Agent skill

Detection Signals

Add, adjust or remove "China user" detection signals in the FuckClaude project (browser scan + /api/check).

MITAuto-check passed

Install Detection Signals

skills CLI

$ npx skills add LinXiaoTao/FuckClaude --skill detection-signals -a claude-code

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

GitHub CLI

$ gh skill install LinXiaoTao/FuckClaude detection-signals --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/LinXiaoTao/FuckClaude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/detection-signals .claude/skills/detection-signals && 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 "detection-signals" agent skill from https://github.com/LinXiaoTao/FuckClaude/tree/master/skills/detection-signals into .claude/skills/detection-signals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "detection-signals", 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/LinXiaoTao/FuckClaude/tree/master/skills/detection-signals

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 LinXiaoTao/FuckClaude --skill detection-signals -a codex

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

GitHub CLI

$ gh skill install LinXiaoTao/FuckClaude detection-signals --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/LinXiaoTao/FuckClaude.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/detection-signals .agents/skills/detection-signals && 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 "detection-signals" agent skill from https://github.com/LinXiaoTao/FuckClaude/tree/master/skills/detection-signals into .agents/skills/detection-signals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "detection-signals", 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 LinXiaoTao/FuckClaude --skill detection-signals -a cursor

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

GitHub CLI

$ gh skill install LinXiaoTao/FuckClaude detection-signals --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/LinXiaoTao/FuckClaude.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/detection-signals .cursor/skills/detection-signals && 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 "detection-signals" agent skill from https://github.com/LinXiaoTao/FuckClaude/tree/master/skills/detection-signals into .cursor/skills/detection-signals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "detection-signals", 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/LinXiaoTao/FuckClaude.git --path skills/detection-signals

--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 LinXiaoTao/FuckClaude --skill detection-signals -a gemini-cli

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

GitHub CLI

$ gh skill install LinXiaoTao/FuckClaude detection-signals --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/LinXiaoTao/FuckClaude.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/detection-signals .gemini/skills/detection-signals && 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 "detection-signals" agent skill from https://github.com/LinXiaoTao/FuckClaude/tree/master/skills/detection-signals into .gemini/skills/detection-signals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "detection-signals", 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 LinXiaoTao/FuckClaude detection-signals

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 LinXiaoTao/FuckClaude --skill detection-signals -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/LinXiaoTao/FuckClaude.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/detection-signals .github/skills/detection-signals && 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 "detection-signals" agent skill from https://github.com/LinXiaoTao/FuckClaude/tree/master/skills/detection-signals into .github/skills/detection-signals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "detection-signals", 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 LinXiaoTao/FuckClaude --skill detection-signals -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 LinXiaoTao/FuckClaude detection-signals --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/LinXiaoTao/FuckClaude.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/detection-signals .opencode/skills/detection-signals && 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 "detection-signals" agent skill from https://github.com/LinXiaoTao/FuckClaude/tree/master/skills/detection-signals into .opencode/skills/detection-signals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "detection-signals", 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: detection-signals
GitHub stars: 1k
Token cost: ~716 tokens
SKILL.md length: 151 words
Files: 1
Skills in repo: 1
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Add, adjust or remove "China user" detection signals in the FuckClaude project (browser scan + /api/check).

Works in 5 steps: signals.ts → i18n/ui.ts(en + zh 两份都要) → pages/api/check.ts(仅当服务端可测) → …
Adding detection methods
SKILL.md covers 信号解剖(src/config/signals.ts), 新增一个信号的完整清单, 打分约定 and 验证(必做), plus 1 more section
Calls pnpm and curl

What it does

Detection Signals is an agent skill from LinXiaoTao/FuckClaude. Add, adjust or remove "China user" detection signals in the FuckClaude project (browser scan + /api/check). Use when adding detection methods, changing signal weights or scorers, or when the user mentions 检测信号 / 检测手段 / 新增检测 / signals / weights / detectors.

Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is MIT.

When your agent uses it

Adding detection methods
Changing signal weights
The user mentions 检测信号 / 检测手段 / 新增检测 / signals / weights / detectors

Example prompts

“China user”
“/detection-signals”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

signals.ts
i18n/ui.ts(en + zh 两份都要)
pages/api/check.ts(仅当服务端可测)
layouts/BaseLayout.astro:JSON-LD featureList 追加 t('signal..name')。
README.md:英文与中文两张「信号与权重」表、API 段落的可测权重描述。

What it can do on your machine

Read from SKILL.md and the folder at commit e4aadac. 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
Shell commands in SKILL.md call:
- pnpm
- curl
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pnpm and curl, which can reach the network depending on how they are called.
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

Detection Signals loads about 716 tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 151 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~69
When it runs · the whole SKILL.md, loaded when a task matches: ~716

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 LinXiaoTao/FuckClaude at commit e4aadac, republished under its MIT licence (© LinXiaoTao). 151 words, ~716 tokens.

Download SKILL.mdSave it as .claude/skills/detection-signals/SKILL.md (or your agent's skills folder).

name: detection-signals
description: Add, adjust or remove "China user" detection signals in the FuckClaude project (browser scan + /api/check). Use when adding detection methods, changing signal weights or scorers, or when the user mentions 检测信号 / 检测手段 / 新增检测 / signals / weights / detectors.

检测信号(Detection Signals)开发

本项目的核心是一组「中国用户」指纹信号:浏览器端跑扫描动画逐项检测,服务端 /api/check 复用同一批纯评分函数做估算。所有检测只读浏览器 API,零上传。

信号解剖(src/config/signals.ts)

export type SignalId = 'timezone' | /* … */ | 'emoji'; // 先扩展联合类型

interface SignalDef {
  id: SignalId;
  weight: number;        // 所有信号权重之和必须恰好 = 100
  claudeUsed?: boolean;  // 仅当 Claude Code 真实机制读取该信号时为 true
  icon: string;          // 内联 SVG(24×24, stroke=currentColor, 复用 ICON 表)
  detect: () => DetectOutcome | Promise<DetectOutcome>; // 支持 async(如 UA-CH 高熵值)
}

interface DetectOutcome {
  raw: string;   // 展示给用户的检测值,如 'Asia/Shanghai'、'none detected'
  score: number; // 0..1 的「中国相似度」;≥0.25 记为命中,≥0.6 为 high
}

detect() 内部禁止网络请求;异常无需自行兜底,调用方 detect.ts 已 try/catch。
探测字体用现成的 isFontAvailable(font, ctx)(canvas 宽度探测)。
读 UA-CH 用 uaData() helper;高熵值(model 等)需 await getHighEntropyValues,拿不到时降级为纯 UA 正则。

新增一个信号的完整清单

signals.ts
- SignalId 联合类型加新 id。
- 写 detectXxx();若服务端(仅凭请求头)也能测,把纯打分逻辑抽成 export function scoreXxx(probe: string) 供 API 复用(参照 scoreTimezone / scoreLanguages / scoreCnBrowser / scoreCnDevice)。
- 在 SIGNALS 数组按权重降序插入,并重新分配权重使总和 = 100。
- 图标加进 ICON 表(线性 stroke 风格,与现有一致)。
i18n/ui.ts(en + zh 两份都要)
- 新增 signal.<id>.name 与 signal.<id>.desc。
- 以下文案硬编码了信号数量,改动数量时同步更新: signals.sub(N 项指纹)、how.p2(N-1 项叠加指纹列表)、faq.a2(其余 N-1 项)。
pages/api/check.ts(仅当服务端可测)
- analyze() 的 measured map 增加条目,复用第 1 步导出的纯评分函数。
- 更新文件头注释与 note 里的 browser-only 列表及可测权重数(当前 62/100)。
layouts/BaseLayout.astro:JSON-LD featureList 追加 t('signal.<id>.name')。
README.md:英文与中文两张「信号与权重」表、API 段落的可测权重描述。

打分约定

决定性证据(如系统时区命中中国时区、检出国产厂商字体)→ score 接近 1。
全球化品牌 / 弱相关线索(如小米设备、emoji 风格)→ 0.4–0.7,并压低 weight。
检不到 / 不适用 → { raw: 'none detected', score: 0 },不要抛错。
阈值语义:signalVerdict — ≥0.6 high、≥0.25 medium(命中)、其余 low。

验证(必做)

bash

pnpm build                 # tsc + astro 构建必须通过
pnpm dev                   # http://localhost:4321

浏览器打开 /zh/ 点「开始检测」,确认新信号出现、动画逐项走完、总分 ≤100。
服务端可测信号用伪造 UA 验证,例如:

bash

curl -s "http://localhost:4321/api/check?format=json" \
  -H "User-Agent: Mozilla/5.0 (Linux; Android 12; HarmonyOS; NOH-AN00) MicroMessenger/8.0.47" \
  -H "Accept-Language: zh-CN,zh;q=0.9"

检查 JSON 里新信号 measured: true、coverage.measuredWeight 与注释一致。

常见陷阱

权重总和 ≠ 100:总分语义会坏掉(README 与文案都声称满分 100)。
只改了英文文案忘了中文(或反之):ui.ts 是 en/zh 双份字典。
服务端 scorer 与浏览器 detect 各写一套逻辑导致结果漂移:必须共用纯函数。
UA 正则过宽误伤(如 /mi/ 会匹配 "Mozilla"):用 \b 边界并放到真机 UA 上验证。

Files

Just SKILL.md in skills/detection-signals of LinXiaoTao/FuckClaude.

Open the folder on GitHubat commit e4aadac

Compare with similar skills

Detection Signals 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.

Detection Signals compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Detection Signals this skillLinXiaoTao/FuckClaude	1k	—	~716	Automated safety check: Pass	MIT	2 days ago
Signals Scout Anomaly DetectionPostHog/posthog	40k	—	~4.6k	Automated safety check: Pass	Custom licence	today
Detecting Pv Signalsmaziyarpanahi/openmed	5.5k	—	~2.3k	Automated safety check: Pass	Apache-2.0	today
Trader Signalruvnet/ruflo	74k	—	~605	Automated safety check: Notes	MIT	today
SignalsPostHog/posthog	40k	—	~4.3k	Automated safety check: Pass	Custom licence	today
Signal Detection Pipelinegooseworks-ai/goose-skills	1.2k	1 repos	~608	Automated safety check: Pass	MIT	yesterday

Similar skills

Signals Scout Anomaly Detection
PostHog/posthog
Official
Signals scout that watches the project's most-viewed dashboards and insights for anomalies — bursts, drops, flat-lines, and trend breaks — against each insight's own seasonality-matched baseline.
40k GitHub stars~4.6k tokensUpdated today
Data & AnalyticsAuto-check passed
Detecting Pv Signals
maziyarpanahi/openmed
Computes disproportionality signals — PRR, ROR, EBGM, and IC (BCPNN) — over FAERS / OpenFDA drug-event data to flag potential safety signals.
5.5k GitHub stars~2.3k tokensUpdated today
Auto-check passed
Trader Signal
ruvnet/ruflo
Generate trading signals using npx neural-trader anomaly detection engine with Z-score scoring and neural prediction
74k GitHub stars~605 tokensUpdated today
Data & AnalyticsAuto-check: notes
Signals
PostHog/posthog
Official
How to query the documentembeddings table for raw signal data using HogQL.
40k GitHub stars~4.3k tokensUpdated today
AI & LLM EngineeringAuto-check passed
Signal Detection Pipeline
gooseworks-ai/goose-skills
Detect buying signals from multiple sources, qualify leads, and generate outreach context
1.2k GitHub starsUsed in 1 repo~608 tokens
Auto-check passed
Signal Detection Analysis
NeuroAIHub/BrainPilot
Domain-validated decision logic, formulas, and interpretation guidelines for applying Signal Detection Theory to cognitive science data
1.1k GitHub stars~4k tokensUpdated 8 days ago
Auto-check passed

Questions about Detection Signals

What does Detection Signals do?

Add, adjust or remove "China user" detection signals in the FuckClaude project (browser scan + /api/check). Detection Signals is an agent skill from LinXiaoTao/FuckClaude. Add, adjust or remove "China user" detection signals in the FuckClaude project (browser scan + /api/check).

When should I use Detection Signals?

Detection Signals fits situations like: adding detection methods; changing signal weights; the user mentions 检测信号 / 检测手段 / 新增检测 / signals / weights / detectors.

How do I install Detection Signals in Claude Code?

Run `npx skills add LinXiaoTao/FuckClaude --skill detection-signals -a claude-code`. Or copy the skill folder (skills/detection-signals in LinXiaoTao/FuckClaude) into .claude/skills/detection-signals in your project. Claude Code loads it when a task matches its description.

How do I install Detection Signals in Codex?

Run `npx skills add LinXiaoTao/FuckClaude --skill detection-signals -a codex`. Or copy the skill folder (skills/detection-signals in LinXiaoTao/FuckClaude) into .agents/skills/detection-signals in your project. Codex loads it when a task matches its description.

Can I use Detection Signals 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 LinXiaoTao/FuckClaude --skill detection-signals -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/detection-signals, .gemini/skills/detection-signals, .github/skills/detection-signals and .opencode/skills/detection-signals in your project.

What does Detection Signals need to run?

Going by SKILL.md and its folder, Detection Signals needs the command-line tools its instructions call (pnpm and curl).

Does Detection Signals access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Detection Signals 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 Detection Signals use?

Detection Signals 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 Detection Signals use?

About 716 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Detection Signals?

Skills that share tags, products or a category with Detection Signals: Signals Scout Anomaly Detection (PostHog/posthog, 40k stars), Detecting Pv Signals (maziyarpanahi/openmed, 5.5k stars), Trader Signal (ruvnet/ruflo, 74k stars) and Signals (PostHog/posthog, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Detection Signals?

LinXiaoTao (a GitHub user) maintains it in LinXiaoTao/FuckClaude, which has 1,030 GitHub stars. The repository was last updated on October 8, 2026.

Source: LinXiaoTao/FuckClaude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Detection Signals

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

检测信号(Detection Signals)开发

信号解剖(src/config/signals.ts)

新增一个信号的完整清单

打分约定

验证(必做)

常见陷阱

Files

Compare with similar skills

Similar skills

Signals Scout Anomaly Detection

Detecting Pv Signals

Trader Signal

Signals

Signal Detection Pipeline

Signal Detection Analysis

Questions about Detection Signals