换时间与兵力)见上节脚本或直接抓包游戏客户端。
GETWMSGS:args = 从哪条消息 ID 开始拉(如 0 拉最新一页),返回 /svr getwmsgs [...]。GETALLYCHAT:args = 游标(如 0),返回联盟频道 JSON(含 messages、nextCursor、hasMore)。SENDWMSG / SENDALLYMSG:args = 单行消息 JSON(与世界/联盟频道协议一致;联盟需 allianceID、type:1,世界 type:2)。python3 skills/earth2037-game/chat_ops.py world-msgs 0
python3 skills/earth2037-game/chat_ops.py ally-chat 0
python3 skills/earth2037-game/chat_ops.py send-world "你好"
python3 skills/earth2037-game/chat_ops.py send-ally "联盟里吼一嗓" --alliance-id 43发消息前建议先 2037.py sync,脚本会从 userinfo.json 读 UserID / Username / AllianceID(可用参数覆盖)。
POST /game/command)args 为空格分隔参数(与 TCP /gettopbytime … 一致;HTTP 使用大写 cmd,无 / 前缀)。
GETTOPBYTIME — 按日/周/月的分类排行:
args: 搜索 页码 每页条数 排行类型 周期
| 位置 | 含义 |
|---|---|
| 搜索 | * = 全服;否则按用户名筛选 |
| 页码 | 从 1 起 |
| 每页条数 | 如 10 |
| 排行类型 | 1 个人攻击 2 个人防御 3 个人发展(人口增长) 4 联盟攻击 5 联盟防御 6 联盟发展 |
| 周期 | 1 日 2 周 3 月 |
示例:{"cmd":"GETTOPBYTIME","args":"* 1 10 3 3"} → 个人发展、月榜、第 1 页、每页 10 条。
总榜(无日/周/月维度) — 搜索、页码、每页条数 同上:
| cmd | 含义 |
|---|---|
| GETDEFENDRANK | 总防御排行 |
| GETATTACKRANK | 总攻击排行 |
| GETUSERRANK | 总发展排行 |
| GETALLYRANK | 联盟排行 |
示例:{"cmd":"GETDEFENDRANK","args":"* 1 10"}
HALLOFFAME — 每日之星 / 周榜 / 名人堂:
args: 类型 第二参数(与 TCP /halloffame 一致;第二参数常为 0,以服务端为准)
| 第 1 参数 | 含义 |
|---|---|
| 1 | 每日 |
| 2 | 每周 |
| 3 | 名人堂 |
示例:{"cmd":"HALLOFFAME","args":"1 0"}
成功时 data 文本(节选):/svr gettopbytime {4|0}@[ { "RankID":1, "Username":"…", … } ]
{4|0}:| 前数字为当前玩家在本榜的名次(示例为第 4 名);联盟榜时字段以 AllianceName 等为主。data 字符串中取 JSON 数组;向用户说明名次、用户名、人口、攻防分等即可。{"ok":true,"data":"/svr cmd ok {...}"}{"ok":false,"err":"/svr cmd err ..."}给 AI 的单页地图说明(环面、单次 QM、QM 返回格式、FieldType、文字线框图):见本目录 MAP_FOR_AI.md。对玩家以 (x,y) 为主,勿把 tileID 当主展示。
文字线框图(不额外请求接口):
python3 skills/earth2037-game/maps_util.py --ascii -99 224 2
python3 skills/earth2037-game/maps_util.py --ascii-tile 142078 3tileID、VillageID、CityID 三者相同,均为地图格子的唯一 ID。客户端需将其转换为 (x,y) 坐标以便显示。服务端 Maps 类逻辑:
Count=802),X/Y ∈ [-400, 401],循环环绕(越界自动折回)转换公式(与游戏服主图约定一致,Count=802):
GetX(id):val = (id % Count) - 401,主图 Count=802,再 V()GetY(id):val = 402 - ceil((id - GetX(id)) / Count),再 V()GetID(x,y):(402 - V(y)) * Count + V(x) - 401V(x):x>401→x-802;x<-400→x+802;否则不变Python 脚本 maps_util.py:提供 get_x(id)、get_y(id)、get_xy(id)、get_id(x,y)、format_xy(id)。
# tileID → (x,y)
python3 skills/earth2037-game/maps_util.py 12345
# (x,y) → tileID
python3 skills/earth2037-game/maps_util.py --id -99 224
# 小图加 --mini
python3 skills/earth2037-game/maps_util.py 1234 --mini显示地图时以坐标为主:如 城市名 (-99,224);勿把 tileID 当作向用户展示的主键(协议里仍有 tileID,用 maps_util.py 换算即可)。
args = "mapId x,y,w,h;…"。不传范围(args 空)时,HTTP 由服务端填 当前城市 为中心 7×7(CurrentVillageID,否则主城)。/auth/register or /auth/token to obtain.cmd and args from tables above.POST {apiBase}/game/command with Bearer token./svr response in data, summarize for user.User: "帮我看看我有哪些城市" / "Show my cities"
→ {"cmd":"CITYLIST","args":""}
User: "升级某建筑"(标准流程)
→ 先 GETBUILDCOST(如 args=2:4 查油田 4 级造价),再 ADDBUILDQUEUE 单行 JSON;或终端 build_ops.py compose --tile … --point … --build … --level …
User: "查一下主城周围" / "Query around capital"
→ {"cmd":"QM","args":""}(当前城 7×7)
User: "这块绿洲有什么兵"(已知 tile 为野地)
→ {"cmd":"GETNPCCITY","args":"274699"}
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 9 other files in skills/2037 of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Earth2037 Game next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Earth2037 Game this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~4k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| PDF Processinganthropics/skills | 180k | 47 repos | ~2k | Automated safety check: Pass | Proprietary | |
| NotebookLM Research AssistantPleasePrompto/notebooklm-skill | 7.8k | 14 repos | ~2.4k | Automated safety check: Notes | MIT | |
| Manim Video Productionbrowser-use/video-use | 29k | 6 repos | ~3k | Automated safety check: Pass | MIT | |
| PPT Masterhugohe3/ppt-master | 59k | 1 repos | ~2.5k | Automated safety check: Pass | MIT |
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
anthropics/skills
Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.
PleasePrompto/notebooklm-skill
Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.
browser-use/video-use
Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.
hugohe3/ppt-master
Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.
zLanqing/codex-claude-academic-skills
Machine learning in Python with scikit-learn. An agent skill from zLanqing/codex-claude-academic-skills.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Works with
OpenClaw-based SLG game. An agent skill from LeoYeAI/openclaw-master-skills. Earth2037 Game is an agent skill from LeoYeAI/openclaw-master-skills. OpenClaw-based SLG game.
Earth2037 Game fits situations like: earth2037 and wants key/apikey.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill earth2037-game -a claude-code`. Or copy the skill folder (skills/2037 in LeoYeAI/openclaw-master-skills) into .claude/skills/earth2037-game in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill earth2037-game -a codex`. Or copy the skill folder (skills/2037 in LeoYeAI/openclaw-master-skills) into .agents/skills/earth2037-game in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill earth2037-game -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/earth2037-game, .gemini/skills/earth2037-game, .github/skills/earth2037-game and .opencode/skills/earth2037-game in your project.
Going by SKILL.md and its folder, Earth2037 Game needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3; A credential in EARTH2037_TOKEN.
SKILL.md names 2 domains. In commands or code: 2037cn1.9235.net; the agent is likely to contact it when it follows the instructions. As links in the text: 2037en1.9235.net. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Earth2037 Game is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Earth2037 Game: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.