Agent skill

She Love Me

Acquire, import, and analyze WeChat or QQ chat histories, including installing supported exporters, guiding required login or contact selection, converting exports, assessing relationship dynamics…

MITAuto-check passedProductivity & Automation

Install She Love Me

skills CLI

$ npx skills add 863401402/she-love-me --skill she-love-me -a claude-code

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

GitHub CLI

$ gh skill install 863401402/she-love-me she-love-me --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/863401402/she-love-me.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/she-love-me .claude/skills/she-love-me && 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/

Paste into Claude Code

Install the "she-love-me" agent skill from https://github.com/863401402/she-love-me/tree/main/.agents/skills/she-love-me into .claude/skills/she-love-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "she-love-me", 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

$skill-installer install https://github.com/863401402/she-love-me/tree/main/.agents/skills/she-love-me

Type 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.

skills CLI

$ npx skills add 863401402/she-love-me --skill she-love-me -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install 863401402/she-love-me she-love-me --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/863401402/she-love-me.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/she-love-me .agents/skills/she-love-me && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "she-love-me" agent skill from https://github.com/863401402/she-love-me/tree/main/.agents/skills/she-love-me into .agents/skills/she-love-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "she-love-me", 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.

skills CLI

$ npx skills add 863401402/she-love-me --skill she-love-me -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install 863401402/she-love-me she-love-me --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/863401402/she-love-me.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/she-love-me .cursor/skills/she-love-me && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "she-love-me" agent skill from https://github.com/863401402/she-love-me/tree/main/.agents/skills/she-love-me into .cursor/skills/she-love-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "she-love-me", 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

$ gemini skills install https://github.com/863401402/she-love-me.git --path .agents/skills/she-love-me

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add 863401402/she-love-me --skill she-love-me -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install 863401402/she-love-me she-love-me --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/863401402/she-love-me.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/she-love-me .gemini/skills/she-love-me && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "she-love-me" agent skill from https://github.com/863401402/she-love-me/tree/main/.agents/skills/she-love-me into .gemini/skills/she-love-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "she-love-me", 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.

GitHub CLI

$ gh skill install 863401402/she-love-me she-love-me

Installs 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).

skills CLI

$ npx skills add 863401402/she-love-me --skill she-love-me -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/863401402/she-love-me.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/she-love-me .github/skills/she-love-me && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "she-love-me" agent skill from https://github.com/863401402/she-love-me/tree/main/.agents/skills/she-love-me into .github/skills/she-love-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "she-love-me", 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.

skills CLI

$ npx skills add 863401402/she-love-me --skill she-love-me -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install 863401402/she-love-me she-love-me --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/863401402/she-love-me.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/she-love-me .opencode/skills/she-love-me && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "she-love-me" agent skill from https://github.com/863401402/she-love-me/tree/main/.agents/skills/she-love-me into .opencode/skills/she-love-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "she-love-me", 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.

Facts

Skill name: she-love-me
GitHub stars: 931
Used in: 1 other repo
Token cost: ~1.3k tokens
SKILL.md length: 315 words
Files: 8 (incl. references)
Skills in repo: 1
Repo updated: Oct 1, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Acquire, import, and analyze WeChat or QQ chat histories, including installing supported exporters, guiding required login or contact selection, converting exports, assessing relationship dynamics…

Works in 6 steps: 数据来源选择 → 统计分析 → 5: 采样范围选择 → …
The user asks to export
SKILL.md covers Prerequisites（用户需先完成）, 执行步骤（严格按顺序） and 错误处理
Needs QCE_TOKEN

What it does

She Love Me is an agent skill from 863401402/she-love-me. Acquire, import, and analyze WeChat or QQ chat histories, including installing supported exporters, guiding required login or contact selection, converting exports, assessing relationship dynamics and risk signals, and generating a structured Chinese HTML report. Use when the user asks to export, import, or analyze WeChat/QQ chats or requests relationship analysis from message history.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `agents/openai.yaml`, `references/analysis-framework.md` and `references/data-sources.md`).

It sits in Productivity & Automation, covering Messaging and chat bots. It works with WeChat. The repository describes itself as: 她不一样恋情分析室 — 微信聊天记录恋爱分析 Agent Skill （曾用名：她爱我吗？）. The licence is MIT.

When your agent uses it

The user asks to export
Analyze WeChat/QQ chats
Requests relationship analysis from message history

Example prompts

“/she-love-me”

Requirements

Python 3
Node.js
A credential in QCE_TOKEN

Workflow steps

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

数据来源选择
统计分析
5: 采样范围选择
AI 深度鉴定（核心）
生成报告
展示结论

What it can do on your machine

Read from SKILL.md and the folder at commit 80aec1d. 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 bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- QCE_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

She Love Me loads about 1.3k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 100 tokens; SKILL.md has 315 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~100
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~15k

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 863401402/she-love-me at commit 80aec1d, republished under its MIT licence (© 863401402). 315 words, ~1,339 tokens.

Download SKILL.mdSave it as .claude/skills/she-love-me/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.

name: she-love-me
description: Acquire, import, and analyze WeChat or QQ chat histories, including installing supported exporters, guiding required login or contact selection, converting exports, assessing relationship dynamics and risk signals, and generating a structured Chinese HTML report. Use when the user asks to export, import, or analyze WeChat/QQ chats or requests relationship analysis from message history.

她不一样

你是「她不一样」的首席分析师兼关系心理顾问，融合专业恋爱心理学框架，帮助用户从聊天记录中看清这个人真实的样子——而不是理想化的投影——以及这段关系真正在走向哪里。

⚠️ 提醒机制：若分析发现严重的单向投入（对称性评分 ≤ 3）、单相思痴迷（Limerence）或情感创伤绑定迹象，必须在报告中单独高亮提醒用户，直接指出问题并给出止损建议。

工作目录：始终使用当前项目的根目录（包含 scripts/ 和 .agents/ 的目录），不要硬编码绝对路径。 临时文件目录：任何临时生成的文件放置在 scripts/tmp/（已加入 .gitignore）。

Prerequisites（用户需先完成）

Python 3.9+
微信/QQ 处于运行 + 登录状态
Windows 微信默认导出路径需要 Node.js 18+ 和管理员终端
从 GitHub 新 clone 时不要运行 setup_check.py --ensure-decryptor：默认上游已被 DMCA 屏蔽

执行步骤（严格按顺序）

Step 0: 数据来源选择

向用户确认数据来源：「Windows 微信本机、QQ、已有 JSON，还是 Markdown？」

Windows 微信本机：读取并严格执行 .agents/skills/she-love-me/references/data-sources.md。Agent 必须端到端完成环境检查、下载安装、初始化、列会话、导出和转换；首选 weflow-cli，失败自动回退 CipherTalk CLI，再回退官方桌面 MCP。仅在登录、管理员授权、桌面账号配置或联系人选择时等待用户。
QQ：执行下方 QQ 路径。
已有 JSON / Markdown / 兼容解密器：读取并执行 data-sources.md 对应章节。

所有路径完成后必须取得转换器或提取器返回的 bundle_dir 和 messages_path，再进入 Step 6。不要硬编码 data/messages.json，不要把聊天数据移出 data/。

══════════════ QQ 路径 ══════════════

Step QQ-1: 获取 QCE Token

向用户说明前置操作，等待用户提供 Token：

QQ 分析需要先启动 QQ Chat Exporter (QCE)。如果你还没安装：

去 Releases 下载 NapCat-QCE-Windows-x64-vxxx.zip

解压后双击 launcher-user.bat，用手机 QQ 扫码登录

控制台出现 Token: xxxxx 后，复制那串 Token

「请粘贴你的 QCE Access Token（在 QCE 控制台或 %USERPROFILE%\.qq-chat-exporter\security.json 的 accessToken 字段中）：」

将 token 保存为 $QCE_TOKEN，端口默认 40653。

Step QQ-2: 列出 QQ 好友

bash

<PYTHON> scripts/list_contacts_qq.py --token "$QCE_TOKEN" --top 30

报错 "无法连接到 QCE 服务" → 提示用户确认 QCE 已启动并 Token 正确。

Step QQ-3: 用户选择联系人（QQ 专用）

向用户展示好友列表，等待选择：「请选择要分析的联系人（输入名字、备注或 QQ 号）：」

Step QQ-4: 提取 QQ 消息

bash

<PYTHON> scripts/extract_messages_qq.py \
  --token "$QCE_TOKEN" \
  --contact "<用户选择的联系人名字/QQ号>" \
  --output-dir data/contacts

找不到联系人 → 建议直接用 QQ 号（纯数字）。导出完成后自动转换为统一的 messages.json 格式，并放入联系人独立目录；后续步骤与微信相同。

══════════════ 共同路径（Step 6 起） ══════════════

Step 6: 统计分析

bash

<PYTHON> scripts/stats_analyzer.py \
  --input "<messages_path>" \
  --output "<bundle_dir>/stats.json"

读取 <bundle_dir>/stats.json，获取全量统计数据。

Step 6.5: 采样范围选择

阶段 1：预扫描，向用户展示时间范围与消息条数，等待选择：

bash

<PYTHON> scripts/build_chat_history.py --input "<messages_path>" --preview

输出 JSON 包含各时间范围的条数和推荐项。向用户展示（格式示例）：

请选择分析的时间范围：
  1. 最近 1 个月（420 条）
  2. 最近 3 个月（1850 条）⭐ 推荐
  3. 最近半年（3200 条）
  4. 全量（8234 条，2024-06-15 ~ 今天）

等待用户选择后，阶段 2：生成分层采样文件：

bash

<PYTHON> scripts/build_chat_history.py \
  --input "<messages_path>" \
  --output "<bundle_dir>/chat_history.txt" \
  --since <用户选择对应的 date_from>

如果用户选择全量，省略 --since 参数。

Step 7: AI 深度鉴定（核心）

读取以下两个文件：

<bundle_dir>/stats.json — 全量统计数据（消息频率、回复时间、情绪词、语言学特征等）
<bundle_dir>/chat_history.txt — 分层采样的关键窗口（关系起源 / 高冲突区间 / 最近30天 / 修复时刻）

统计层已覆盖全量，叙事分析基于采样窗口 + 统计数据综合判断，不要仅凭窗口内的消息下结论。

分析顺序：F → A → B → C → D → E → G

模块 F 是所有模块的基础——只有真正理解了「这两个人」，才能准确判断「这段关系」。

📖 完整分析框架：读取 .agents/skills/she-love-me/references/analysis-framework.md（模块 F + A + B） 🚨 危险预警定义：读取 .agents/skills/she-love-me/references/risk-signals.md（模块 C） 🎯 军师与语气风格：读取 .agents/skills/she-love-me/references/strategist-guide.md（模块 D + E + G） 📋 输出 JSON schema：读取 .agents/skills/she-love-me/references/report-schema.md

5 条执行铁律（不可忽略）：

无证据不诊断 — 所有心理学推断必须引用带时间戳的原话作为锚点
高亮预警优先 — 危险预警仅当量化条件与文本条件同时满足时触发（见 .agents/skills/she-love-me/references/risk-signals.md 双阈值规则）
先叙事，后框架 — 描述鉴定师「看到」的画面，再引入理论名词
防御语言是金矿 — 「不合适」「随便」「来者不拒」永远追问：这句话保护了什么？想让对方做什么？
证据不足留白 — 对于 partner_attachment、core_fear、trauma_bonding、future_faking、fatal_mistake、advancement_path 等字段，若无充分证据支撑，输出 {"value": null, "evidence_level": "insufficient", "reason": "..."} 而非强行推断

将完整分析结果保存到 <bundle_dir>/analysis.json。

Step 8: 生成报告

bash

<PYTHON> scripts/generate_html_report.py \
  --stats "<bundle_dir>/stats.json" \
  --analysis "<bundle_dir>/analysis.json" \
  --contact "<联系人名字>" \
  --output "<bundle_dir>/reports/"

Step 9: 展示结论

用 Markdown 格式向用户展示鉴定摘要。

📋 展示模板：读取 .agents/skills/she-love-me/references/report-template.md

错误处理

错误	处理
管理员权限错误	Windows：提示以管理员身份重开终端
macOS 权限错误	提示检查终端系统权限并重新运行
微信未运行	提示用户打开微信
找不到联系人	列出相似名字供用户重新选择
数据库解密失败	检查 `vendor/wechat-decrypt/config.json` 中的 `db_dir`
自动下载解密器失败 / HTTP 451	改用 weflow-cli、CipherTalk CLI 或官方桌面 MCP 导出 JSON；WeFlow 仅用于已有旧 JSON，不使用来源不明镜像
毫秒级时间戳	导入与统计脚本会自动归一化为秒，无需手工转换
语音消息	仅在数据源含 `transcript` / `voice_transcript` 时分析转写文本；当前不直接识别音频文件
messages.json 不存在	提示先运行 Step 5 提取消息
用户要看表情但 `messages.json` 无 `emoji` 元信息	重新运行 Step 5，确认使用的是最新 `scripts/extract_messages.py`
表情下载失败	查看 `<bundle_dir>/emojis_download_manifest.json`；常见原因是 CDN 链接失效或超时
不同联系人数据互相覆盖	必须使用 `--output-dir data/contacts`，并继续沿用 Step 5 返回的 `bundle_dir`

Files

SKILL.md and 7 other files (references) in .agents/skills/she-love-me of 863401402/she-love-me.

SKILL.md
agents/openai.yaml
references/analysis-framework.md
references/data-sources.md
references/report-schema.md
references/report-template.md
references/risk-signals.md
references/strategist-guide.md

Open the folder on GitHubat commit 80aec1d

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in 863401402/she-love-me, which our catalogue first saw on October 7, 2026.

NeverSight/learn-skills.devdata/skills-md/863401402/she-love-me/she-love-me

Compare with similar skills

She Love Me 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.

She Love Me compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
She Love Me this skill863401402/she-love-me	931	1 repos	~1.3k	Automated safety check: Pass	MIT	9 days ago
Wechat Article Extractorfreestylefly/wechat-article-extractor-skill	136	1 repos	~1k	Automated safety check: Pass	None	7 mo ago
Wechat Miniprogram Builderchenjin-cmd/wechat-miniprogram-builder	356	—	~634	Automated safety check: Pass	MIT	2 mo ago
Skill Wechat PublisherZJU-REAL/Easel	3.4k	—	~1.8k	Automated safety check: Pass	Apache-2.0	today
Wechat Mp Writerth3ee9ine/wechat-claw-skill	207	—	~1.4k	Automated safety check: Pass	MIT	6 mo ago
Qiaomu Wx Videojoeseesun/qiaomu-wx-video	135	—	~751	Automated safety check: Pass	MIT	2 mo ago

Similar skills

Wechat Article Extractor
freestylefly/wechat-article-extractor-skill
Extract metadata and content from WeChat Official Account articles.
136 GitHub starsUsed in 1 repo~1k tokens
Productivity & AutomationAuto-check passed
Wechat Miniprogram Builder
chenjin-cmd/wechat-miniprogram-builder
This skill should be used when the user wants to build, launch, monetize, or promote a WeChat mini-program with AI (vibe coding) — including topic selection, account registration & ICP filing…
356 GitHub stars~634 tokensUpdated 2 mo ago
Productivity & AutomationAuto-check passed
Skill Wechat Publisher
ZJU-REAL/Easel
微信公众号文章自动创作与发布工具。给定参考文章、文字或文档，自动搜索整理全网相关信息、生成图文并茂的公众号文章，并发布到微信公众号草稿箱。特别强调反 AI 检测写作。
3.4k GitHub stars~1.8k tokensUpdated today
Productivity & AutomationAuto-check passed
Wechat Mp Writer
th3ee9ine/wechat-claw-skill
微信公众号文章全自动写作与发布。从信息搜集、AI配图规划、报刊级 HTML 排版、到草稿创建和发布的完整流程。适用于 AI 日报、财经周报、深度分析、新闻资讯类文章。内置多种模板，并提供本地渲染、校验、图片规划和发布流水线脚本。
207 GitHub stars~1.4k tokensUpdated 6 mo ago
Productivity & AutomationAuto-check passed
Qiaomu Wx Video
joeseesun/qiaomu-wx-video
Qiaomu skill and workflow for downloading a WeChat Channels / 视频号 video or generated live replay when the user provides a weixin.qq.com/sph share link.
135 GitHub stars~751 tokensUpdated 2 mo ago
Productivity & AutomationAuto-check passed
Xiaohu Wechat Cover
xiaohuailabs/xiaohu-wechat-format
公众号封面图生成器。一步出图，输入文章路径或主题即可。当用户要求'公众号封面''微信封面''文章封面'时使用. An agent skill from xiaohuailabs/xiaohu-wechat-format.
699 GitHub stars~545 tokensUpdated 4 mo ago
Productivity & AutomationAuto-check passed

Works with

WeChat

Questions about She Love Me

What does She Love Me do?

Acquire, import, and analyze WeChat or QQ chat histories, including installing supported exporters, guiding required login or contact selection, converting exports, assessing relationship dynamics…. She Love Me is an agent skill from 863401402/she-love-me. Acquire, import, and analyze WeChat or QQ chat histories, including installing supported exporters, guiding required login or contact selection, converting exports, assessing relationship dynamics and risk signals, and generating a structured Chinese HTML report.

When should I use She Love Me?

She Love Me fits situations like: the user asks to export; analyze WeChat/QQ chats; requests relationship analysis from message history.

How do I install She Love Me in Claude Code?

Run `npx skills add 863401402/she-love-me --skill she-love-me -a claude-code`. Or copy the skill folder (.agents/skills/she-love-me in 863401402/she-love-me) into .claude/skills/she-love-me in your project. Claude Code loads it when a task matches its description.

How do I install She Love Me in Codex?

Run `npx skills add 863401402/she-love-me --skill she-love-me -a codex`. Or copy the skill folder (.agents/skills/she-love-me in 863401402/she-love-me) into .agents/skills/she-love-me in your project. Codex loads it when a task matches its description.

Can I use She Love Me 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 863401402/she-love-me --skill she-love-me -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/she-love-me, .gemini/skills/she-love-me, .github/skills/she-love-me and .opencode/skills/she-love-me in your project.

What does She Love Me need to run?

Going by SKILL.md and its folder, She Love Me needs credentials named QCE_TOKEN. Our summary lists: Python 3; Node.js; A credential in QCE_TOKEN.

Does She Love Me access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is She Love Me 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 She Love Me use?

She Love Me 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 She Love Me use?

About 1.3k tokens (SKILL.md is roughly 5.4k 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 14k tokens, read only when the agent opens those files.

What are the alternatives to She Love Me?

Skills that share tags, products or a category with She Love Me: Wechat Article Extractor (freestylefly/wechat-article-extractor-skill, 136 stars), Wechat Miniprogram Builder (chenjin-cmd/wechat-miniprogram-builder, 356 stars), Skill Wechat Publisher (ZJU-REAL/Easel, 3.4k stars) and Wechat Mp Writer (th3ee9ine/wechat-claw-skill, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains She Love Me?

863401402 (a GitHub user) maintains it in 863401402/she-love-me, which has 931 GitHub stars. The repository was last updated on October 1, 2026.

Source: 863401402/she-love-me on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install She Love Me

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

她不一样

Prerequisites（用户需先完成）

执行步骤（严格按顺序）

Step 0: 数据来源选择

══════════════ QQ 路径 ══════════════

Step QQ-1: 获取 QCE Token

Step QQ-2: 列出 QQ 好友

Step QQ-3: 用户选择联系人（QQ 专用）

Step QQ-4: 提取 QQ 消息

══════════════ 共同路径（Step 6 起） ══════════════

Step 6: 统计分析

Step 6.5: 采样范围选择

Step 7: AI 深度鉴定（核心）

Step 8: 生成报告

Step 9: 展示结论

错误处理

Files

Used in 1 other repository

Compare with similar skills

Similar skills

Wechat Article Extractor

Wechat Miniprogram Builder

Skill Wechat Publisher

Wechat Mp Writer

Qiaomu Wx Video

Xiaohu Wechat Cover

Related

Questions about She Love Me