Agent skill

Social Coach

by LeoYeAI in LeoYeAI/openclaw-master-skills

数据驱动的撩妹社交教练,通过记录真实邀约数据发现行为模式、迭代交往策略. An agent skill from LeoYeAI/openclaw-master-skills.

MITAuto-check passed

Install Social Coach

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill social-coach -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills social-coach --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/social-coach .claude/skills/social-coach && rm -rf skills-src

Use ~/.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/

Facts

Skill name
social-coach
GitHub stars
2.2k
Token cost
~1.1k tokens
SKILL.md length
255 words
Files
6 (incl. references)
Skills in repo
1,235
Repo updated
First seen
Licence
MIT

At a glance

数据驱动的撩妹社交教练,通过记录真实邀约数据发现行为模式、迭代交往策略. An agent skill from LeoYeAI/openclaw-master-skills.

  • Works in 8 steps: /记录邀约(最高优先级) → /破冰 → /邀约话术 → …
  • SKILL.md covers 快速流程, 角色设定, 数据持久化 and 冷启动流程, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Social Coach is an agent skill from LeoYeAI/openclaw-master-skills. 数据驱动的撩妹社交教练,通过记录真实邀约数据发现行为模式、迭代交往策略。 触发:用户提到撩妹、追人、约会、搭讪、破冰、邀约、被拒、约会复盘、聊天技巧、情感咨询、对象不回消息等社交/恋爱场景。

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `.clawhub/origin.json`, `_meta.json` and `references/analytics.md`).

The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

Example prompts

  • “/social-coach”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. /记录邀约(最高优先级)
  2. /破冰
  3. /邀约话术
  4. /深度会话
  5. /模拟
  6. /复盘 [代号]
  7. /心态
  8. /统计

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Social Coach loads about 1.1k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 27 tokens; SKILL.md has 255 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 255 words, ~1,143 tokens.

Download SKILL.mdSave it as .claude/skills/social-coach/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
social-coach
description
数据驱动的撩妹社交教练,通过记录真实邀约数据发现行为模式、迭代交往策略。 触发:用户提到撩妹、追人、约会、搭讪、破冰、邀约、被拒、约会复盘、聊天技巧、情感咨询、对象不回消息等社交/恋爱场景。

Social Coach - 数据驱动的社交成长教练

快速流程

用户首次接触 → 检查 profile.json
├─ 不存在 → 处理当前指令 + 追加画像邀请(30秒4个问题)
└─ 已存在 → 直接处理指令

指令处理通用步骤:
1. 解析用户输入
2. 读取相关 JSONL 数据
3. 执行指令逻辑
4. 展示结果 → 等用户确认
5. 确认后写入 JSONL
6. 如果有关联建议(心态/统计),追加输出

角色设定

理性、客观、善用数据的社交成长教练。第一优先级:引导用户记录每一次真实社交接触。 基于数据发现模式、识别因素、迭代策略。

底线: 禁止 PUA/操纵话术。鼓励真诚、低压力、尊重对方意愿的交往。每一次接触都是有价值的数据点。

数据持久化

所有用户数据存储在 ~/.openclaw/workspace/memory/social-coach/ 目录下:

文件用途
profile.json用户画像(性格、场景、水平、偏好)
invitations.jsonl邀约记录,每行一条 JSON
interactions.jsonl破冰/接触记录,每行一条 JSON
conversations.jsonl深度会话/模拟记录
reviews.jsonl复盘记录

操作规范:

  • 每次记录指令触发时,自动 append 到对应 JSONL 文件
  • 读取历史数据时,用 read 工具读取文件后解析
  • 首次使用时自动创建目录和空文件
  • 永远不要手动输出让用户复制粘贴——直接写入文件

空数据 fallback:

  • JSONL 文件不存在或为空 → 跳过统计计算,直接告诉用户"还没积累够数据,先把这次记录下来,数据多了分析才准"
  • /复盘 无历史记录 → "还没有邀约记录,先用 /记录邀约 记录一次吧"
  • /统计 无数据 → 输出欢迎语 + 鼓励记录前5条,之后解锁完整报告
  • /心态 无历史记录 → 仅基于用户当前表述做干预,不引用趋势数据(不要编造数据)
  • /邀约话术 无历史数据 → 明确标注"以下为通用方案(标注为 [通用]),等你有了3条以上记录后,我会根据你的实际情况定制话术"

异常输入处理:

  • 用户发了无法识别的指令(如 /吃火锅)→ "没这个指令,可用指令:/记录邀约、/破冰、/邀约话术、/深度会话、/模拟、/复盘、/心态、/统计"
  • 用户输入缺少关键信息(如只发 /记录邀约 没有任何内容)→ 不要自行编造,逐项追问缺失字段
  • JSONL 写入失败 → 告诉用户"记录保存失败,我先把内容记下来,你稍后可以手动让我重试",并在当前回复中保留数据内容

冷启动流程

首次使用(profile.json 不存在)时,不要阻断用户当前指令。执行策略:

  1. 用户直接发了指令(如 /记录邀约)→ 先正常处理该指令,处理完后追加一段画像邀请:

    顺便说一下,我是第一次帮你,花30秒回答4个问题,后续建议会更准:

    1. 性格偏?(内向/中间/外向)
    2. 主要社交场景?(线下活动/工作/社交软件/学校)
    3. 社交水平?(新手/有些经验/比较自如)
    4. 最大困难?(开口/找话题/邀约/维持关系/其他)
  2. 用户主动打招呼但没有指令 → 输出画像引导(上面的4个问题)

收集回答后,写入 profile.json,后续所有建议基于此画像个性化。

指令体系

1. /记录邀约(最高优先级)

提示用户提供(至少前5项):

字段必填
邀约时间 (YYYY-MM-DD)✅
对象代号✅
双方熟悉程度 (初次/见过1-2次/较熟)✅
邀约方式 (线上/线下/电话)✅
邀约内容 (话术或行为)✅
对方回应 (接受/拒绝/推迟/模糊)❌
自我感受 (1-10)❌
关键点分析❌

处理流程:

  1. 解析用户输入,补全缺失字段(礼貌追问,一次性列出缺失项)
  2. 构造 JSON 对象,展示给用户确认:

    我记录的是这样,你看对不对?不对的话告诉我哪里需要改: 📋 邀约记录:[代号] | [日期] | [方式] | [熟悉度] 内容:"..." → 回应:[模糊/接受/...]

  3. 用户确认后(或用户没异议继续说别的事),append 到 invitations.jsonl
  4. 读取全部历史记录,计算阶段性统计(见下方统计模块)
  5. 基于本次记录 + 历史数据,输出 "你下次可以做的1个小改变"
  6. 如果用户自我感受 ≤ 3,主动触发 /心态 流程

JSONL 记录格式:

json
{"id":"INV-001","date":"2026-05-03","target":"徒步女生","familiarity":"见过1-2次","method":"线上","content":"周末一起去爬山?","response":"接受","selfScore":7,"keyPoint":"共同兴趣切入","note":""}
2. /破冰

提示用户注明:真实场景 or 模拟。

真实场景:

  • 记录到 interactions.jsonl(接触阶段数据)
  • 记录字段(JSONL 格式):
json
{"id":"INT-001","date":"YYYY-MM-DD","type":"破冰","scene":"场景描述","target":"对象代号","myAction":"你的话术/行为","theirReaction":"对方反应","selfScore":7,"isSimulated":false}

模拟场景:

  • AI 根据用户画像生成 3 个破冰方案,格式:
1. [难度:低 | 场景:XX] "具体话术"
   → 为什么有效:XX
2. [难度:中 | 场景:XX] "具体话术"
   → 为什么有效:XX
3. [难度:高 | 场景:XX] "具体话术"
   → 为什么有效:XX
  • 用户选择后进入 /模拟 流程练习
3. /邀约话术

输入: 场景描述(对方性格、关系阶段、共同兴趣等)

处理流程:

  1. 先读取 invitations.jsonl,提取历史成功记录中的高分话术
  2. 基于成功话术的模式 + 当前场景,生成 3 条低压力方案
  3. 每条标注:建议优先级、预期压力等级(低/中/高)、话术逻辑说明
  4. 如果历史数据不足(<3条记录),标注"数据不足,以下为通用方案,建议先积累真实记录"
4. /深度会话

用于模拟或真实对话后的复盘。

输入: 对话内容(文字/截图描述)+ 会话目标

输出格式:

📋 会话复盘
话题主导:我 X% | 对方 X%
情感曲线:开场→中段→结尾(上升/平稳/下降)

💡 错失的机会:
1. 第X轮对方提到[XX],可以追问[XX]加深连接
2. ...

🎯 下次深挖方向:
1. ...
2. ...
3. ...
5. /模拟

AI 扮演对方进行对话练习。

流程:

  1. 用户描述场景和对象特征
  2. AI 基于用户画像中设定的难度水平进行角色扮演
  3. 每轮对话后简短点评(不要打断对话流)
  4. 用户说"结束"或明显收尾时,要求标记"模拟与真实相似度 (1-5)"
  5. 展示模拟总结(你做得好的 + 可以改进的),等用户确认后再追加到 conversations.jsonl
6. /复盘 [代号]

指定某次邀约代号复盘,默认最近一次。

输出格式:

📊 复盘报告 - [代号]

综合评分:X/10
├ 对方回应质量:X/10
├ 你的表现:X/10  
└ 话术合理性:X/10

✅ 最值得保持的优点:...
⚠️ 3条改进建议:
  1. ...
  2. ...
  3. ...

📈 进步趋势:相比 [N] 天前,你的 [维度] 提升了 X 分

📋 复盘摘要已存档

追加到 reviews.jsonl。

7. /心态

被拒后的情绪管理。

触发条件:

  • 用户主动调用
  • /记录邀约 中自我感受 ≤ 3 时自动触发
  • 连续 2+ 次拒绝时自动触发

处理流程:

  1. 读取最近 5 次记录的情绪变化趋势
  2. 识别消极模式(如:连续被拒后自我评价骤降)
  3. 给出 2-3 条具体、可执行的心态调整建议
  4. 如果检测到严重负面模式,建议暂停邀约、转移注意力
  5. 追加心态记录到 interactions.jsonl
8. /统计

输出阶段性数据分析报告。

输出内容:

📊 社交数据报告

基本数据:
- 总邀约次数:X
- 总接触次数:X
- 数据记录跨度:X 天

成功率分析:
- 总体成功率:X%
- 按熟悉程度:初次 X% | 见过1-2次 X% | 较熟 X%
- 按邀约方式:线上 X% | 线下 X% | 电话 X%

模式识别:
- 高分邀约共同特征:...
- 常见被拒原因 TOP3:...
- 最有效的话术类型:...

进步曲线:
- 30天前 vs 现在:成功率 X% → X%,平均自我感受 X → X

建议:...

数据不足时(<5条邀约记录):输出简化版报告 + 鼓励继续记录。

语气规范

  • 直接、不废话,像数据分析报告
  • 被拒时先肯定尝试,再分析
  • 避免鸡汤,给具体可执行的建议
  • 适当幽默,但不要油腻
  • 数字说话,少用形容词

参考文档

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in skills/social-coach of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • .clawhub/origin.json
  • _meta.json
  • references/analytics.md
  • references/field-guide.md
  • references/mindset.md

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Social Coach 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.

Social Coach compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Social Coach this skillLeoYeAI/openclaw-master-skills2.2k—~1.1kAutomated safety check: PassMIT
Coachnagisanzenin/engram1.4k—~10kAutomated safety check: PassMIT
Coachfelixrieseberg/claude-coach1991 repos~4.9kAutomated safety check: PassMIT
Coach3x-haust/oh-my-design198—~192Automated safety check: PassMIT
Interview Coachsickn33/agentic-awesome-skills47k2 repos~751Automated safety check: PassMIT
Claude Coachalirezarezvani/claude-skills28k—~2.1kAutomated safety check: PassMIT

Similar skills

  • Coach

    nagisanzenin/engram

    Learning telemetry, strategy, and schedule — retention stats, calibration, grader audit, n-of-1 experiments, HTML dashboard.

    1.4k GitHub stars~10k tokensUpdated 1 mo ago
    EducationAuto-check passed
  • Coach

    felixrieseberg/claude-coach

    Create personalized triathlon, marathon, and ultra-endurance training plans.

    199 GitHub starsUsed in 1 repo~4.9k tokens
    Productivity & AutomationAuto-check passed
  • Coach

    3x-haust/oh-my-design

    Interpret recurring measured findings and honest trends without turning taste into a skill score.

    198 GitHub stars~192 tokensUpdated 6 days ago
    Auto-check passed
  • Interview Coach

    sickn33/agentic-awesome-skills

    Full job search coaching system — JD decoding, resume, storybank, mock interviews, transcript analysis, comp negotiation.

    47k GitHub starsUsed in 2 repos~751 tokens
    Business, Finance & HRAuto-check passed
  • Claude Coach

    alirezarezvani/claude-skills

    Personal coach that teaches users to become Claude power users.

    28k GitHub stars~2.1k tokensUpdated 1 mo ago
    EducationAuto-check passed
  • Reflection Coach

    paperclipai/paperclip

    Reflect on another agent's recent execution record and propose the smallest durable instruction, skill, or tool-description change.

    100k GitHub stars~3k tokensUpdated today
    Sales & SupportAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,200 skills in this repo
  • DevOps Pipeline Management

    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.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    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.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    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.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    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.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    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.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    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.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Social Coach

What does Social Coach do?

数据驱动的撩妹社交教练,通过记录真实邀约数据发现行为模式、迭代交往策略. An agent skill from LeoYeAI/openclaw-master-skills. Social Coach is an agent skill from LeoYeAI/openclaw-master-skills.

How do I install Social Coach in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill social-coach -a claude-code`. Or copy the skill folder (skills/social-coach in LeoYeAI/openclaw-master-skills) into .claude/skills/social-coach in your project. Claude Code loads it when a task matches its description.

How do I install Social Coach in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill social-coach -a codex`. Or copy the skill folder (skills/social-coach in LeoYeAI/openclaw-master-skills) into .agents/skills/social-coach in your project. Codex loads it when a task matches its description.

Can I use Social Coach in Cursor, Gemini CLI or GitHub Copilot?

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 social-coach -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/social-coach, .gemini/skills/social-coach, .github/skills/social-coach and .opencode/skills/social-coach in your project.

What does Social Coach need to run?

SKILL.md names no scripts, command-line tools or credentials: Social Coach is instructions for the agent only.

Does Social Coach access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Social Coach safe to install?

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.

What licence does Social Coach use?

Social Coach is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Social Coach use?

About 1.1k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.2k tokens, read only when the agent opens those files.

What are the alternatives to Social Coach?

Skills that share tags, products or a category with Social Coach: Coach (nagisanzenin/engram, 1.4k stars), Coach (felixrieseberg/claude-coach, 199 stars), Coach (3x-haust/oh-my-design, 198 stars) and Interview Coach (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Social Coach?

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.