Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计异常

fix-posthog修复 posthog

Agent Skill

fix-posthog 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

470

周安装

20

GitHub Stars

8

下载量

165
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:fix-posthog(修复 posthog)
来源仓库:https://github.com/phrazzld/claude-config
仓库路径:skills/fix-posthog
安装命令:
npx skills add https://github.com/phrazzld/claude-config --skill fix-posthog
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/phrazzld/claude-config --skill fix-posthog

简介

fix-posthog 用于查找、检索和筛选相关信息。

  • 适合在事件追踪或数据分析相关任务中使用。
  • 通过 npx skills add 命令从 phrazzld/claude-config 仓库安装。
  • 需确认是否访问 PostHog 实例或发送埋点数据。
  • 建议检查数据合规性和隐私政策。fix-posthog 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

/fix-posthog

Run /check-posthog, then fix the highest priority issue.

What This Does

  1. Run /check-posthog to identify issues
  2. Pick the highest priority unfixed issue
  3. Implement the fix
  4. Verify the fix works
  5. Report what was fixed

Fixes one issue per invocation. Run multiple times to fix multiple issues.

Fix Playbook

P0: SDK Not Initialized

Problem: initPostHog() not called or PostHogProvider missing.

Fix:

codex exec --full-auto "Add PostHog initialization. \
Create lib/analytics/posthog.ts with initPostHog(). \
Create PostHogProvider component. \
Add to app/layout.tsx. \
Reference: ~/.claude/skills/posthog/references/sdk-patterns.md. \
Verify: pnpm typecheck" \
--output-last-message /tmp/codex-fix.md 2>/dev/null

P0: API Key Missing

Problem: NEXT_PUBLIC_POSTHOG_KEY not set.

Fix:

# Get key from PostHog dashboard
# Add to .env.local
echo "NEXT_PUBLIC_POSTHOG_KEY=phc_xxx" >> .env.local

# Add to Vercel production
printf '%s' 'phc_xxx' | vercel env add NEXT_PUBLIC_POSTHOG_KEY production

P1: No Reverse Proxy

Problem: Direct PostHog host gets blocked by ad blockers.

Fix:

codex exec --full-auto "Add PostHog reverse proxy to next.config. \
Add rewrites for /ingest/* to us.i.posthog.com/*. \
Add rewrites for /ingest/static/* to us-assets.i.posthog.com/static/*. \
Update posthog.init to use api_host: '/ingest'. \
Reference: ~/.claude/skills/posthog/references/sdk-patterns.md section 4. \
Verify: pnpm build" \
--output-last-message /tmp/codex-fix.md 2>/dev/null

P1: Privacy Masking Missing

Problem: mask_all_text and maskAllInputs not configured.

Fix:

codex exec --full-auto "Add privacy settings to PostHog init. \
Add mask_all_text: true. \
Add session_recording.maskAllInputs: true. \
Add person_profiles: 'identified_only'. \
Reference: ~/.claude/skills/posthog/references/privacy-checklist.md. \
Verify: pnpm typecheck" \
--output-last-message /tmp/codex-fix.md 2>/dev/null

P1: PII in identify() Calls

Problem: Email/name passed to posthog.identify().

Fix:

codex exec --full-auto "Remove PII from posthog.identify calls. \
Only pass user ID, no email/name/phone properties. \
Search: grep -rE 'posthog.identify.*email|identify.*name' --include='*.ts' --include='*.tsx'. \
Verify: pnpm typecheck && grep -rE 'posthog.identify.*email' returns no results" \
--output-last-message /tmp/codex-fix.md 2>/dev/null

P2: No Standard Events

Problem: No typed event schema defined.

Fix:

codex exec --full-auto "Add typed event schema to PostHog analytics. \
Create StandardEvent type with: user_signed_up, user_activated, subscription_started, subscription_cancelled, feature_used. \
Add trackEvent function that enforces type. \
Reference: ~/.claude/skills/posthog/references/sdk-patterns.md section 1. \
Verify: pnpm typecheck" \
--output-last-message /tmp/codex-fix.md 2>/dev/null

Verification

After each fix, verify with MCP:

# Check events are flowing
mcp__posthog__query-run with TrendsQuery for last 1h

# Check for errors
mcp__posthog__list-errors

Manual browser verification:

  1. Open DevTools → Network
  2. Filter for ingest or posthog
  3. Trigger action → verify request succeeds
  4. Check PostHog Live Events → verify event appears

Output

After fixing, report:

  • What was fixed
  • How it was verified
  • What's the next priority issue (if any)

Related

  • /check-posthog - Audit only (no fixes)
  • /log-posthog-issues - Create GitHub issues
  • /posthog - Full lifecycle workflow

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.49%
按下载量换算60

Claude

30.66%
按下载量换算51

Cursor

19.91%
按下载量换算33

Gemini CLI

10.08%
按下载量换算17

安全审计

Gen Agent Trust Hub

可疑

Socket

可疑

Snyk

未通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills